WO2019222860A1

WO2019222860A1 - System, method and/or computer readable medium for growing plants in an autonomous green house

Info

Publication number: WO2019222860A1
Application number: PCT/CA2019/050713
Authority: WO
Inventors: Eric Arthur DUFFUS; Justin Michael THOMSON
Original assignee: Greenearth Automation Inc
Current assignee: Greenearth Automation Inc
Priority date: 2018-05-25
Filing date: 2019-05-24
Publication date: 2019-11-28
Anticipated expiration: 2020-11-25

Abstract

According to the invention, there is disclosed a system, method and/or non-transient computer readable medium for growing plants in a facility autonomously. The system includes an irrigation subsystem associated with the plants, including: (i) one or more spray heads; (ii) a water tank comprising a volume of water; and (iii) a pump adapted to transfer the water to the one or more spray heads to irrigate the plants; Also included is a robotic gardener subsystem including: (i) a chassis; (ii) tools adapted to manipulate the plants; (iii) on-board sensors adapted to receive data associated with the plants; and (iv) a command processor operative to (1) collect and transmit the data associated with the plants and (2) controlling the tools and/or the irrigation subsystem. An AI control system is included having: (i) a server operative to (1) electronically receive the data associated with the plants; (2) apply one or more artificial intelligence algorithms to the data associated with the plants to generate machine learning data and pattern data; (3) generate instructions for the tools and/or the irrigation subsystem based on the machine learning data and pattern data; and (4) transmit the instructions to the command processor; and (ii) a database to electronically store the data associated with the plants, the instructions for the tools and/or the irrigation subsystem, the machine learning data and the pattern data. The system is operative to autonomously optimize the growth of the plants in the facility based on the instructions.

Description

SYSTEM, METHOD AND/OR COMPUTER READABLE MEDIUM FOR GROWING

PLANTS IN AN AUTONOMOUS GREEN HOUSE

FIELD OF THE INVENTION

[0001] The present invention relates generally to methods, systems and/or computer readable media for growing plants, and more specifically to controlled environment agriculture facilities and methods, systems and/or computer readable media for automated plant cultivation in such facilities.

BACKGROUND OF THE INVENTION

[0002] A variety of organizations produce, process or supply cannabaceae plants. These include breweries, licensed cannabis producers, licensed cannabis processors, licensed cannabis suppliers and hops producers. The North American indoor hop industry was valued at USD $618 Million in 2017, with 25% year over year growth since 2014. Global indoor hop production in 2017 was valued at USD $1.2 Billion. In 2017, the North American indoor cannabis industry was valued at USD $17.2 Billion, with 30% growth year over year since 2015. Analysts predict that the global cannabis market in 2018 will be worth approximately USD $42.9 Billion. The entire cannabaceae industry worldwide is worth approximately USD $44.1 Billion. Canada is the only country globally recognized for its legal cannabis production and is positioned to become the global leader in cannabaceae production by 2021.

[0003] Currently the distribution of indoor cannabaceae is divided into three sectors: retail, high-quality wholesale, and low-quality wholesale. Retail distribution is divided into private retail and local markets. High-quality wholesale is divided into processors, suppliers and large government institutions. Low-quality wholesale is primarily reserved for low-cost suppliers and processors. There is a need for advanced facilities positioned to service the retail and high- quality wholesale distribution of cannabaceae by selling fixed-price production contracts and providing turn-key facilities and production systems that produce cannabaceae for suppliers.

[0004] Controlled environment agriculture (“CEA”) is the cultivation of vegetable, ornamental and other plants in an enclosure within which those environmental factors which are generally recognized as influencing plant growth, maturation and productivity, are systematically time-programmed and carefully controlled. Typically the controlled growth factors include the intensity, duration and spectral distribution of illumination, the temperature, humidity and flow rate of the air, its carbon dioxide concentration, and the composition and temperature of the nutrient supplied to the growing plants.

[0005] CEA facilities may be specifically adapted for use in growing the Cannabaceae family of plants, of which the Cannabis plant is one genus. Cannabaceae may be sensitive to their growth conditions and are susceptible to disease and infection. Furthermore, plant growth for medicinal purposes is ideally highly reproducible and controlled. In the prior art, CEA technology is labor intensive (traditionally one of largest input costs in CEA operation) and requires a population base in the community to support such demands. To date, however, CEA facilities only allow for the control of certain environmental parameters and are not able to respond in intelligent ways to dynamic growth conditions while ensuring reproducibility in all aspects of industrial plant growth, namely: growing, harvesting, and packaging.

[0006] The devices, systems, methods and/or computer readable media of the prior art have not been adapted to solve the one or more of the above-identified problems, thus negatively affecting the ability to produce and grow certain plants with precise, repeatable growing conditions to generate predictable yields with low risk of disease and infection, and reduced input costs.

[0007] What may be needed is a CEA facility with low labor requirements that facilitates the control of one or more environmental parameters, an ability to respond to dynamic growth conditions, and/or encourage reproducibility of industrial plant growth.

[0008] It is an object of the present invention to obviate or mitigate one or more of the aforementioned disadvantages and/or shortcoming associated with the prior art, to provide one of the aforementioned needs or advantages, and/or to achieve one or more of the aforementioned objects of the invention.

SUMMARY OF THE INVENTION

[0009] According to the invention, there is disclosed a system for growing plants in a facility. The system includes an irrigation subsystem associated with the plants, including: (i) one or more spray heads; (ii) a water tank comprising a volume of water; and (iii) a pump adapted to transfer the water to the one or more spray heads to irrigate the plants; Also included is a robotic gardener subsystem including: (i) a chassis; (ii) tools adapted to manipulate the plants; (iii) on-board sensors adapted to receive data associated with the plants; and (iv) a command processor operative to (1) collect and transmit the data associated with the plants and (2) controlling the tools and/or the irrigation subsystem. An AI control system is included having: (i) a server operative to (1) electronically receive the data associated with the plants; (2) apply one or more artificial intelligence algorithms to the data associated with the plants to generate machine learning data and pattern data; (3) generate instructions for the tools and/or the irrigation subsystem based on the machine learning data and pattern data; and (4) transmit the instructions to the command processor; and (ii) a database to electronically store the data associated with the plants, the instructions for the tools and/or the irrigation subsystem, the machine learning data and the pattern data. The system is operative to autonomously optimize the growth of the plants in the facility based on the instructions.

[0010] According to an aspect of one preferred embodiment of the invention, the on-board sensors include: a visual detection system; a microscope camera; a sonar sensor; a backscatter detection system; a spectrometer camera; and an atmospheric sensor board.

[0011] According to an aspect of one preferred embodiment of the invention, the data associated with the plants includes: health (including disease and infection), stage of growth, images, video, humidity levels, temperature, oxygen levels, type and intensity of electromagnetic radiation, carbon dioxide levels, and/or plant mass.

[0012] According to an aspect of one preferred embodiment of the invention, the system also includes a growth subsystem for delivering a predetermined nutrient formulation to the plants in the facility. The growth subsystem includes: (a) a biosensor adapted to receive nutrient data associated with the plants; (b) a nutrient supply comprising one or more nutrients; (c) a holding tank for mixing the one or more nutrients with water from the water tank for generating a nutrient formulation; (d) a microcontroller operative to (1) collect and transmit the nutrient data associated with the plants to the AI control system to generate instructions for a predetermined nutrient formulation and (2) receive the instructions from the AI control system for generating the predetermined nutrient formulation in the holding tank; and (e) nutrient lines to deliver the predetermined nutrient formulation to the plants. [0013] According to an aspect of one preferred embodiment of the invention, the system also includes a cable drive subsystem for moving the robotic gardener subsystem along an x-axis, a y- axis and a z-axis within the facility based on instructions generated by the AI control system using data from the visual detection system. The cable drive subsystem includes: (a) a y-axis support beam adapted for moveable engagement with at least two x-axis support beams at a first end and a second end of the y-axis support beam; (b) an x-axis motor associated with the x-axis support beams and operatively connected to the first end of the y-axis support beam; (c) a z-axis support adapted for moveable engagement along the y-axis support beam at a first end of the z- axis support and attached to the robot chassis at a second end of the z-axis support; (d) a y-axis motor associated with the y-axis support beam and operatively connected to the first end of the z- axis support; and (e) a z-axis motor associated with the robot chassis and operatively connected to the second end of the z-axis support. The system is operative to facilitate three-dimensional movement based on selected activation of the x-axis motor, the y-axis motor, and the z-axis motor by the command unit.

[0014] According to an aspect of one preferred embodiment of the invention, the system may be used with plants grown hydroponically, aeroponically or adapted for use with traditional media and irrigation systems.

[0015] According to the invention, there is disclosed a method for optimizing the growth of plants in a facility. The method includes the steps of (a) operating an irrigation subsystem associated with the plants, including: (i) one or more spray heads; (ii) a water tank comprising a volume of water; and (iii) a pump adapted to transfer the water to the one or more spray heads to irrigate the plants; (b) operating a robotic gardener subsystem including: (i) a chassis; (ii) tools adapted to manipulate the plants; (iii) on-board sensors adapted to receive data associated with the plants; and (iv) a command processor operative to (1) collect and transmit the data associated with the plants and (2) controlling the tools and/or the irrigation subsystem; (c) operating an AI control system including: (i) a server operative to electronically receive the data associated with the plants to: (1) apply one or more artificial intelligence algorithms to the data associated with the plants to generate machine learning data and pattern data; (2) generate instructions for the tools and/or the irrigation subsystem based on the machine learning data and pattern data; and (3) transmit the instructions to the command processor; and (ii) a database to electronically store the data associated with the plants, the instructions for the tools, the machine learning data and the pattern data. The data associated with the plants and the instructions for the tools and/or the irrigation subsystem based on the machine learning data and pattern data are for use in autonomously optimizing the growth of the plants in the facility.

[0016] According to the invention, there is provided a non-transient computer readable medium on which is physically stored executable instructions for use in association with a facility for growing plants. The facility includes: (1) an irrigation subsystem comprising (i) one or more spray heads; (ii) a water tank comprising a volume of water; and (iii) a pump adapted to transfer the water to the one or more spray heads to irrigate the plants; (2) a robotic gardener subsystem comprising: (i) tools adapted to manipulate the plants; (ii) on-board sensors; and (iii) a command processor; and (3) an AI control system comprising a server. The AI control system automatically collects and/or electronically communicates data associated with the plants from the command processor to the server; applies one or more artificial intelligence algorithms to the data associated with the plants to generate machine learning data and pattern data; generates instructions for the tools and/or the irrigation subsystem based on the machine learning data and pattern data; communicates the instructions to the command processor; and electronically stores the data associated with the plants, the instructions for the tools and/or the irrigation subsystem, the machine learning data and the pattern data. The data associated with the plants and the instructions for the tools and/or the irrigation subsystem are for use in autonomously optimizing the growth of the plants in the facility.

[0017] Other advantages, features and characteristics of the present invention, as well as methods of operation and functions of the related elements of the system, method, device and computer readable medium, and the combination of steps, parts and economies of manufacture, will become more apparent upon consideration of the following detailed description and the appended claims with reference to the accompanying drawings, the latter of which are briefly described herein below.

BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The novel features which are believed to be characteristic of the system, device, method and/or computer readable medium according to the present invention, as to their structure, organization, use, and method of operation, together with further objectives and advantages thereof, will be better understood from the following drawings in which presently preferred embodiments of the invention will now be illustrated by way of example. It is expressly understood, however, that the drawings are for the purpose of illustration and description only, and are not intended as a definition of the limits of the invention. In the accompanying drawings:

[0019] FIG. 1 is a schematic of an embodiment of the present invention;

[0020] FIG. 2 is a schematic of a further embodiment of the present invention; [0021] FIG. 3 is a schematic of a further embodiment of the present invention;

[0022] FIGS. 4A and 4B are schematics of a further embodiment of the present invention; [0023] FIG. 5 is a flow chart of a further embodiment of the present invention;

[0024] FIG. 6 is a schematic of a further embodiment of the present invention;

[0025] FIG. 7 is a prior art schematic;

[0026] FIG. 8 is a prior art schematic;

[0027] FIGS. 9A and 9B are schematics of a further embodiment of the present invention;

[0028] FIG. 10 is a schematic of a further embodiment of the present invention;

[0029] FIG. 11 is a schematic of a further embodiment of the present invention;

[0030] FIGS. 12A, 12B and 12C are schematics of a further embodiment of the present invention;

[0031] FIGS. 13A and 13B are schematics of a further embodiment of the present invention; [0032] FIG. 14 is a schematic of a further embodiment of the present invention;

[0033] FIGS. 15A, 15B and 15C are schematics of a further embodiment of the present invention; and

[0034] FIGS. 16A and 16B are schematics of a further embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0035] The description that follows, and the embodiments described therein, may be provided by way of illustration of an example, or examples, of particular embodiments of the principles of the present invention. These examples are provided for the purposes of explanation, and not of limitation, of those principles and of the invention. In the description, like parts are marked throughout the specification and the drawings with the same respective reference numerals. The drawings are not necessarily to scale and in some instances proportions may have been exaggerated in order to more clearly depict certain embodiments and features of the invention.

[0036] The present disclosure may be described herein with reference to system architecture, block diagrams and flowchart illustrations of methods, and computer program products according to various aspects of the present disclosure. It may be understood that each functional block of the block diagrams and the flowchart illustrations, and combinations of functional blocks in the block diagrams and flowchart illustrations, respectively, can be implemented by computer program instructions.

[0037] These computer program instructions may be loaded onto a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions that execute on the computer or other programmable data processing apparatus create means for implementing the functions specified in the flowchart block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer- readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart block or blocks. The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0038] Accordingly, functional blocks of the block diagrams and flow diagram illustrations support combinations of means for performing the specified functions, combinations of steps for performing the specified functions, and program instruction means for performing the specified functions. It may also be understood that each functional block of the block diagrams and flowchart illustrations, and combinations of functional blocks in the block diagrams and flowchart illustrations, can be implemented by either special purpose hardware-based computer systems which perform the specified functions or steps, or suitable combinations of special purpose hardware and computer instructions.

[0039] The present disclosure may now be described in terms of an exemplary system in which the present disclosure, in various embodiments, would be implemented. This may be for convenience only and may be not intended to limit the application of the present disclosure. It may be apparent to one skilled in the relevant art(s) how to implement the present disclosure in alternative embodiments.

[0040] In this disclosure, a number of terms and abbreviations may be used. The following definitions and descriptions of such terms and abbreviations are provided in greater detail. [0041] As used herein, a person skilled in the relevant art may generally understand the term “comprising” to generally mean the presence of the stated features, integers, steps, or components as referred to in the claims, but that it does not preclude the presence or addition of one or more other features, integers, steps, components or groups thereof.

[0042] It should also be appreciated that the present invention can be implemented in numerous ways, including as a system, a device, a method, or a computer readable medium wherein program instructions are sent over a network (e.g., IoT optical or electronic communication links). In this specification, these implementations, or any other form that the invention may take, may be referred to as processes or methods. In general, the order of the steps of the disclosed processes may be altered within the scope of the invention.

[0043] Preferred embodiments of the present invention can be implemented in numerous configurations depending on implementation choices based upon the principles described herein. Various specific aspects are disclosed, which are illustrative embodiments not to be construed as limiting the scope of the disclosure. Although the present specification describes components and functions implemented in the embodiments with reference to standards and protocols known to a person skilled in the art, the present disclosures as well as the embodiments of the present invention are not limited to any specific standard or protocol. Each of the standards for non- mobile and mobile computing, including the Internet and other forms of computer network transmission (e.g., TCP/IP, UDP/IP, HTML, and HTTP) represent examples of the state of the art. Such standards are periodically superseded by faster or more efficient equivalents having essentially the same functions. Accordingly, replacement standards and protocols having the same functions are considered equivalents. [0044] As those of ordinary skill in the art would generally understand, the Internet is a global computer network which comprises a vast number of computers and computer networks which are interconnected through communication links. A person skilled in the relevant art may understand that an electronic communications network of the present invention, may include, but is not limited to, one or more of the following: a local area network, a wide area network, peer- to-peer communication, an intranet, or the Internet. The interconnected computers exchange information using various services, including, but not limited to, electronic mail, Gopher, web- services, application programming interface (API), File Transfer Protocol (FTP). This network allows a server computer system (a Web server) to send graphical Web pages of information to a remote client computer system. The remote client computer system can then display the Web pages via its web browser. Each Web page (or link) of the“world wide web” (“WWW”) is uniquely identifiable by a Uniform Resource Locator (URL). To view a specific Web page, a client computer system specifies the URL for that Web page in a request (e.g., a HyperText Transfer Protocol (“HTTP”) request). The request is forwarded to the Web server that supports the Web page. When the Web server receives the request, it sends the Web page to the client computer system. When the client computer system receives the Web page, it typically displays the Web page using a browser. A web browser or a browser is a special-purpose application program that effects the requesting of web pages and the displaying of web pages and the use of web-based applications. Commercially available browsers include Microsoft Internet Explorer and Firefox, Google Chrome among others. It may be understood that with embodiments of the present invention, any browser would be suitable.

[0045] Web pages are typically defined using HTML. HTML provides a standard set of tags that define how a Web page is to be displayed. When a provider indicates to the browser to display a Web page, the browser sends a request to the server computer system to transfer to the client computer system an HTML document that defines the Web page. When the requested HTML document is received by the client computer system, the browser displays the Web page as defined by the HTML document. The HTML document contains various tags that control the displaying of text, graphics, controls, and other features. The HTML document may contain URLs of other Web pages available on that server computer system or other server computer systems.

[0046] A person skilled in the relevant art may generally understand a web-based application refers to any program that is accessed over a network connection using HTTP, rather than existing within a device’s memory. Web-based applications often run inside a web browser or web portal. Web-based applications also may be client-based, where a small part of the program is downloaded to a user’s desktop, but processing is done over the Internet on an external server. Web-based applications may also be dedicated programs installed on an internet-ready device, such as a smart phone or tablet. A person skilled in the relevant art may understand that a web site may also act as a web portal. A web portal may be a web site that provides a variety of services to users via a collection of web sites or web based applications. A portal is most often one specially designed site or application that brings information together from diverse sources in a uniform way. Usually, each information source gets its dedicated area on the page for displaying information (a portlet); often, the user can configure which ones to display. Portals typically provide an opportunity for users to input information into a system. Variants of portals include“dashboards”. The extent to which content is displayed in a“uniform way” may depend on the intended user and the intended purpose, as well as the diversity of the content. Very often design emphasis is on a certain“metaphor” for configuring and customizing the presentation of the content and the chosen implementation framework and/or code libraries. In addition, the role of the user in an organization may determine which content can be added to the portal or deleted from the portal configuration.

[0047] It may be generally understood by a person skilled in the relevant art that the term “mobile device” or“portable device” refers to any portable electronic device that can be used to access a computer network such as, for example, the internet. Typically, a portable electronic device comprises a display screen, at least one input/output device, a processor, memory, a power module and a tactile man-machine interface as well as other components that are common to portable electronic devices individuals or members carry with them on a daily basis. Examples of portable devices suitable for use with the present invention include, but are not limited to, smart phones, cell phones, wireless data/email devices, tablets, PDAs and MP3 players, etc.

[0048] It may be generally understood by a person skilled in the relevant art that the term “network ready device” or “internet ready device” refers to devices that are capable of connecting to and accessing a computer network, such as, for example, the Internet, including but not limited to an IoT device. A network ready device may assess the computer network through well-known methods, including, for example, a web-browser. Examples of internet- ready devices include, but are not limited to, mobile devices (including smart-phones, tablets, PDAs, etc.), gaming consoles, and smart-TVs. It may be understood by a person skilled in the relevant art that embodiment of the present invention may be expanded to include applications for use on a network ready device (e.g. cellphone). In a preferred embodiment, the network ready device version of the applicable software may have a similar look and feel as a browser version but that may be optimized to the device. It may be understood that other“smart” devices (devices that are capable of connecting to and accessing a computer network, such as, for example, the internet) such as sensors or actuators, including but not limited to smart valves, smart lights, IoT devices, etc.

[0049] It may be further generally understood by a person skilled in the relevant art that the term“downloading” refers to receiving datum or data to a local system (e.g., mobile device) from a remote system (e.g., a client) or to initiate such a datum or data transfer. Examples of a remote systems or clients from which a download might be performed include, but are not limited to, web servers, FTP servers, email servers, or other similar systems. A download can mean either any file that may be offered for downloading or that has been downloaded, or the process of receiving such a file. A person skilled in the relevant art may understand the inverse operation, namely sending of data from a local system (e.g., mobile device) to a remote system (e.g., a database) may be referred to as“uploading”. The data and/or information used according to the present invention may be updated constantly, hourly, daily, weekly, monthly, yearly, etc. depending on the type of data and/or the level of importance inherent in, and/or assigned to, each type of data. Some of the data may preferably be downloaded from the Internet, by satellite networks or other wired or wireless networks.

[0050] Elements of the present invention may be implemented with computer systems which are well known in the art. Generally speaking, computers include a central processor, system memory, and a system bus that couples various system components including the system memory to the central processor. A system bus may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. The structure of a system memory may be well known to those skilled in the art and may include a basic input/output system (“BIOS”) stored in a read only memory (“ROM”) and one or more program modules such as operating systems, application programs and program data stored in random access memory (“RAM”). Computers may also include a variety of interface units and drives for reading and writing data. A user of the system can interact with the computer using a variety of input devices, all of which are known to a person skilled in the relevant art.

[0051] One skilled in the relevant art would appreciate that the device connections mentioned herein are for illustration purposes only and that any number of possible configurations and selection of peripheral devices could be coupled to the computer system.

[0052] Computers can operate in a networked environment using logical connections to one or more remote computers or other devices, such as a server, a router, a network personal computer, a peer device or other common network node, a wireless telephone or wireless personal digital assistant. The computer of the present invention may include a network interface that couples the system bus to a local area network (“LAN”). Networking environments are commonplace in offices, enterprise-wide computer networks and home computer systems. A wide area network (“WAN”), such as the Internet, can also be accessed by the computer or mobile device.

[0053] It may be appreciated that the type of connections contemplated herein are exemplary and other ways of establishing a communications link between computers may be used in accordance with the present invention, including, for example, mobile devices and networks. The existence of any of various well-known protocols, such as TCP/IP, Frame Relay, Ethernet, FTP, HTTP and the like, may be presumed, and computer can be operated in a client-server configuration to permit a user to retrieve and send data to and from a web-based server. Furthermore, any of various conventional web browsers can be used to display and manipulate data in association with a web based application.

[0054] The operation of the network ready device (i.e., a mobile device) may be controlled by a variety of different program modules, engines, etc. Examples of program modules are routines, algorithms, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. It may be understood that the present invention may also be practiced with other computer system configurations, including multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCS, personal computers, minicomputers, mainframe computers, and the like. Furthermore, the invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0055] Elements of the present invention may be implemented with an IoT network that includes various devices (including IoT devices) and/or other physical objects. For example, in various embodiments, the devices and/or other physical objects in the IoT network may include, among other things, one or more IoT devices having communication capabilities, non-IoT devices having communication capabilities, and/or other physical objects that do not have communication capabilities.

[0056] Persons skilled in the art may appreciate that the IoT is a concept in which a large number of network ready devices are interconnected to each other and to the Internet to provide functionality and data acquisition at very low levels. As used herein, an IoT device may include a semi -autonomous device performing a function. The function may include sensing or control, among others. The IoT device may communicate with other IoT devices and a wider network, such as the Internet. Example networks of IoT devices may include commercial and home automation devices, such as water distribution systems, electric power distribution systems, pipeline control systems, plant control systems, light switches, thermostats, locks, cameras, alarms, motion sensors, and the like. The IoT devices may be accessible through remote computers, servers, and other systems, to control systems or access data. Other IoT devices may include IoT gateways, which are used to couple IoT devices to other IoT devices, and to cloud applications. Cloud applications may include services, for example, such as data storage, process control, and the like.

[0057] Elements of the present invention may be implemented on a Blockchain which is a peer-to-peer decentralized open ledger, and may rely on a distributed network shared between its users where everyone holds a public ledger of every transaction carried out using the architecture, which are then checked against one another to ensure accuracy, preferably using one of a variety of cryptographic functions. This ledger is called the“blockchain”. Blockchain may be used instead of a centralized third party auditing and being responsible for transactions. The blockchain is a public ledger that records transactions. A novel solution accomplishes this without any trusted central authority: maintenance of the blockchain is performed by a peer-to- peer network of communicating nodes running software. Network nodes can validate transactions, add them to their copy of the ledger, and then broadcast these ledger additions to other nodes. The blockchain is a distributed database; in order to independently verify the chain of ownership or validity of any and every transaction, each network node stores its own copy of the blockchain. [0058] Embodiments of the present invention may implement Artificial Intelligence (“AT’) or machine learning (“ML”) algorithms. AI and ML algorithms are general classes of algorithms used by a computer to recognize patterns and may include one or more of the following individual algorithms: nearest neighbor, naive Bayes, decision trees, linear regression, principle component analysis (“PCA”), support vector machines (“SVM”), evolutionary algorithms, and neural networks. These algorithms may“learn” or associate patterns with certain responses in several fashions, including: supervised learning, unsupervised learning, semi -supervised learning, and reinforcement learning.

[0059] Embodiments of the present invention can be implemented by a software program for processing data through a computer system. It may be understood by a person skilled in the relevant art that the computer system can be a personal computer, mobile device, notebook computer, server computer, mainframe, networked computer (e.g., router), workstation, and the like. In one embodiment, the computer system includes a processor coupled to a bus and memory storage coupled to the bus. The memory storage can be volatile or non-volatile (i.e. transitory or non-transitory) and can include removable storage media. The computer can also include a display, provision for data input and output, etc. as may be understood by a person skilled in the relevant art.

[0060] Some portion of the detailed descriptions that follow are presented in terms of procedures, steps, logic block, processing, and other symbolic representations of operations on data bits that can be performed on computer memory. These descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. A procedure, computer executed step, logic block, process, etc. is here, and generally, conceived to be a self-consistent sequence of operations or instructions leading to a desired result. The operations are those requiring physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated in a computer system. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers or the like.

[0061] In the description and drawings herein, and unless noted otherwise, the terms "vertical", "lateral" and "horizontal", are generally references to a Cartesian co-ordinate system in which the vertical direction generally extends in an "up and down" orientation from bottom to top (z-axis) while the lateral direction generally extends in a "left to right" or "side to side" orientation (x-axis or y-axis depending on figure orientation). In addition, the horizontal direction extends in a "front to back" orientation and can extend in an orientation that may extend out from or into the page (x-axis or y-axis depending on figure orientation).

[0062] As used herein, a person skilled in the relevant art may generally understand the term “hydroponics” to generally mean a method of growing plants without soil instead using mineral nutrient solutions in a water solvent. Terrestrial plants may be grown with only their roots exposed to the nutritious liquid, or the roots may be physically supported by an inert medium such as perlite, gravel, coco coir, or expanded clay pellets.

[0063] As used herein, a person skilled in the relevant art may generally understand the term “aeroponics” to generally mean a process of growing plants in an air or mist environment without the use of solid or an aggregate medium. Persons skilled in the art, however, will appreciate that water is preferably used in aeroponics to transmit nutrients. [0064] Open-loop Geothermal Energy Subsystem with Water Harvesting technology

[0065] As depicted in FIG. 1, in an embodiment of the present invention a CEA facility 10 is preferably equipped with a carbon-zero geothermal energy and water harvesting subsystem 100. An open-loop geothermal subsystem 100 includes a heat pump 102, an inlet pipe 104, a raw collection tank 140 and an outlet pipe 106 (alternately“overflow pipe 106”). A pump (not shown) preferably draws ground water from a water source (e.g., a water table) via the inlet pipe 104 into a gravity-fed reservoir 108. Potential energy stored in the water drawn by the pump is preferably used to generate electricity using a refrigeration cycle provided by the heat pump 102 to power one or more components of the CEA facility 10 via an electricity output (not shown).

[0066] Preferably, once the heat is extracted from the ground water by the heat pump 102, the heat extracted ground water (alternately,“effluent”) is directed into the raw collection tank 140 (e.g., via one or more conduits; not shown) that is in communication with an irrigation subsystem 110 which preferably filters and sterilizes the effluent prior to collection in a fresh water tank 155. A person skilled in the relevant art may appreciate that by collecting the effluent of the heat pump 102, the subsystem 100 provides the facility 10 with fresh water without the need for high-power pumps. One or more water volume sensors 120 (alternately“water sensors 120”) preferably monitor when the reservoir 108 and/or raw collection tank 140 reach a predetermined maximum volume, whereupon a valve 122 is activated to redirect the effluent out of the facility 10 (e.g., back to the water source) though overflow pipe 106 to prevent an overflow. The overflow pipe 106 is preferably associated with the raw collection tank 140. In preferable embodiments, the valve 122 is actuated automatically upon reaching the predetermined maximum volume or remotely by a user (not shown). In an embodiment of the invention, it is preferable to directly integrate the heat pump 102 with the reservoir 108 to allow the heat pump 102 to directly heat or cool the effluent to a predetermined optimal temperature range of the plants and their roots in the subsystem 100.

[0067] A person skilled in the relevant art may also appreciate that radiant heat from the water in the geothermal energy and water harvesting subsystem 100 acts similar to a boiler system, directly heating the facility 10 and the plants to ideal conditions. A person skilled in the relevant art may also appreciate that the geothermal energy and water harvesting subsystem 100 may preferably provide sufficient renewable energy to heat, cool and/or provide electricity for the entire CEA facility 10 and/or also preferably provide a continuous and reliable water source for the indoor crop. The facility 10 may also be adapted to include air heating elements to produce convective heat.

[0068] In a preferred embodiment of the present invention the heat pump 102, water sensors 120 and/or valve 122 are in communication via a network (e.g., an IoT network) associated with the CEA facility 10 to facilitate control (including, for example, external and/or remote) by a user. The network is controlled by an IoT unit 202 associated with a server 328. A person skilled in the relevant art may appreciate that the geothermal energy and water harvesting subsystem 100 preferably reduces energy costs (typically a significant operating expense), optimize plant root health, reduce the cost of irrigation systems (e.g., eliminating pumps and/or controls), and/or reduce operating risk (e.g., risk related to geographic location). An operating risk related to geographic location may occur when the geothermal system is located in an area that may require calcium and/or sulfur filtering increasing operational costs (e.g., southern Hamilton, Ontario). [0069] As shown in FIGS. 1-2, the facility 10 preferably includes at least one planter box 14 (alternately“pod 14” or“planter pod 14”), associated with the irrigation subsystem 110 adapted to receive fresh water from the fresh water tank 155, for rinsing and cleansing the planter boxes 14. The plants 16 preferably receive water and nutrients from the nutrient tank (not shown). Persons skilled in the art will appreciate that the plants 16 may be the same or different (e.g., genetically modified, species, etc.). Preferably, the facility 10 is adapted to facilitate optimal growing conditions for the plants 16 (collectively, as a subset, or individually).

[0070] The arrows in FIG. 1 depict the flow of water from the inlet pipe 104, the reservoir 108, the raw collection tank 140 (and optionally the overflow pipe 106), the fresh water tank 155 and the subsystem 110.

[0071] Water Reclamation and Nutrient Tanks

[0072] As shown in FIGS. 15A and 15B, in an embodiment of the present invention the CEA facility 10 preferably additionally includes a nutrient tank 130, a nutrient supply 134, a filtration and sterilization unit 145 and a holding tank 150.

[0073] In a preferred embodiment, in addition to the effluent (water drawn from the water source), rain water from the roof of the facility 10 and/or drainage water from the planter boxes 14 is received in the raw collection tank 140 via a series of conduits (not shown). As depicted in FIG. 15 A, the movement of water within the facility 10 is depicted by the arrows“A”. The water in the raw collection tank 140 is preferably passed through (e.g., via a pump 28) a filtration and sterilization unit 145 whereupon it is received in a fresh water tank 155. In preferable embodiments, as previously described, additional water is obtained from the ground water supply in the reservoir 108 and received in the raw collection tank 140 whereupon it is subject to the filtration and sterilization unit 145 and stored in the fresh water tank 155. Water from the fresh water tank 155 may be used to irrigate the plants via the irrigation subsystem 110, is drawn (e.g., via a pump 28) and mixed with a predetermined amount of nutrient from the nutrient supply 134 with the holding tank 150 to produce a base nutrient formula and/or is used to rinse and cleanse the planter boxes 14 (or channels). In preferable embodiments, the base nutrient formula is determined by an AI control system 400 based on measurements obtained by a nutrient sensor 132 (which may also preferably include a pH sensor and/or electro conductivity sensor) and IoT network data 800. The base nutrient formula is preferably fed to the nutrient tank 130 wherein a predetermined amount of nutrients from the nutrient supply 134 - including, but not limited to, macronutrients and micronutrients such as nitrogen, phosphorus, potassium, calcium, sulphur, magnesium, hydrogen, iron, boron, chlorine, manganese, zinc, copper, molybdenum, and nickel - and/or fresh water is added and measured to a specific formulation for feeding a specific channel of plants. The specific formulation is then used to feed the plants in a given channel (e.g., channels 1-13) via nutrient lines 136 as shown in FIG. 15C. A channel may include one or more planter boxes. Excess water preferably drains from the channels and returns to the raw collection tank 140.

[0074] As shown in FIG. 15A, the raw collection tank 140 includes the water sensor 120 to monitor water levels in the facility 10. If the predetermined maximum water level is achieved or surpassed, the excess water is preferably directed to the outlet pipe 106.

[0075] As shown in FIG. 15B, the movement of water from the raw collection tank 140 to the fresh water tank 155 and then to the nutrient tank 130 and/or holding tank 150 is depicted by the arrows“A”. The movement of air or water within the facility 10, after being heated or cooled by the heat pump 102 using the ground water imported by the inlet pipe into the reservoir 108, is depicted by arrows“B”. As previously discussed, the heat pump 102 is also preferably used to generate electricity for the facility 10.

[0076] Preferably, nutrients are introduced into the micronutrient supply 134 raw. In a preferable embodiment, the nutrients are diluted to a set concentration (e.g., a predetermined part per million or ppm) individually for macronutrients and collectively for micronutrients. Pumps (e.g., peristaltic pumps) are preferably used to maintain a predetermined nutrient ppm within the nutrient supply 134.

[0077] The AI Control System 400, using the robotic gardener subsystem 300, preferably determines the health of plants within the facility (including the stage of growth for each plant) and determines the optimal specific nutrient formulation required for each plant.

[0078] As shown in FIG. 15A, the facility 10 preferably includes an air intake 26 for receiving an external fresh air supply. The air intake 26 preferably includes a filtration unit (not shown) to clean and/or sterilize the external air prior to introduction to the facility 10. The flow of air within the facility from the intake 26 to the planter boxes 14 is depicted by arrows“B” and is facilitated by circulation fans 24 and a series of conduits (e.g., ventilation ducts). In one embodiment, the air received by the air intake 26 is heated or cooled by the heat pump 102.

[0079] Collaborative Cable-Driven Robotic Gardeners

[0080] As depicted in FIGS. 2 and 3, in an embodiment of the present invention the CEA facility 10 is equipped with at least one robotic gardener subsystem 300 that is preferably adapted for collaboration with one or more additional robotic gardener subsystems 300. In an embodiment, the one or more gardener subsystems 300 are adapted for movement about the facility 10. In preferable embodiments, movement of the gardener subsystems 300 is cable- driven. Persons skilled in the art, however, may appreciate that alternate modes of movement may be applied including, but not limited to, propellers (not shown) and/or toothed belts (not shown). Each gardener subsystem 300 is preferably adapted to utilize an on-board command processor 320, a network interface 308 adapted to facilitate communication via a network 200 (e.g., an IoT network), and/or interconnected hardware systems to facilitate the performance of certain tasks (e.g., tasks associated with a highly trained greenhouse worker). The robotic gardener subsystems 300 are preferably adapted to work at high-speeds (e.g., movement greater than about lm/s) while avoiding obstacles (e.g., lights, wires, irrigation lines and/or plants). The robotic gardener subsystems 300 are preferably connected to and/or compliant with one or more recognized safety standards (e.g., Class 3 and/or 4 standard in Ontario, Canada).

[0081] In preferable embodiments, a cable drive subsystem 350 enables manual control when operation is within a predetermined Safety Class required in a given region for automation safety. Manual control may preferably include semi-autonomous control (e.g., predetermined missions, specific facility operations and tasks) and/or remote control from a mobile device. Manual control is preferably only engaged if the safety shut-off has not been triggered. In an embodiment, it is triggered by the presence of a human in the operating range of the machines. In another embodiment, it is triggered if the safety switches have been triggered at the entrances to the operating area with the CEA 10. Persons skilled in the art may appreciate that provincial, state and/or national safety requirements for autonomous machines can vary by region.

[0082] In a preferred embodiment of the present invention, as shown in FIG. 3, each robotic gardener subsystem 300 may be equipped with one or more attachments 302 (alternately“tools 302”) to facilitate the performance of specific tasks (e.g., tasks traditionally accomplished by humans in the prior art). In an embodiment of the present invention, each robotic gardener subsystem 300 is preferably adapted to include: an electronic amplifier 304 (e.g., an electric servo drive system, preferably having adjustable precision and controls that are IoT-based), a pulley subsystem 350 (preferably ceiling-mounted, XYZ parallel cable, and/or linear bearings), robot chassis 306 (preferably being lightweight, self-leveling, integrated harvest bin and/or load cell), one or more arms 312, tools 302 (preferably multi-axis, end-of-arm, for example, grippers, electric shears, etc.), an IoT sensor interface 308, and one or more on-board sensors 310 (or “features 310”), including: a visual detection system 3 l0a (e.g., LiDar), a microscope camera 3 l0b (e.g., CMOS sensors), a sonar sensor 3 l0c, a backscatter detection sensor 3 l0d, an atmospheric sensor board 3 l0e; and/or a spectrometer camera (for measuring xylem and phloem movement within a plant; not shown). The atmospheric sensor board 3 l0e preferably includes one or more sub sensors, including but not limited to one or more sub sensors for detecting: tilt, acceleration, humidity, temperature, oxygen, electromagnetic radiation (including infrared, light, etc.), motion and/or carbon dioxide. The robotic gardener 300 also preferably includes a command processor 320 (e.g., a Nvidia Jetson or similar), a power supply and battery 326, a location unit 334 (e.g., a global positioning system), and/or a z-axis motor 356. Persons skilled in the art will appreciate that the combination of associating the on-board sensors 310 with the robot chassis 306 and moving the chassis 306 using the cable drive system 350 preferably reduces the number of sensors required to operate the facility. Instead of locating one or more of the on-board sensors 310 directly in the planter boxes 14, the on-board sensors 310 are preferably moved around the facility 10 and the location of the on-board sensors 310 in three- dimensional space is preferably determined using the location unit 334. [0083] In a preferred embodiment of the present invention each robotic gardener subsystem 300 may be controlled by one or more of the independent command processors 320 (alternately “control units 320”). Control units 320 may be prioritized such that there is a primary control unit 320 and a secondary control unit 322. In a preferred embodiment of the present invention, the primary control unit 320 is local to the robot chassis 306 (e.g., on-board) and the secondary control unit 322 is external or remote from the robot chassis 306. In some embodiments, the secondary control unit 322 is a pre-programmed algorithm residing in a database associated with the facility 10. A person skilled in the relevant art may appreciate that such a primary control unit 320 / secondary control unit 322 structure preferably facilitates initial and immediate actions of the robotic gardener subsystem 300 to be governed by the on-board hardware and command software. In a preferred embodiment, a database (not shown) is included in the robot chassis 306 to facilitate immediate actions of the robotic gardener subsystem 300 by the primary control unit 320. In some preferable embodiments, the secondary control unit 322 is adapted to control the IoT network 200.

[0084] Preferably, each robotic gardener subsystem 300 is pre-programmed to perform tasks using any one or more of the attachments 302 (e.g., precisely controlled tasks), on-board sensors 310, and/or the IoT network data 800. The IoT network data 800 preferably includes robot data 802 (including tool data 804, on-board sensor data 806 such as vision data, microscope data, sonar data, backscatter detection data, atmospheric data, location data, spectrometer data) and facility data 808 (including growth data 810, water sensor data 812, nutrient sensor data 814, experiment data 816, root zone sensor data 818, mass sensor data 820, light and air sensor data 822). [0085] Before each robotic gardener subsystem 300 is activated, a predefined command set from a server 328 (or“server processor 328”) associated with a database 324 is uploaded to the command processor 320 based on the specific plant species and/or genetic strain being grown. In a preferred embodiment, this may be done manually and/or remotely by an operator using a mobile user interface. Pre-programming may include receiving instructions from the database 324, for the command processor 320 to precisely carry out for example business processes in the CEA 10. A person skilled in the relevant art may appreciate that the processes or tasks may include functions traditionally performed by manual laborers. A person skilled in the relevant art may also appreciate that the robotic gardener subsystems 300, adapted for use with one or more of the tools 302 and on-board sensors 310 will preferably facilitate the performance of greenhouse tasks by the robotic gardener subsystem 300, including but not limited to: inspecting clone health, inspecting clone maturity, relocation of plants and clones, placement of plants in pots, analysis of disease and infection, cutting nodes and leaves, comparing patterns of plant health, pruning, testing, checking for maturity, harvesting, transporting, destroying and removing as well as specialty labor activities and/or custom-designed tasks. In a preferred embodiment, the predefined command set and/or instructions generated by the server 328 are transmitted to the command processor 320 for controlling the various components in the facility 10.

[0086] The use of robotic systems in CEAs preferably provides a number of advantages (e.g., the robotic gardener subsystem 300 may facilitate precise, error free operation of a facility 10 with little to no labor costs) that may not be presently realized by persons of skill in the art. Furthermore, the cost of the system is preferably comparable to the annual cost of hired labor, without the added risk of hired labor. The robotic gardener subsystem 300 is preferably low energy, robust and reliable, and/or inexpensive to operate and maintain. The robotic gardener subsystem 300 is preferably adapted to continuously optimize performance, receive live updates to add novel features, and/or produce higher crop yields than a human-operated facility of equal cost. In addition, the robotic gardener subsystem 300 is adapted to reduce waste of clean environment garments while reducing contamination risk from external elements.

[0087] As best shown in FIG. 9A, the cable drive system 350 preferably includes three motors (e.g., industrial servo motors) - an x-axis motor, a y-axis motor, and a z-axis motor - that are adapted to facilitate three-axis motion for the robotic gardener subsystem 300, similar to a gantry crane.

[0088] In an embodiment of the invention, as shown in FIG. 9A, the X-axis motion (of the three axis motion: X, Y and Z) of the first robotic gardener subsystem 300a is preferably facilitated by a first x-axis motor 352a that preferably includes a cable pulley 360a (alternately “belt drive 360a” supported by a first x-axis support beam 370a) (e.g., similar to a clothes line) mounted to the drive shaft 358a of the motor 352a to move a first y-axis support beam 380a along the x-axis. The first x-axis motor 352a is preferably mounted to a surface of the x-axis bearing track 362 or the x-axis support beam 370. Preferably, the y-axis support beam 380a is adapted to support the first robotic gardener subsystem 300a and movement along the x-axis is facilitated by wheel -based support of the y-axis support beam 380a about the x-axis support beams 370a, b. In preferable embodiments, the dimensions and physical properties of the cable 360a is predetermined based on the mechanical requirements of the x-axis system 350a. Preferably, the first y-axis support beam 380a (i.e., at a position distal to the pulley cable 360a) is mounted to a linear bearing track 362a that extends the entire length of the operating range of the robotic gardener subsystem 300 using a bearing track mount 382 for additional support. The bearing track mount 382 preferably projects from a surface of the y-axis support beam 380 and is adapted to movably bear on the bearing track mount 382. This configuration preferably, facilitates quick and frictionless motion along the X-axis. In preferable embodiments, linear bearings 362a, 362b are mounted above the robot chassis 306 (e.g., directly to the CEA 10) and include two tracks that run in parallel (e.g., a track on a first side and second side of the CEA 10). In an embodiment of the invention, when the first x-axis motor 352a is activated by the AI control system 400, the rotation of the motor 352a preferably causes the first x-axis cable pulley 360a to pull the first y-axis support beam 380a mounted to the linear bearings 362a along the x- axis. Rotating the first x-axis motor drive shaft 358a in one direction will preferably cause the x- axis pulley system 350a to pull the first y-axis support beam 380a along the bearings 362a in a forwards or backwards direction along the X-axis.

[0089] As shown in FIG. 9A, to control the Y-axis of motion 350b, a first y-axis motor 354a is preferably mounted directly to a surface of the first y-axis support beam 380a. Similar to the first x-axis motor 352a, the second Y-axis motor drive shaft 364a is preferably mounted directly to a y-axis parallel cable pulley system 366a. The first Y-axis motor 354a and the pulley and cable system 366a are preferably mounted directly to a surface of the first y-axis support beam 380a. This configuration preferably facilitates the entire Y-axis servo motor 354a and cable system 366a to be pulled along the linear bearings 362a when the X-axis servo motor 352a is activated. This preferably facilitates the control of both the X- and Y-axes of motion by controlling the electricity supplied to the servo motors 352a, 354a.

[0090] The Z-axis 350c of the cable drive system 350 preferably controls the vertical motion of the chassis 306 as shown in FIG. 9A. In an embodiment of the invention, the chassis 306 is preferably directly associated with the cable-pulley system 350c. The Z-axis motor 356a is preferably mounted to the chassis 306 (as shown in FIG. 3) or mounted local to the first y-axis support beam 380a. Hence, when the Z-axis motor 356a is activated, the chassis 306 is preferably raised or lowered (i.e., moved along a vertical direction) via the first Z-axis cable pulley 368a. In preferable embodiments, when the Y-axis motor 354a is activated, the chassis 306 is moved along the Y-axis with the Z-axis motor 356a. When the X-axis motor 352a is activated, the Y-axis motor 354a and cable-pulley system 350b is preferably pulled (e.g., in a forwards or backwards direction) along the linear bearing tracks 362a along with the Z-axis system 350c and the chassis 306.

[0091] Preferably, each motor 352a, 354a, 356a is adapted to operate independently (including simultaneously). Because the subsystem 350 is preferably configured for two robotic gardener subsystems 300 operating independently, the CEA 10 may comprise two 3-axis servo motor systems operating in mirror fashion to each other. In a preferred embodiment, as shown in FIG. 9A, the two systems are preferably associated with individual y-axis support beams 380a,b, including a second x-axis motor 352b, a second y-axis motor 354b, a second z-axis motor 356b, a second x-axis drive shaft 358b, a second x-axis cable pulley 360b, a second x-axis bearing track 362b, a second y-axis drive shaft 364b, a second y-axis cable pulley 366b, a second z-axis cable pulley 368b, a second x-axis support beam 370b and a second y-axis support beam 380b. A stopper mechanism (e.g., a limit switch, not shown) is preferably placed between the first y- axis support beam 380a and the second y-axis support beam 380b to prevent the two systems from overlapping and thus colliding.

[0092] In an alternative embodiment, as shown in FIG. 9B, the two systems 300a,b may preferably share the y-axis support beam 380 adapted to move along the x-axis 350a via the X- axis cable pulley 360. Such a configuration is preferably accomplished by using a first y-axis cable pulley 366a track and a second y-axis cable pulley 366b on opposing surfaces of the y-axis support beam 380. A first y-axis motor 354a is preferably associated with the first y-axis cable pulley 366a to facilitate movement of the system 300a along the y-axis 350b. A second y-axis motor (not shown) is preferably associated with the second y-axis cable pulley 366b to facilitate movement of the system 300b along the y-axis 350b. A first z-axis motor 356a is preferably associated with the first z-axis cable pulley 368a to facilitate movement of the system 300a along the z-axis 350c. A second z-axis motor (not shown) is preferably associated with the second z- axis cable pulley 368b to facilitate movement of the system 300b along the z-axis 350c. A stopper mechanism (e.g., a limit switch, not shown) is preferably associated with, and placed between, the first and second systems 300a, b to avoid overlap and/or collision. This alternative embodiment is preferably adapted for use in the vertical growth configuration described below.

[0093] In an embodiment of the present invention, as shown schematically in FIG. 11, the robotic gardener subsystem 300 preferably includes the x-axis motor 352, the y-axis motor 354, and the z-axis motor 356 operatively connected to the electronic amplifier 304 which is in communication with the command processor 320 (e.g., via an EtherCAT connection). The command processor 320 is preferably operatively connected to one or more on-board sensors 310 and tools 302 (including tools associated with one or more arms 312). The command processor 320 is preferably in communication with the AI control system 400 (including the server 328, the database 324 and the IoT unit 202) via the IoT network 200. Communication between the command processor 320 and the server 328 (e.g., a DGX-2 deep learning system offered by Nvidia to apply algorithms for inspection of plants, identification of plants, optimization of plant growth, autonomous facility controls and parameters, and/or plant growth experiments) may preferably be facilitated by an MQTT protocol. In some preferable embodiments, a mobile user interface (e.g., a website, mobile application, etc.) is associated with the subsystem 300 (e.g., via the MQTT protocol). As shown in FIG. 11, facility sensors (including, water sensor 120, nutrient sensor 132, biosensors 162, beehive sensors 604, root zone sensors 922, mass sensors 924, light and air sensors 906), facility components (heat pump 102, light rail system 22, irrigation system 30, pumps 28, fans 24 (including HVAC), valve 122, microcontrollers 160, beehive 600, grow lights 904, aeroponics system) and the cloud database 406 are also preferably in communication with the AI control system 400 via the IoT network 200

[0094] In a preferred embodiment, the robotic gardener subsystem 300 uses the visual detection system 3 l0a to control the cable drive subsystem 350 (e.g., gantry and robot motion). The visual detection system 3 l0a sends data 806 to the command processor 320, which is in communication with the AI control system 400 via the IoT network 200. The server 328 may preferably apply machine learning algorithms 500 and a machine learning library (e.g., Tensorflow) to the data 806 via, for example, the robot operating system (e.g., Nvidia Isaac or Robot Operating System“ROS”) to generate machine learning data and/or instructions, which may be stored in the database 324 (or a database local to the chassis 306) and/or sent to the command processor 320. The command processor 320 (e.g., a Nvidia Jetson or similar) is preferably in communication with the electronic amplifier 304 (e.g., using PCIe, EtherCAT master card, EtherCAT Slave Bus) to, for example, send instructions and/or receive tool data 804. The electronic amplifier 304 is preferably in communication (e.g., using encoders) with the x-axis motor 352, the y-axis motor 354, and the z-axis motor 356 (e.g., via EtherCAT) in addition to the tools 302, which may be associated with the arm 312. In some embodiments of the present invention, the command processor 320 is local to the y-axis support beam 380. [0095] In a preferred embodiment, the server 328 controls the facility 10. The command processor 320 preferably receives on-board sensor data 806 from the on-board sensors 310 which is relayed to the AI control system 400 via the IoT network 200. The server 328 may preferably apply machine learning algorithms 500 and a machine learning library (e.g., Tensorflow) to the data 806 via, for example, the robot operating system (e.g., Nvidia Isaac or ROS) to generate machine learning data and/or instructions, which may be stored in the database 324 and/or sent to the command processor 320. The command processor 320 is preferably in communication (e.g., using encoders) with the x-axis motor 352, the y-axis motor 354, and the z-axis motor 356. The server 328, via the IoT network 200, is preferably adapted to communicate with the components in the facility including, for example: the HVAC control panel; lighting control panel; aeroponics system, pump and nutrient panel; fan and motor control panel; and/or microcontrollers.

[0096] The robotic gardener subsystem 300 may preferably use a software development kit (e.g., the NVIDIA etson TX2 running NVIDIA etpack 3.2 and robot operating system (e.g., Nvidia Isaac or ROS)), a vision detection system (e.g., Intel RealSense D400 series visual system), an arm (e.g., a 4-axis SCARA robot arm) driven by high torque stepper motors connected to a relay circuit board (preferably custom printed), a grasper (e.g., the Shadow Robotics Hand), a cutter (e.g., an electric cutting mechanism called a nipper), and/or various on board sensors including a LIDAR sensor, a Sonar sensor, and/or CMOS sensors. Embodiments of the present invention may additionally include light spectrum sensors (not shown). In an embodiment of the present invention, the IoT microcontroller 322 (or“secondary control processor 322”) may preferably be a Nvidia letson or similar including a custom relay and sensor board adapted for use with Nvidia Isaac or ROS and Ubuntu Core, for example. In a preferable embodiment of the present invention, the robotic gardener subsystem 300 applies open source software including the operating system (e.g., Ubuntu 16.04). An MQTT protocol may preferably be used to transfer data signals from the IoT microcontroller 322 to a server 328 and the database 324 and a message queuing telemetry transport and client implementations (e.g., an open source EMQTT broker and MQTT Paho Client) to publish and/or broker data signals to the database 324. In an embodiment, the database 324 is preferably a SQL and SQL lite system. In an embodiment of the present invention, the mathematics for deep learning may preferably be processed using a data center GPU (e.g., an NVIDIA VI 00 series GPU with CUDA 9.1, cuDNN, cuBLAS including access to NVIDIA libraries and technology frameworks) of the server 328. Preferably, the mathematics for deep learning may be processed using a machine learning library (e.g., Tensorflow) and/or a deep learning framework (e.g., CAFFE2, MXNET). An embodiment of the deep learning architecture that will run on, for example, Tensorflow is described below.

[0097] In preferable embodiments, a pretrained Convolutional Neural Network (“CNN”; for example, AlexNet) is utilized including pre-training using an image database (e.g., ImageNet). The last two layers of the CNN will preferably be trained using a dataset including information associated with Cannabaceae plants in the database 324. Persons skilled in the art may also appreciate that the vision detection system (e.g., Intel Realsense binocular vision system) may be used to record video data (e.g., at 1 fps) of Cannabaceae plants growing from seed to full maturity. As this vision data (i.e., a component of the on-board sensor data 806) is received, the pretrained CNN in the last few layers is preferably updated with the growing dataset. In preferred embodiments of the present invention, each life cycle stage of plants that corresponds to a new set of robotic gardener tasks will have its own dataset and CNN. Once the CNNs have been pre-trained on each life-cycle, the output of the last fully connected layer of the CNN before the classification layer is preferably used in each corresponding timeframe of the LSTM (alternately“Long Short Term Memory”) in the LSTM-CNN model. Preferably, the parameters of the CNN are trained using stochastic gradient descent in groups of approximately 30 (although persons skilled in the art may appreciate that stochastic gradient descent groups of other sizes may be used), anticipate using a learning rate of about 0.001, weight decay of approximately 0.000001 and momentum of about 0.95. Preferably, stochastic gradient descent may be used again for the LSTM and trained using the same (or different) group size, a larger fixed learning rate of approximately 0.01 for example, the same (or different) momentum, and larger weight decay of about 0.005 for example. In preferable embodiments, a machine learning library (e.g., TensorFlow) is used with a neural networks API (e.g., Keras), with augmentation of the model using cloud GPU framework (e.g., Nvidia’s Cloud GPU framework) containers to optimize the training and parameters.

[0098] Wireless Dual-Command System for Robot Swarms

[0099] As depicted in FIG. 3, in an embodiment of the present invention the robotic gardener subsystem 300 is preferably in communication with a database 324. In some embodiments, a database (not shown) is included in the robot chassis 306 to, for example, store robot data 802 if the robotic gardener subsystem 300 is unable to communicate with the database 324. In addition, each primary on-board control unit 320 is preferably adapted to communicate (e.g., wirelessly) with the database 324 (via the server 328) to determine a sequence of actions for the robotic gardener subsystem 300. In a preferred embodiment, as the robotic gardener subsystem 300 performs a predetermined sequence of actions, it preferably maintains communication with the database 324 to, for example, send real-time robot data 802 from any one or more of the tools 302 and on-board sensors 310 along with other relevant data to the database 324. Persons skilled in the art will also appreciate that the robot data 802 from the one or more tools 302 and/or on-board sensors 310 may also be communicated at one or more predetermined time intervals. In a preferred embodiment, the data 800 will be relayed via secure channels (e.g., blockchain) using the IoT network 200.

[00100] The IoT network 200 preferably runs wirelessly and facilitates control of the facility 10 from the server 328 using an ROS Distribution (e.g., Nvidia Isaac or ROS) installed, for example, on an operating system (e.g., Ubuntu 16.04). The ROS Distribution preferably controls the output signals to the pumps, motors and/or relays associated with the CEA facility 10. The signals that control ROS are preferably generated by an algorithm or code (e.g., Python code) stored in the database 324 and machine learning library (e.g., Tensorflow) programs that output the code to ROS preferably when the AI deep learning system creates an insight from specific data signals (e.g., data 806) generated by the visual detection system 3 l0a mounted on the chassis 306 or from data 800 stored on the database 324 from the IoT microcontrollers 322. Relevant data signals are preferably stored on a blockchain 330 which can be accessed by the server 328 for analysis using, for example, machine learning and/or deep learning algorithms (e.g., developed using Python). Additional data signals that will be stored on the blockchain 330 or database 324 include, for example, real-time internet data or user defined metrics / parameters. Information from the database 324 is preferably recorded onto the blockchain 330 and shared with users or the public based on their specific interaction with the robotic gardener subsystem 300 (an example of different users would be a customer or administrator). In preferable embodiments, the blockchain 330 facilitates the transparent access and storage of financial transaction, environment data and/or plant data that can be stored and shared with relevant stakeholders and utilized to improve brand image by promoting honesty and transparency while also keeping certain data private and/or secure.

[00101] In an embodiment of the present invention, the server 328 preferably monitors the activity of each robotic gardener subsystem 300 by analyzing the blockchain 330, IoT network 200 and/or the database 324. Preferably, as the server 328 analyzes the data 800, it may alter the robotic gardener subsystem 300 parameters (e.g., in real-time or subsequently) to optimize the actions of the robotic gardener subsystem 300 for each specific task beyond its pre-programmed capability for the respective task. A person skilled in the relevant art may appreciate that this functionality preferably enables multiple robotic gardener subsystems 300 to work collaboratively to solve problems, to respond to and/or alter their activity based on new and/or external data sets (e.g., disease detection, social media trends and/or customer feedback data), and/or to optimize robotic gardener subsystem 300 performance based on newly discovered data beyond the predefined algorithms for each plant species. A person skilled in the relevant art may also appreciate that this feature would allow the robotic gardener subsystems 300 to independently change their behavior to solve problems based on subjective parameters including, for example, urgency, customer orders, cycle time, cost and/or quality. The server 328 and/or database 324 may preferably be adapted to store and analyze the data 800 and controls and subsequently apply machine learning algorithms to optimize (preferably continuously) the robotic gardener subsystem 300 processes and/or improve performance over time for each plant species.

[00102] It may be appreciated that control systems for the robotic gardener subsystems 300 preferably have the ability to control each robotic gardener subsystem 300 using artificial intelligence and machine learning algorithms, which preferably improves profit margins and reduces operating expenses by programming the facility 10 to improve (preferably continuously) its performance (e.g., reducing material cost, increasing yield, and/or improving genetics) and/or preferably reduces risk by allowing the facility 10 to adapt production relative to external or internet data including political, social and/or economic trends (e.g., in real time). Furthermore, it may be appreciated that the control system for the robotic gardener subsystem 300 facilitates storing and/or development of valuable data and insights in the database 324, which can for example be sold, licensed and/or monetized for additional revenue.

[00103] Server with AI Control Algorithms

[00104] As depicted in FIG. 4B, in an embodiment of the present invention the CEA facility 10 is preferably equipped with an AI control system 400, which is the“brain” of the autonomous CEA facility 10. The AI control system 400 may be local to, or remote from, the facility 10. The AI control system 400 preferably includes the server 328 (e.g., Nvidia Volta architecture to perform mathematics for deep learning), the database 324 including a predefined library of proprietary machine learning and AI control algorithms, the secondary control unit 322, a memory 322 (including AI algorithms 500 and a front end web platform 404), a cloud- computing interface 402, a front-end web platform 404 with custom user-interface and/or the IoT unit 202. Preferably, the components comprising the AI control system 400 are in communication with each other as well as a cloud database 406 via the IoT network 200.

[00105] Preferably, the components of the system 400 include instant and open communication with each other for optimal functionality. With that said, it is not necessary for the operation of the system 400 and often the independent components will have no need to communicate or will not be able to communicate (e.g., internet failure, power outage, remote location, etc.). This functionality is preferably used to create redundancy and depending on cost and technology limits may not be implemented.

[00106] In a preferred embodiment of the present invention, as shown in FIG. 10, the AI control system 400 is adapted to communicate with one or more command processors 320 via the IoT network 200. The IoT network 200 also preferably facilitates communication between the AI control system 400 and the cloud database 406.

[00107] The AI control system 400 preferably receives all data 800 produced by the facility 10 and the IoT network 200, including one or more pieces of data 802 transmitted from the robotic gardener subsystems 300, including tool data 804 from one or more tools 302 and on board sensor data 806 (e.g., data from the visual detection system, microscope camera, etc.) from one or more on-board sensors 310, and/or facility data 808 from the other facility sensors (including, for example, the water sensor 120). The AI control system 400 preferably processes the data 800 produced by the facility 10 and/or the IoT network 200 using an edge-network operating system which stores data 800 in the database 324 for analysis and/or subsequent retrieval. The database 324 preferably uses at least one, preferably two, redundant storage systems including for example: a stack of solid-state drives located in the server 328, a cloud database 406 that is a mirror of the database 324 stored on the server 328 in solid-state drives, etc. This redundancy preferably increases performance, increases security and/or reduces risk of data loss.

[00108] In a preferred embodiment of the present invention the server 328 separates and/or organizes incoming signals (or“data 800”) into individual data-sets from the IoT network 200. In an example of a preferred embodiment, there are provided sixty-four (64) data channels with each channel corresponding to a group of sixteen (16) data-sets generated from individual sensors (for example, biosensors 162) associated with the facility 10 and the IoT network 200, including one or more pieces of data 802 transmitted from the robotic gardener subsystems 300, including data 804, 806 from one or more tools 302 and on-board sensors 310, and/or facility data 808 generated by facility sensors (including, for example, the water sensor 120). Each data- set is preferably tagged with a location (e.g., network location), an output signal, a profile, parameters and/or classifications.

[00109] Each data-set preferably includes a defined set of data-stacks that characterize the data 800 based on its classification on the IoT network and/or its parameters. Each group of parameters in a data-stack is preferably placed into regularly acceptable ranges, facilitating organization of data by the server 328 according to one or more of its numerical value, frequency, and/or pattern. The server 328 preferably contains user defined data profiles adapted to identify and/or build relationships between multiple data-stacks stored in the database 324. The profiles preferably include the parameters of the data 800 and the given set of outputs required for those parameters. The data profiles also preferably contain a defined set of command outputs that control variables through the IoT network 200. A person skilled in the relevant art may appreciate that this preferably facilitates a response to one or more unique sets of acceptable ranges by the server 328 including modifying facility controls, nutrient controls, and/or lighting controls if the analyzed numbers, patterns and/or frequencies fall outside of a predetermined acceptable range. Furthermore, having multiple organized data-sets and/or data profiles preferably enables pattern recognition by the server 328 and/or generates relationships between unrelated data using the AI algorithms and/or tools (e.g., using the Nvidia Volta architecture). [00110] In preferable embodiments of the present invention, the system 400 includes programs or instructions that employ deep learning architectures to classify data into different sections based on analysis of the data sets (e.g., Python and/or Tensorflow). An example of a data set includes images (e.g., video and/or pictures) of cannabis plants or individual cannabis strains that are stored on the database 324 from a robotic gardener subsystem 300 comprising a visual detection system 3 lOa. Data sets are preferably used to train neural networks that are used to predict the specific tasks, operations and/or activities the robotic gardener subsystem 300 and/or CEA facility 10 should next pursue. Preferably, the facility 10 acts on these predictions using algorithms (e.g., Python and/or Tensorflow code) stored on the memory 332 and/or database 324. ROS preferably outputs signals to the facility controls and/or relays to the facility components (including the robotic gardener subsystems 300) responsible for performing the desired operations and/or tasks. Data set creation is known as "training" a neural network. The system 400, once fully operational, is preferably designed to train itself once the fundamental operations and processes have been implemented. Deep learning is discussed in greater detail below.

[00111] By way of example for a single tomato plant, a data-set would preferably comprise all of the data related to said plant, a data-stack may be the“water flow rate data” for the plant on a given channel, which classifies the type of data stored in the data-set. The filtered parameters of the“water flow rate” could be, for example: below the limit, lower limit, the optimal metric, the upper limit or above the limit. The data profile for growing beefsteak tomatoes is a unique group of data sets, stacks and/or parameters that classify how that respective type of tomato should be grown using a predefined acceptable data range. Should a given data-stack be outside of a predetermined acceptable range, the server may preferably automatically issue a corrective command (e.g., closing irrigation valves to limit nutrient flow rates to a specific channel).

[00112] Persons skilled in the art will appreciate that the embodiments of the present invention, as described herein, can be adapted for use with any indoor crop and is not limited to cannabis plants or tomato plants.

[00113] Machine-Learning Algorithms

[00114] In a preferred embodiment of the present invention, artificial intelligence algorithms 500 (including machine learning algorithms and deep learning algorithms) are used in the operation of the CEA facility 10 to recognize patterns in the data 800. These patterns are preferably stored in the database 324 as, for example, a reference for comparison to future patterns to continuously modify facility operations based on predetermined conditions. Preferably, the algorithms 500 are sets of code (e.g., Python code) stored on the memory 332 and/or the database 324 that create complex logical arguments from the high-speed analysis of all data channels (e.g., all 64 channels), facilitating the output of commands (e.g., Python commands) by the server 328 to control hardware (e.g., facility components) in communication with the IoT Network 200 when a pattern appears preferably for the optimization of various metrics and/or parameters.

[00115] FIG. 5 depicts an example of an algorithm 500 preferably adapted to maximize the mass of an average plant on a given channel. In a first step 502, the exemplary algorithm preferably analyzes the database and data channels (e.g., in real-time) to generate patterns related to plant mass. In a second step 504 the exemplary algorithm preferably compares the data patterns with several inputs, which preferably includes differentials from data-stacks stored in the database, the control feedback signals, data from the IoT network and/or the Internet. In a third step 506, correlations between all data are preferably identified. In a fourth step 508, the exemplary algorithm determines whether the facility conditions are optimal and/or within predetermined acceptable limits. If the correlations result in a logical argument for plant growth by altering the CEA facility conditions, i.e., the facility conditions are not optimal, the server will preferably apply a step 510 of altering the facility controls to maximize the average plant mass on a given channel based on the pattern. If the exemplary algorithm detects a correlation between an increase in voltage reading from a load cell, indicating higher plant mass, and the simultaneous increase between light intensity and humidity data sets (i.e., not individually), the exemplary algorithm will preferably apply the step 510 of sending an output signal to increase both humidity and light intensity until the output signal no longer creates a differential in load cell voltage. Preferably, the exemplary algorithm will apply a step 512 of maintaining the facility conditions if the conditions are determined to be within the predetermined acceptable limits (including, for example, not individually increasing humidity or light intensity if it only detects a pattern in load cell voltage when the light and humidity are increased together). The exemplary algorithm 500 may then preferably add the current conditions and other relevant data to the database 324 and reanalyze the CEA facility conditions, to learn over time. Persons skilled in the art may appreciate that although plant mass may be significant, correlations developed and/or identified by the algorithms and/or programs (e.g., Tensorflow, Python, Neural networks) of the present invention for all data points in the facility will also preferably be less than, equal to, or of greater significance. [00116] A person skilled in the relevant art may appreciate the advantages provided by the use of ML algorithms in CEAs, as highly intelligent control systems designed to preferably continuously optimize all aspects of a facility and maximize profit, reduce costs and/or maximize quality of the produce using a high volume of data that could not be processed by humans.

[00117] ’Hexagon¹ connected bee management system, with BeeFlow and AI analytics

[00118] As depicted in FIG. 6, in a preferred embodiment of the present invention, pollination inside the CEA facility 10 is supported through the use of an IoT connected beehive 600 (“Smarthive 600”). The SmartHive 600 preferably monitors bee health while allowing the uninhibited flow of bees 602 in and out of the facility 10 without increasing energy expenses and/or allowing the entrance of other foreign pests. The SmartHive 600 is preferably an artificial structure that contains a living beehive that is integrated into a surface of the CEA facility 10 to allow bees 602 to live, grow and repopulate in a healthy and natural manner. The SmartHive 600 preferably facilitates easy access of bees 602 into or out of the facility 10. The SmartHive 600 is preferably equipped with a suite of sensors 604 that, for example, track the number of bees, monitors the health parameters of the hive and links with the server 328 though the IoT network 200 and database 324 to monitor and correlate bee health with indoor crop growth parameters, preferably through the use of an algorithm. A person skilled in the relevant art may appreciate the advantages of utilizing the SmartHive 600, as bees 602 are an inexpensive method to pollinate crops which preferably increases yield; however, the advantages of combining a beehive with an IoT network may not have been realized in the prior art. The beeflow system is preferably designed as pressure-based (e.g., fan) or having a physical barrier (e.g., door). [00119] Growth Subsystem with integrated IoT Biosensor Network

[00120] As depicted in FIG. 4A, in an embodiment of the present invention the CEA facility 10 is equipped with a growth subsystem 450 including a plurality of planter box microcontrollers 160, biosensors 162 and/or planter boxes 16 (preferably hydroponic or aeroponic) that integrate the irrigation subsystem 110, nutrient lines 136, nutrient tank 130, holding tank 150, raw collection tank 140 and/or fresh water tank 155 to facilitate autonomous monitoring and/or control of the plants 16 being grown in the boxes 14. The microcontrollers 160 are preferably adapted to allow users to remotely, for example over the IoT network of the facility 10 provided by the IoT unit 202, monitor and/or control a plant’s water supply, nutrient supply, moisture, light intensity / spectrum, plant mass (kg), growth solution pH, temperature and/or other biological metrics, as measured by the biosensors 162 (including light and air sensors 906 and root zone sensors 922). A person skilled in the relevant art may appreciate that monitoring (e.g., wirelessly) and control (e.g., wirelessly) of a plant's environment and inputs systems preferably reduces production costs. The microcontrollers 160 are preferably adapted to communicate with the server 328, reducing the need to manually manage and/or care for plants 16. The CEA facility 10 may also preferably be adapted to use a backscatter-diffraction technology associated with the pots 16 (preferably integrated therewith) to facilitate precise identification and/or location of individual plants without additional electronics by the robotic gardener subsystems 300. In addition, as shown in FIGS. 4A and 15A, the facility 10 further includes a light rail system 22. The light rail system 22 includes one or more lights 20 (alternately“light ballasts 20”) that are preferably mounted on a track adapted for linear movement - for example, in association with the robotic gardener subsystem 300. In a preferred embodiment, the light rail system 22 is adapted to slide the light ballasts 20 back and forth (e.g., along the x-axis support beam 370) over the canopy of the plants to reduce the amount of lights and energy required during operation (i.e., so that the entire facility 10 is not required to be lit at the same time). Lights 20, are also preferably adapted for individual or collective activation as determined by the AI control system 400 or the user. In an embodiment, the light rail system 22 is additionally adapted to move the fans 24. In an embodiment of the present invention, the subsystem 450 may be adapted to use aeroponics or hydroponics. Persons skilled in the art may appreciate that aeroponics may be simpler to automate, control and may be associated with lower cost and resource use. In preferable embodiments, a gravity fed aeroponics system with optional rainwater harvest and geothermal water system may be used.

[00121] The nutrient lines 136 shown in FIG. 4A are an embodiment of the present invention whereby the lines 136 are connected to the irrigation subsystem 110. In an alternate embodiment of the present invention, the lines 136 are directly connected to the planter boxes in each channel (as shown in FIG. 15C) to facilitate the delivery of specific nutrient formulations to the plants in the channel.

[00122] As depicted in FIG. 4A, the IoT network 200 is preferably adapted to wirelessly connect a plurality of plants 16 (e.g., 4096 plants) using the blockchain ledger 330. The IoT network 200 preferably contains a plurality of data-channels dependent on a multiple of the number of plants 16 (e.g., 256 data-channels for 4096 plants), with each channel preferably containing a predetermined number of plants (e.g., 16 plants for each of the 256 data channels) and is capable of being modular to any number of facilities connected together. The IoT network 200 preferably facilitates instant and seamless data communication between each data-channel, the robotic gardener subsystems 300, the facility 10 and/or the server 328. By facilitating individual data-channels of plants to compare and/or communicate biological metrics with a larger community of plants, the entire community of plants may preferably be used to collectively work together to optimize the growth of the entire crop, including the application of algorithms 500 to analyze the facility data 808 (which includes the growth data 810). The microcontroller channels are preferably connected to an operating system (e.g., edge-network) that facilitates the processing of data (e.g., in real-time) to facilitate alteration of the facility controls without an internet connection. The IoT network 200 preferably enables the server 328 or the user to have separate growing conditions for each channel (e.g., 256 in the present example), preferably creating an opportunity to perform real-time experiments or to grow many different types of plants and/or the same plant having modified genes simultaneously.

[00123] As shown in FIGS. 16A and 16B, an embodiment of the present invention facilitates experiments 170 by the user with different controls and inputs for individual channels and facilitates the experimental analysis of plant health and/or growth. Persons skilled in the relevant art may appreciate that this embodiment preferably enables autonomous growth and/or the comparison of many different types of crops at the same time without any additional work, enable the growth of different genetics in each channel, allowing the objective monitoring of plant performance based on a change in variables (e.g., nutrient formulation, grow light intensity, etc.) in each channel, and/or enable the slight modification of the controls and inputs from one channel to the next, revealing how a change in control or input (e.g., amount and/or intensity of light or amount of nutrients) changes the growth of the plants.

[00124] As shown in FIG. 16A, the water in the raw collection tank 140 is subject to the filtration and sterilization unit 145 and held in the fresh water tank 155, the holding tank 150, and/or the nutrient tank 130. Water from the fresh water tank 155 may be used to irrigate the plants via the irrigation subsystem 110 or rinse and cleanse the channels (or planter boxes 14). Alternately, water from the fresh water tank may also be used to irrigate the plants subject to the experiments 170 and/or mixed with the nutrients from the macronutrient supply l34a and/or the micronutrient supply l34b in the holding tank 150 and/or the nutrient tank 130 at one or more predetermined nutrient formulations and/or concentrations. In a preferred embodiment, as shown in FIG. 16A, the nutrient tank 130 includes a plurality of formulation tanks l30a, each one of the formulation tanks l30a adapted to hold a specific one of the predetermined nutrient formulations and/or concentrations for use in the experiments 170 and/or for feeding one or more plants 16. The nutrient solution in the holding tank 150 and/or the nutrient tank 130 may be used to supply the experiments 170 with macronutrients and/or micronutrients. After drainage from the experiments 170, water may be recollected in the raw collection tank 140 and/or introduced to the nutrient lines 136 via the pump 28.

[00125] As shown in FIG. 16B, the pumps 28 are preferably pressure bladders adapted to supply the various channels (i.e., 1-50, 51-100, 101-150, 151-200, 201-250, etc.) with optimal nutrient solutions via the nutrient lines 136 and spray heads 30 (e.g., rotary spray). In preferable embodiments, the irrigation subsystem 110 includes a plurality of spray heads 30 mounted in the planter boxes 14 and/or the lid 900.

[00126] Preferably the CEA facility 10 can be operated by or more individuals, requiring minimal training to operate, and is easy to manage and monitor remotely (e.g., on a mobile device). In an embodiment, an individual can preferably supervise multiple facilities from one monitoring location. The AI control system 400 preferably facilitates access to all monitoring areas (e.g., growth, water, security, statistics, etc.) Access to the monitoring location is preferably controlled for security (e.g., via RFID entry). In addition, the maintenance door within the monitoring location preferably only unlocks when maintenance work is scheduled to be performed. The individual preferably undergoes a cleaning or sterilization process, including dressing in clean clothes adapted for the facility (e.g., robe). Once the cleaning process is complete, lock down of autonomous gardener subsystem 300 takes place. Once the system is locked out, the secondary door into the grow space unlocks.

[00127] In an embodiment of the invention, sixteen (16) plants per channel may be used to optimize the cost of the sensors 162 and grow lights 904 while also limiting the impact of growth anomalies and/or variations from impacting the ability of the system 400 to develop correlations in the data 810. As may be known to persons skilled in the art, a channel of for example four plants may cost significantly more to operate (compared to embodiments having a greater number of plants, for example, 16 plants per channel), and the data 810 could have more noise (or variability) in the signal due to natural plant variations, with very little improvement in plant growth and health. Embodiments comprising, for example, 16 plants per channel preferably creates a robust data signal for each IoT node which provides cleaner data for the system 400 to analyze when running deep learning algorithms. Embodiments comprising plant quantities of greater than, for example, 16 plants may make the use of load cells difficult, may make optimizing the hardware more difficult and expensive and may not optimize plant health as effectively per unit of cost. In addition, the decrease in noise benefited from adding anything more than, for example, 16 plants (such as, for example, 20 plants) may be marginal or on the order of statistical error. In preferable embodiments, the channels are created in rows two plants wide to facilitate access by the robotic gardener system 300 to each plant effectively using the tools 302 with which it will be equipped. Accordingly, preferable embodiments of the invention include a channel design of 8x2 as such a configuration fits into current greenhouse and facility designs, fits on widely available plant benches and aeroponics systems and can work well with load cells 924 to measure plant mass. An 8x2 configuration also adequately fits grow lights (e.g., LED), since most high-end grow lights are designed to service a square area which for the 8x2 configuration, fits three grow lights. The 8x2 configuration may preferably optimize costs since grow lights and sensors are typically the most expensive components of the facility, with load cells 924 also typically being a high cost expenditure. Persons skilled in the art, however, will appreciate that channel designs having configurations other than 8x2 can be adapted for use with the present invention.

[00128] Preferably, when connected to the server 328 implementing algorithms (e.g., the AI algorithms 500 described herein), the analysis of the IoT network data 800 may generate further data on plant growth that may have not otherwise been discovered. Server 328 integration also enables the autonomous optimization of inputs and controls to maximize metrics such as: plant yield, plant growth rate, revenue/plant, yield/plant and/or quality/plant. In preferable embodiments, the algorithms 500 will be implemented by the system 400 to facilitate performance of experiments on plant growth by the facility that will create data on growing all types of plants that may never have been discovered before.

[00129] Persons skilled in the relevant art may appreciate the cost saving and/or efficiency benefits realized from the integration of these traditionally disparate systems; however, persons skilled in the relevant art may not have realized how to coordinate their actions, particularly for example over an IoT network 200. Persons skilled in the relevant art may also not have appreciated the ability to acquire data that can be sold for additional revenue, nor the potential for discovery of new growing methods that could revolutionize the industry. Persons skilled in the relevant art may also appreciate that the combination of these systems inside a CEA with an IoT network will preferably facilitate faster and more reliable inspection and/or production of crops with greater yields and/or higher quality.

[00130] Lid Design

[00131] FIGS. 12A and 12B depict a lid 900 adapted for use with the planter box 14 in accordance with a preferred embodiment of the present invention. Although the lid 900 depicted in FIGS. 12A and 12B is adapted for an 8x2 plant configuration, persons skilled in the art will appreciate that alternate configurations are within the scope of the present invention. FIG. 12A depicts the underside of the lid 900 (i.e., the surface facing the plants when the lid 900 is installed on the planter box 14). The lid 900 preferably includes vents 902 (e.g., sixteen vents) that surround the planter box 14 to facilitate ventilation and surround the plants in a warm convection environment. In addition, the lid 900 includes grow lights 904 for promoting plant growth and the heat generated by the grow lights 904 also contributes to the warm environment. In a preferred embodiment, the lid 900 includes three (3) grow lights 904 for every 16 plants (in an 8x2 configuration; not shown). The heat preferably facilitates the draw of nutrients through the plants for increasing crop yield. In a preferred embodiment, the irrigation subsystem 110 supplies a plurality of spray heads 30 adapted to provide plants with fresh water and/or nutrient solution.

[00132] In preferable embodiments, the lid 900 is adapted to engage and/or receive one or more pillars 920 (alternatively“posts 920”) as depicted in FIGS. 13A-C. The pillars 920 preferably house or include root zone sensors 922 positioned within the growth solution in a hydroponic system or in close proximity to the roots in an aeroponic system, as shown in the side view of the post 920 FIG. 13B, which are adapted to monitor for example root health and/or growth medium conditions in the planter box 14. In addition, the pillars 920 are preferably adapted to include one or more mass sensors 924 (or“load cells 924”) for tracking plant growth (e.g., the weight of the plants to determine in real time which variables optimize and/or promote growth) as depicted in FIGS. 13B and 13C. In preferable embodiments, the pillars 920 are adapted to facilitate power and/or utility cables 926 (e.g., through a hollow centre) from a first to a second end of the post 920 as shown in the cross-sectional view of the post 920 (FIG. 13A).

[00133] The lid 900 is preferably adapted to support the growth surface area 18 of the planter box 14 (as shown in FIG. 12C) and accommodate the height of a predetermined number (e.g., sixteen) of plants. In preferable embodiments, the lid 900 is adapted to include clips (not shown) to route water lines (e.g., ¼” poly fridge lines) for supplying a plurality of sprayers (e.g., 4 sprayers per plant) from about 80 to about 100 psi and 50 micron droplets. In preferable embodiments, when compared to traditional systems in the prior art, the lid 900 and planter box 14 is adapted to facilitate significant savings in water use (e.g., up to 98%) and nutrient use (e.g., up to 66%) due to reduced or no soil use (e.g., preferably in a system adapted for hydroponics or aeroponics). This preferred embodiment may also facilitate faster plant growth with the plants in closer proximity to each other.

[00134] FIG. 12B depicts the outer surface of the lid 900 (i.e., the surface facing away from the plants when the lid 900 is installed on the planter box 14). As best shown in FIG. 12B, the lid 900 further includes a light and air sensor 906 for monitoring the intensity of light from the grow lights 904 and air quality (e.g., oxygen level, carbon dioxide level, carbon monoxide levels and levels of other gases known to affect plant growth, temperature, humidity, etc.). [00135] FIG. 12C depicts a top view of the planter box 14 without the lid 900 including the posts 920 projecting vertically and a drain 908 to, for example, facilitate water egress in a system adapted for aeroponics, as well as facilitating power and/or utility line entry into the planter box environment. Such a configuration also supports a vertical stacked configuration of the planter boxes (as discussed below).

[00136] As best shown in FIG. 13A, a top view of the post 920, a wireless interface 928 facilitates communication of the light and air sensor 906, root zone sensors 922, and mass sensors 924 with the IoT network 200. In a preferred embodiment, the post 920 is adapted to position the mass sensors 924 beneath the plants and/or in a position to optimize the measurement of plant mass as will be understood by a person of skill in the art.

[00137] In a preferred embodiment, the lid 900 may be removed by the robotic gardener subsystem 300 (e.g., using the tools 302) to facilitate access to the plants 16. Alternatively, the lid 900 may be removed manually. In an embodiment, the lid 900 is removably secured to the planter box 14 (e.g., clips, fasteners, hinges, pulleys, etc.).

[00138] Vertical Growth

[00139] Persons skilled in the art of the present invention will appreciate that in an alternate embodiment, the planter boxes may be arranged in a vertical and/or stacked configuration. In a vertical grow configuration, planter boxes 14 are stacked on-top of one another with a predetermined amount of spacing in between (e.g., eight feet) to accommodate the heights of the plants. The robotic gardener subsystem 300 is adapted to navigate the stacked planter boxes in three-dimensions using the cable drive subsystem 350. In addition, the grow lights 904 and fans 24 are preferably positioned in a fixed location on the underside of the planter box 14 (e.g., aeroponic) above as shown in FIG. 14. In a preferred embodiment, in the vertical growth configuration, four (4) grow lights 904 are used for every 16 plants (not shown). As shown in FIG. 14, the spacing between the planter boxes 14 is sufficient to facilitate manipulation of the plants by the art 312 and the tools 302 of the robotic gardener subsystem. In a preferred embodiment, the robotic gardener subsystem positioned in an east-west orientation is adapted to work on plants having a north-south exposure and the robotic gardener subsystem positioned in a north-south orientation is adapted to work on plants having an east-west exposure.

[00140] Online Farmer's Market & Autonomous Delivery Network

[00141] In an embodiment of the present invention the CEA facility 10 is equipped with an E- commerce front end that preferably enables customers to select, purchase and/or order fresh cannabaceae directly from the facility allowing for guaranteed delivery times. This e-commerce platform may preferably use a suite of integrated open source software and AI algorithms to automate inventory management, website analytics, business analytics, facility integration, customer data, payment information and/or delivery. The e-commerce platform and AI algorithms are connected to a custom delivery app, that may function similarly to other applications (e.g., Uber™), using the latest web application technologies. The delivery network is preferably designed for future drone delivery and/or autonomous car delivery. The E- commerce front end and delivery app are preferably directly connected to the facility database and server to enable seamless integration and control of facility operations, inventory management, IoT control systems and/or the e-commerce front end from a mobile device. The e-commerce system and the facility database are preferably connected using a blockchain that allows the transparent and instant transfer of detailed product information, growing conditions, payment processing and/or delivery information directly to the customer. This preferably allows for complete autonomous control of the entire supply chain including automated delivery with the delivery app. The delivery app is preferably designed to use webhooks from the e-commerce platform and the facility server to ensure the error-free delivery of produce direct to the customer, preferably using a third party GPS API (e.g., Google Maps™). The system is preferably designed to seamlessly integrate with drone delivery and/or autonomous vehicle delivery. Preferably, the E-commerce front end and custom delivery app implements seamlessly into E-commerce platforms and web development and web design tools regardless of the platform, and the app is preferably designed to use APIs and webhooks to connect third party software directly to the facility to facilitate drone delivery and autonomous vehicle delivery through the E-commerce platform backend.

[00142] Persons skilled in the relevant art may appreciate that the E-commerce front end and custom delivery app as integrated into the CEA facility, will facilitate the autonomous control and/or management of the entire supply chain, including real-time inventory management, instant order processing capabilities and/or real-time, direct-to-customer delivery without any human interaction. This may preferably provide organizations and operators the specific benefit of saving money in supply chain management. Persons skilled in the relevant art may also appreciate that by incorporating the server with algorithms, IoT network and/or database, supply chain management insights may be provided to enable algorithms adapted to optimize business processes to manage inventories, production rates and/or delivery routes. Although desirable, persons skilled in the relevant art may have not understood the combination of systems and/or integration methods to facilitate a fully autonomous, vertically integrated supply chain which also directly connects into CEA facility operations while providing insights on business performance, supply chain performance and/or analysis of business metrics. Deep Learning

[00143] In preferable embodiments, deep learning may be used to provide fully autonomous indoor agriculture production systems for the Cannabaceae production industry. These production systems may preferably require autonomous production robotic gardeners and an autonomous IoT facility control system connected to a deep learning server and database. In an embodiment of the present invention, a vision system will be utilized to predict the identity of the plants, their components and the associated mission tasks necessary for the plants.

[00144] In the prior art, there may have been challenges identifying the genotype, phenotype and stage of growth in the plants life cycle. Recent studies in the prior art may have overcome many of these challenges with high throughput systems for plant phenotyping [See, for example, references 1, 2, 3, 4, 5] as well as plant segmentation with feature extraction [See, for example, references 6, 7, 8, 9] This prior art research may have included creating robust solutions to feature extraction, segmentation and/or classification when identifying plants with computer vision systems. One challenge which may be addressed by the present invention is incorporating the time aspect of classification into a deep learning model, since the stage of growth of each plant determines the facility outputs, environmental controls of the facility and also the mission task of the robot.

[00145] In the prior art, Recurrent Neural Networks (Long Short Term Memory RNNSs in particular) may be able to articulate and learn complicated long-range dynamics and may have become popular for task recognition. CNNs have a well-documented history of accurately segmenting and classifying visual data (especially using, e.g., AlexNet and ResNet). Preferred embodiments of the present invention may include combining the learning capabilities of CNNs with the long term, time-based task recognition capabilities of LSTM RNN [See, for example, references 4, 11] In an embodiment of the invention, the growth and development of Cannabaceae plants is preferably assessed as an action recognition problem by using CNN for extracting discriminative features and then applying LSTM for encoding the growth behavior of the plants and the resulting robotic gardener task. Preferably, task outputs may be created and associated with time dependant features of plant growth.

[00146] FIG. 7 depicts a CNN (e.g., Alexnet) in accordance with the prior art. A CNN consists of convolutional layers, max pooling layers and fully connected layers. Each convolutional layer has an output block of two-dimensional images, that are convolved by previous feature maps with a smaller filter which then learn the parameters during the training process. The last layers tightly connected together where class scores are obtained from the final layer. [See, for example, reference 4]

[00147] In the prior art, the CNN structure may have varied based on the application and the size of the training dataset. Several architectures may have been developed and reported to work well for image classification and segmentation problems in self driving car applications, among which AlexNet and ResNet26 [See, for example, reference 4] are the most notable ones. FIG. 7 depicts the schematic of a 5-layer AlexNet, three of which are followed by max pooling layers as well as three fully connected layers. This is a network that has been reported to perform extremely well in the prior art.

[00148] FIG. 8 depicts the structure of a prior art LSTM. At each time point the memory cell may be filtered based on previous output, current input and current memory cell data f and s may be hyperbolic tangent and sigmoid functions, and represent element-wise multiplication. [See, for example, reference 4]

[00149] In preferable embodiments, Deep Reinforcement Learning is used to, for example, control the arms 312 and tools 302 of the robotic gardener subsystem 300 using data 806 collected by the visual detection system 3 l0a in real-time. Persons skilled in the art will appreciate that deep reinforcement learning (“DRL”) is preferably used for unsupervised autonomous robot control. DRL uses deep learning and reinforcement learning principles to create efficient algorithms that can be applied to robotics, among other fields. Persons skilled in the art will understand that DRL preferably uses raw sensor or image signals as input and may also benefit from end-to-end reinforcement learning and convolutional neural network.

[00150] Although practical, standard RNNs of the prior art may not be adapted to articulate time-based dependencies more than a few steps. An LSTM of the prior art may include a memory cell and gates that control when new information should be written to memory or how much of the current memory content should be replaced. The state of the LSTM at each point in the network may analyze the visual input at that instance and combine that with data output of the previous cell in addition to the current content of the memory cell. The input gate may filter new input data that is recorded into memory, and the output gate may filter the old memory that is to be preserved at a given time step. The LSTM output cell may also be processed by applying the output gate to the memory cell. This may allow the LSTM to articulate and learn long-term time dependencies. When training an LSTM, the model may learn when to update the memory, fully or partially, based on the dataset and incoming data.

[00151] Code and Documentation [00152] In an embodiment of the present invention, a pretrained CNN (e.g., Alexnet) pre- trained using, for example, ImageNet may be used with the system. The last two layers of the CNN will preferably be trained using a dataset including Cannabaceae plants from the database. In some embodiments, the system includes a visual detection system (e.g., an NIR RGB binocular vision system) to record video data of Cannabaceae plants growing from seed to full maturity (e.g., 1FPS). As the data is received, the pretrained CNN may preferably be updated in the last few layers with the growing dataset. Preferably, each life cycle stage of the plants that corresponds to a new set of robotic gardener tasks will be associated with its own dataset and CNN.

[00153] In preferable embodiments, once the CNNs have been pre-trained on each life cycle the output of the last fully connected layer of the CNN before the classification layer may be used. This output preferably feeds into each corresponding time frame of the LSTM in the LSTM-CNN model. The parameters of the CNN are preferably trained using Stochastic Gradient Descent (“SGD”) in groups of approximately 30, anticipate using a learning rate of about 0.001, weight decay of approximately 0.000001 and/or momentum of about 0.95.

[00154] In preferable embodiments, SGD may also be used for the LSTM and be trained with the same or similar group size, a larger / same / smaller fixed learning rate of approximately 0.01, the same or similar momentum, and larger / same / smaller weight decay of about 0.005. Preferably, a machine learning library (e.g., TensorFlow) is used with a neural networks API (e.g., Keras), with augmentation of the model using cloud GPU framework (e.g., Nvidia’s Cloud GPU framework) containers to optimize the training and parameters.

References [00155] [1] T. Brown, R. Cheng, X. Sirault, T. Rungrat, K. Murray, M. Trtilek, R. Furbank,

M. Badger, B. Pogson, and J. Borevitz,“Traitcapture: genomic and environment modelling of plant phenomic data,” in Current Opinion in Plant Biology, 2014.

[00156] [2] M. Minervini, M. Giuffrida, P. Perata, and S. Tsaftaris,“Phenotiki: An open software and hardware platform for affordable and easy image-based phenotyping of rosette- shaped plants,” The Plant Journal, 2017.

[00157] [3] N. Fahlgren, M. Feldman, M. A. Gehan, M. S. Wilson, C. Shyu, D. W. Bryant, S.

T. Hill, C. J. McEntee, S. N. Wamasooriya, I. Kumar, T. Ficor, S. Turnipseed, K. B. Gilbert, T. P. Brutnell, J.C. Carrington, T. C. Mockler, and I. Baxter,“A versatile phenotyping system and analytics platform reveals diverse temporal responses to water availability in setaria,” in Molecular Plant, 2015.

[00158] [4] Sarah Taghavi Namin, Mohammad Esmaeilzadeh, Mohammad Najafi, Tim B.

Brown, and Justin O. Borevitz, “Deep Phenotyping: Deep Learning for Temporal Phenotype/Genotype Classification,” Australian National University, Canberra, Australia, 2017.

[00159] [5] A. Knecht, M. Campbell, A. Caprez, D. Swanson, and H. Walia,“Image harvest: an open-source platform for high-throughput plant image processing and analysis,” Journal of Experimental Botany, 2016.

[00160] [6] Yu Sun, Yuan Liu, Guan Wang, and Haiyan Zhang,“Deep Learning for Plant

Identification in Natural Environment,” Computational Intelligence and Neuroscience, vol. 2017, Article ID 7361042, 6 pages, 2017. [00161] [7] X. Yin, X. Liu, J. Chen, and D. Kramer,“Multi-leaf tracking from fluorescence plant videos,” in ICIP, 2014.

[00162] [8] S. G. Wu, F. S. Bao, E. Y. Xu, Y.-X. Wang, Y.-F. Chang, and Q.-L. Xiang,“A leaf recognition algorithm for plant classification using probabilistic neural network,” in Signal Processing and Information Technology, 2007.

[00163] [9] A. Aakif and M. F. Khan,“Automatic classification of plants based on their leaves,” in Biosystems Engineering, 2015.

[00164] [10] A. Krizhevsky, I. Sutskever, and G. E. Hinton,“Imagenet classification with deep convolutional neural networks,” in NIPS, 2012.

[00165] [11] Michael Teti, Elan Barenholtz, Shawn Martin, and William Edward Hahn“A

Systematic Comparison of Deep Learning Architectures in an Autonomous Vehicle” Florida Atlantic University, 2018.

[00166] Data Store

[00167] A preferred embodiment of the present invention provides a system comprising data storage that may be used to store all necessary data required for the operation of the system. A person skilled in the relevant art may understand that a“data store” refers to a repository for temporarily or persistently storing and managing collections of data which include not just repositories like databases (a series of bytes that may be managed by a database management system (DBMS)), but also simpler store types such as simple files, emails, etc. A data store in accordance with the present invention may be one or more databases, co-located or distributed geographically or cloud-based. The data being stored may be in any format that may be applicable to the data itself, but may also be in a format that also encapsulates the data quality.

[00168] The foregoing description has been presented for the purpose of illustration and maybe not intended to be exhaustive or to limit the invention to the precise form disclosed. Other modifications, variations and alterations are possible in light of the above teaching and may be apparent to those skilled in the art, and may be used in the design and manufacture of other embodiments according to the present invention without departing from the spirit and scope of the invention. It may be intended the scope of the invention be limited not by this description but only by the claims forming a part of this application and/or any patent issuing herefrom.

Claims

Hll EMBODIMENTS FOR WHICH AN EXCLUSIVE PRIVILEGE OR PROPERTY IS CLAIMED ARE AS FOLLOWS:

1. A system for growing plants in a facility, wherein the system comprises:

(a) an irrigation subsystem associated with the plants, comprising: (i) one or more spray heads; (ii) a water tank comprising a volume of water; and (iii) a pump adapted to transfer the water to the one or more spray heads to irrigate the plants;

(b) a robotic gardener subsystem comprising: (i) a chassis; (ii) tools adapted to manipulate the plants; (iii) on-board sensors adapted to receive data associated with the plants; and (iv) a command processor operative to (1) collect and transmit the data associated with the plants and (2) controlling the tools and/or the irrigation subsystem;

(c) an AI control system comprising: (i) a server operative to (1) electronically receive the data associated with the plants; (2) apply one or more artificial intelligence algorithms to the data associated with the plants to generate machine learning data and pattern data; (3) generate instructions for the tools and/or the irrigation subsystem based on the machine learning data and pattern data; and (4) transmit the instructions to the command processor; and (ii) a database to electronically store the data associated with the plants, the instructions for the tools and/or the irrigation subsystem, the machine learning data and the pattern data;

wherein the system is operative to autonomously optimize the growth of the plants in the facility based on the instructions.

2. The system of claim 1, wherein the on-board sensors comprise: a visual detection system; a microscope camera; a sonar sensor; a backscatter detection system; a spectrometer camera; and an atmospheric sensor board.

3. The system of any one of claims 1-2, wherein the data associated with the plants comprises: health (including disease and infection), stage of growth, images, video, humidity levels, temperature, oxygen levels, type and intensity of electromagnetic radiation, carbon dioxide levels, and/or plant mass.

4. The system of any one of claims 1-3, further comprising a growth subsystem for delivering a predetermined nutrient formulation to the plants in the facility, the growth subsystem comprising: (a) a biosensor adapted to receive nutrient data associated with the plants; (b) a nutrient supply comprising one or more nutrients; (c) a holding tank for mixing the one or more nutrients with water from the water tank for generating a nutrient formulation; (d) a microcontroller operative to (1) collect and transmit the nutrient data associated with the plants to the AI control system to generate instructions for a predetermined nutrient formulation and (2) receive the instructions from the AI control system for generating the predetermined nutrient formulation in the holding tank; and (e) nutrient lines to deliver the predetermined nutrient formulation to the plants.

5. The system of any one of claims 1-4, further comprising a cable drive subsystem for moving the robotic gardener subsystem along an x-axis, a y-axis and a z-axis within the facility based on instructions generated by the AI control system using data from the visual detection system, the cable drive subsystem comprising:

(a) a y-axis support beam adapted for moveable engagement with at least two x-axis support beams at a first end and a second end of the y-axis support beam;

(b) an x-axis motor associated with the x-axis support beams and operatively connected to the first end of the y-axis support beam;

(c) a z-axis support adapted for moveable engagement along the y-axis support beam at a first end of the z-axis support and attached to the robot chassis at a second end of the z-axis support; (d) a y-axis motor associated with the y-axis support beam and operatively connected to the first end of the z-axis support; and

(e) a z-axis motor associated with the robot chassis and operatively connected to the second end of the z-axis support;

wherein the system is operative to facilitate three-dimensional movement based on selected activation of the x-axis motor, the y-axis motor, and the z-axis motor by the command unit.

6. The system of any one of claims 1-5 wherein the plants are grown hydroponically or aeroponically.

7. A method for optimizing the growth of plants in a facility, wherein the method comprises the steps of:

(a) operating an irrigation subsystem associated with the plants, comprising: (i) one or more spray heads; (ii) a water tank comprising a volume of water; and (iii) a pump adapted to transfer the water to the one or more spray heads to irrigate the plants;

(b) operating a robotic gardener subsystem comprising: (i) a chassis; (ii) tools adapted to manipulate the plants; (iii) on-board sensors adapted to receive data associated with the plants; and (iv) a command processor operative to (1) collect and transmit the data associated with the plants and (2) controlling the tools and/or the irrigation subsystem;

(c) operating an AI control system comprising: (i) a server operative to electronically receive the data associated with the plants to: (1) apply one or more artificial intelligence algorithms to the data associated with the plants to generate machine learning data and pattern data; (2) generate instructions for the tools and/or the irrigation subsystem based on the machine learning data and pattern data; and (3) transmit the instructions to the command processor; and (ii) a database to electronically store the data associated with the plants, the instructions for the tools, the machine learning data and the pattern data;

wherein the data associated with the plants and the instructions for the tools and/or the irrigation subsystem based on the machine learning data and pattern data are for use in autonomously optimizing the growth of the plants in the facility.

8. A non-transient computer readable medium on which is physically stored executable instructions for use in association with a facility for growing plants, the facility comprising: (1) an irrigation subsystem comprising (i) one or more spray heads; (ii) a water tank comprising a volume of water; and (iii) a pump adapted to transfer the water to the one or more spray heads to irrigate the plants; (2) a robotic gardener subsystem comprising: (i) tools adapted to manipulate the plants; (ii) on-board sensors; and (iii) a command processor; and (3) an AI control system comprising a server to automatically:

(a) collect and/or electronically communication data associated with the plants from the command processor to the server;

(b) apply one or more artificial intelligence algorithms to the data associated with the plants to generate machine learning data and pattern data;

(c) generate instructions for the tools and/or the irrigation subsystem based on the machine learning data and pattern data;

(d) communicate the instructions to the command processor; and

(e) electronically store the data associated with the plants, the instructions for the tools and/or the irrigation subsystem, the machine learning data and the pattern data; wherein the data associated with the plants and the instructions for the tools and/or the irrigation subsystem are for use in autonomously optimizing the growth of the plants in the facility.