WO2021159603A1 - Indoor navigation method and apparatus for unmanned aerial vehicle, device and storage medium - Google Patents

Abstract

An indoor navigation method and apparatus for an unmanned aerial vehicle, a device and a storage medium. The method comprises: upon receiving an unmanned aerial vehicle navigation request, obtaining an initial position and a destination position of an unmanned aerial vehicle (S10); acquiring operating state information of the unmanned aerial vehicle by means of a first acquisition apparatus of the unmanned aerial vehicle, and acquiring surrounding environment information of different heights and different photographing angles at the initial position by means of a second acquisition apparatus of the unmanned aerial vehicle (S20); constructing a feature point cloud of a photographed object according to the operating state information and the surrounding environment information, and processing the feature point cloud to obtain a point cloud model of the photographed object (S30); and superposing the point cloud model and a preset BIM model to obtain a superposed model, generating a navigation route to the destination position according to the superposed model, and controlling the unmanned aerial vehicle to operate according to the navigation route (S40). Indoor automatic navigation for unmanned aerial vehicles is achieved, and the accuracy of indoor navigation for unmanned aerial vehicles is improved.

Description

UAV indoor navigation method, device, equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on February 12, 2020, the application number is 202010089061.5, and the invention title is "UAV indoor navigation method, device, equipment and storage medium". The entire content of the patent application is approved. The reference is incorporated in this application.

Technical field

This application relates to the field of artificial intelligence technology, and in particular to the indoor navigation method, device, equipment and storage medium of an unmanned aerial vehicle.

Background technique

The current drones that can realize autonomous flight rely on satellite signals to give location information, and then use the existing map to plan the route based on the location information. However, the drone cannot receive GPS signals in an environment with shelters such as indoors and tunnels. Therefore, the indoor positioning and navigation of UAVs are usually in the following ways:

1. Based on Bluetooth low energy or wireless network positioning, if this technology wants to achieve higher accuracy, it needs to deploy the Bluetooth signal source grid in advance in advance, and then calculate the signal strength on the client to locate, which makes the indoor positioning cost more expensive. high;

2. Based on cellular network positioning, this technology does not require any front-end network deployment, and ordinary devices that can receive mobile phone signals can be positioned by comparing signals from multiple base stations. But it is difficult to guarantee the positioning accuracy;

3. Positioning technology based on radio frequency identification, which requires the deployment of radio frequency identification equipment in advance, and the accuracy of indoor navigation and positioning is not ideal;

4. Visual positioning. This positioning system can use the camera to collect images of the surrounding environment and determine the location by comparing it with the information entered in advance. This method cannot determine different partitions of the same layout (such as different rooms with the same hotel decoration), and Due to the changeable environment, in a relatively small space, drones may not be able to avoid obstacles smoothly.

The inventor realized that in the above-mentioned way, the drone cannot obtain the actual state of itself and the surrounding environment during the flight. When an emergency occurs around the drone, the drone cannot respond in time, making it difficult for the drone to stay indoors. Autonomous positioning and navigation in the environment.

Summary of the invention

technical problem

The solution to the problem

Technical solutions

The main purpose of this application is to provide a method, device, equipment and storage medium for UAV indoor navigation, aiming to solve the current technical problem of high cost and low accuracy of UAV indoor navigation.

In order to achieve the above objective, this application provides an indoor navigation method for a UAV. The indoor navigation method for a UAV includes the following steps:

When receiving the drone navigation request, get the initial position and destination position of the drone;

Collect the operating state information of the drone through the first collection device in the drone, and collect the surrounding environment at different heights and different shooting angles at the initial position through the second collection device in the drone information;

Constructing a feature point cloud of the shooting object according to the operating state information and the surrounding environment information, and processing the feature point cloud to obtain a point cloud model of the shooting object;

The point cloud model and the preset BIM model are superimposed to obtain a superimposed model, a navigation route to the destination location is generated according to the superimposed model, and the drone is controlled to operate according to the navigation route.

In addition, in order to achieve the above objective, the present application also provides an indoor navigation device for an unmanned aerial vehicle. The indoor navigation device for an unmanned aerial vehicle includes:

The request receiving module is used to obtain the initial position and destination position of the drone when receiving the drone navigation request;

The information collection module is used to collect the operating state information of the UAV through the first collection device in the UAV, and collect the different heights and heights at the initial position through the second collection device in the UAV. Surrounding environment information at different shooting angles;

A model construction module, configured to construct a feature point cloud of the shooting object according to the operating state information and the surrounding environment information, and process the feature point cloud to obtain a point cloud model of the shooting object;

The route generation module is used to superimpose the point cloud model and the preset BIM model to obtain a superimposed model, generate a navigation route to the destination location according to the superimposed model, and control the drone to operate according to the navigation route .

In addition, in order to achieve the above purpose, this application also provides an indoor navigation device for drones;

The UAV indoor navigation device includes: a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein: the computer program is executed by the processor to achieve the above The steps of the UAV indoor navigation method, wherein the UAV indoor navigation method at least includes the following steps: when receiving the UAV navigation request, obtain the initial position and the target position of the UAV; The first collection device in the drone collects operating state information of the drone, and the second collection device in the drone collects surrounding environment information at different heights and different shooting angles at the initial position; The operating state information and the surrounding environment information construct a feature point cloud of the shooting object, processing the feature point cloud to obtain a point cloud model of the shooting object; superimposing the point cloud model with a preset BIM model to obtain a superimposed model , Generating a navigation route to the destination location according to the superposition model, and controlling the drone to operate according to the navigation route.

In addition, in order to achieve the above object, this application also provides a computer storage medium; the computer storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned indoor navigation method for drones are realized, wherein: The indoor navigation method of the UAV includes at least the following steps: when receiving the UAV navigation request, obtain the initial position and the target position of the UAV; The operating state information of the man-machine is collected by the second collecting device in the drone to collect the surrounding environment information at different heights and different shooting angles at the initial position; and the shooting is constructed according to the operating state information and the surrounding environment information The feature point cloud of the object is processed, and the feature point cloud is processed to obtain the point cloud model of the shooting object; the point cloud model and the preset BIM model are superimposed to obtain the superposition model, and the superposition model is generated according to the superposition model. Navigate the route, and control the UAV to operate according to the navigation route.

The embodiment of the application proposes an indoor navigation method, device, equipment, and storage medium for a UAV. When a terminal receives a UAV navigation request, it obtains the initial position and the target position of the UAV; The first collection device in the UAV collects the operating state information of the UAV, and the second collection device in the UAV collects the surrounding environment information at different heights and different shooting angles at the initial position; according to the operation State information and the surrounding environment information construct a feature point cloud of the subject, process the feature point cloud to obtain a point cloud model of the subject; superimpose the point cloud model with a preset BIM model to obtain a superimposed model, and The superposition model generates a navigation route to the destination location, and controls the UAV to operate according to the navigation route. The technical solution of this embodiment does not require additional hardware costs, and the information of building components, doors and windows and other UAV navigation obstacles can be accurately determined through the superimposed model, so that the UAV can better avoid obstacles and reduce the incidence of accidents. The indoor automatic navigation of the UAV is realized, and the accuracy of the indoor navigation of the UAV is improved.

The beneficial effects of the invention

Brief description of the drawings

Description of the drawings

FIG. 1 is a schematic diagram of a device structure of a hardware operating environment involved in a solution of an embodiment of the present application;

FIG. 2 is a schematic flowchart of the first embodiment of the indoor navigation method for drones under this application;

FIG. 3 is a schematic diagram of functional modules of an embodiment of an indoor navigation device for drones under this application.

The realization, functional characteristics, and advantages of the purpose of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings.

Invention embodiment

Embodiments of the present invention

It should be understood that the specific embodiments described here are only used to explain the present application, and are not used to limit the present application.

As shown in Figure 1, Figure 1 is the terminal of the hardware operating environment involved in the solution of the embodiment of the application (also called the UAV indoor navigation device, where the UAV indoor navigation device can be a separate UAV indoor navigation device The structure can also be formed by combining other devices with the UAV indoor navigation device) schematic diagram of the structure.

The terminal in the embodiments of this application can be a fixed terminal or a mobile terminal, such as smart air conditioners with networking functions, smart lights, smart power supplies, smart speakers, autonomous vehicles, PC (personal computer) personal computers, smart phones, and tablet computers. , E-book readers, portable computers, etc.

As shown in FIG. 1, the terminal may include a processor 1001, for example, a central processing unit (CPU), a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to implement connection and communication between these components. The user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as WIreless-FIdelity, WIFI interface). The memory 1 005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), for example, a magnetic disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

Optionally, the terminal may also include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, and a WiFi module; an input unit, a display screen, and a touch screen; the network interface can be selected in addition to WiFi, Bluetooth, Probes and so on. Among them, sensors such as light sensors, motion sensors and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor; of course, the mobile terminal may also be equipped with other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc., which will not be repeated here.

Those skilled in the art can understand that the terminal structure shown in FIG. 1 does not constitute a limitation on the terminal, and may include more or less components than shown in the figure, or combine some components, or arrange different components.

As shown in Figure 1, the computer software product is stored in a storage medium (storage medium: also called computer storage medium, computer medium, readable medium, readable storage medium, computer readable storage medium, or directly called medium, etc., storage medium It can be a non-volatile readable storage medium, such as RAM, magnetic disk, optical disk, and includes several instructions to make a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute this application In the method described in each embodiment, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a computer program.

In the terminal shown in FIG. 1, the network interface 1004 is mainly used to connect to a back-end server and communicate with the back-end server; the user interface 1003 is mainly used to connect to a client (user side) to communicate with the client; and the processor 1001 can be used to call a computer program stored in the memory 1005 and execute the steps in the UAV indoor navigation method provided in the following embodiments of the present application.

Based on the above hardware operating environment, an embodiment of the UAV indoor navigation method of the present application is proposed.

In the embodiment of the UAV indoor navigation method of the present application, two points in the indoor space are required, and the point cloud model generated in real time can automatically plan the UAV indoor navigation route, so that the UAV can navigate. specifically:

2, in the first embodiment of an indoor navigation method for an unmanned aerial vehicle of the present application, the indoor navigation method for an unmanned aerial vehicle includes:

In step S10, when the drone navigation request is received, the initial position and the target position of the drone are acquired.

The UAV indoor navigation method in this embodiment is applied to a terminal (also called UAV indoor navigation equipment). The terminal communicates with the UAV, and the terminal can control the UAV. The UAV has a preset collection device, The collection device is used to collect information about the surrounding environment of the drone and the operating status information of the drone (the operating status of the drone and the relative displacement information of the drone). The number of depth cameras, inertial measurement devices, perception cameras, and depth cameras is not limited. The drone sends the collected surrounding environment information and drone operation status information to the terminal, and the terminal processes the surrounding environment information and the drone operation Status information, get the UAV's indoor navigation route, and realize the accurate navigation of the UAV.

Specifically, the terminal receives the drone navigation request, and the triggering method of the drone navigation request is not specifically limited, that is, the drone navigation request can be triggered by the user actively, for example, the user clicks the drone navigation corresponding on the terminal display interface Button to trigger the drone navigation request; in addition, the drone navigation request can also be automatically triggered by the terminal. For example, the trigger condition of the drone navigation request is preset in the terminal: trigger the drone navigation request in the early morning every day. Collect xxx floor information, and the terminal will automatically trigger the drone navigation request when it reaches the wee hours.

When the terminal receives the drone navigation request, the terminal obtains the initial position and destination position of the drone. The initial position and destination position of the drone can be set by the user; for example, the initial position of the drone is entered on the user terminal It is: 1 room on the 3rd floor of the xxx building, and the destination is: 3 rooms on the 2nd floor of the xxx building.

In this embodiment, a specific implementation method for determining the initial position and the target position of the drone is provided, which includes the following steps:

Step a1, when receiving the drone navigation request, obtain the building identifier of the building where the drone is currently located, and the preset BIM model associated with the building identifier;

Step a2, construct a three-dimensional coordinate system based on the preset BIM model, use the three-dimensional coordinates of the current position of the drone as the initial position of the drone, and obtain the navigation destination corresponding to the drone navigation request; Use the three-dimensionality of the navigation destination as the target position of the drone.

That is, when the terminal receives the drone navigation request, the terminal obtains the building identifier of the building where the drone is currently located (the building identifier refers to the identification information that uniquely identifies the building, such as the name of the building or the location information of the building), and the terminal Obtain the preset BIM model associated with the building logo (the preset BIM model refers to the preset BIM model (Building Information Modeling model) associated with the building logo, and the BIM model contains buildings); it is generally constructed based on the preset BIM model In the three-dimensional coordinate system, the terminal uses the three-dimensional coordinates of the current position of the drone as the initial position of the drone, the terminal obtains the navigation destination corresponding to the drone navigation request, and uses the three-dimensional navigation destination as the destination position of the drone.

In this embodiment, a three-dimensional coordinate system is constructed based on the BIM model to accurately determine the initial position and target position of the drone, so as to realize accurate navigation of the drone.

Step S20: Collect operating state information of the drone through the first collection device in the drone, and collect different heights and different shooting angles at the initial position through the second collection device in the drone Surrounding environment information.

The collection device is preset in the drone, and the collection device is divided into a first collection device and a second collection device according to the purpose of the collection device. The first collection device is used to collect the operating state information of the drone, and the first collection device includes at least One inertial measuring device and at least one sensing camera; the second collecting device is used to collect information about the surrounding environment of the drone, and the second collecting device includes at least one depth camera. For example, the drone carries one inertial measuring device and one depth camera. And 4 environment-aware cameras, of which, the inertial measuring device is responsible for sensing the direction information of the drone, the environment-aware camera is responsible for obtaining the relative displacement of the drone, and the depth camera is responsible for sensing the depth image information of the drone’s object. Specifically, include:

Step b1: Adjust the height and shooting angle of the drone at the initial position, collect the direction information of the drone through the inertial measurement device, collect characteristic images through the sensing camera, and analyze the characteristic images to obtain The relative position information of the drone, using the direction information and the relative position information as operating state information of the drone;

Step b2: Transmit infrared pulses to the subject through the depth camera, receive the infrared pulse reflected by the subject and the reflection time of the infrared pulse, process the reflection time to obtain the depth image information of the subject, and convert the depth The image information serves as the surrounding environment information.

In this embodiment, the terminal controls the drone to autonomously adjust the height and shooting angle near the initial position, and performs multi-angle shooting to obtain feature images. The terminal extracts feature points of the feature image, and the terminal analyzes the feature image to obtain the relative position information of the drone. The direction information and relative position information are used as the operating status information of the UAV. The terminal emits infrared pulses through the depth camera, and obtains the depth image information by calculating the reflection time, that is, the distance from the surface of the object to the camera.

Step S30: Construct a feature point cloud of the shooting object according to the operating state information and the surrounding environment information, and process the feature point cloud to obtain a point cloud model of the shooting object.

The terminal converts the depth image information in the surrounding environment information into a three-dimensional feature point cloud, and the terminal fuses the three-dimensional feature point cloud into a three-dimensional grid to obtain a point cloud model, that is, the terminal emits rays from the current collection device position to the three-dimensional feature point cloud of the previous step. The feature point cloud is intersected to obtain the point cloud under the current frame perspective, and the terminal calculates its normal vector to register the input depth image information of the next frame, and continuously loop to obtain feature point clouds under different perspectives. The scene surface of the reconstructed subject is reconstructed to form a point cloud model. Specifically, step S30 includes:

Step b1, extracting direction information and relative position information in the operating state information, and iterating the direction information and the relative position information to obtain the attitude change value of the first collecting device in the UAV;

Step b2, extracting the depth image information in the surrounding environment information, and iterating the depth image information according to the attitude change value to obtain the feature point cloud of the drone photographed object;

Step b3, processing the characteristic point cloud by a preset SLAM algorithm to obtain a point cloud model of the shooting object.

Specifically, the terminal extracts the direction information and relative position information from the operating status information, and the terminal iterates the direction information and relative position information to obtain the attitude change value of the first acquisition device in the drone; the terminal extracts the depth in the surrounding environment information For image information, the terminal iterates the depth image information according to the attitude change value to obtain the feature point cloud of the drone photographed object; the terminal uses the preset SLAM algorithm (Simultaneous localization and mapping, synchronous positioning and mapping algorithm) to process the feature point cloud to obtain Point cloud model of the subject.

In this embodiment, the terminal determines the attitude change value of the drone to construct the characteristic point cloud of the shooting object, and obtains the approximate point cloud model of the shooting target according to the SLAM algorithm. The terminal recognizes the corresponding non-building components in real time according to the point cloud model Obstacle information.

Step S40: Superimpose the point cloud model and the preset BIM model to obtain a superimposed model, generate a navigation route to the destination location according to the superimposed model, and control the drone to operate according to the navigation route.

The BIM model is preset in the terminal, and the terminal determines the building component information according to the preset BIM model. The terminal can determine the non-building component information based on the point cloud model. The terminal superimposes the BIM model and the point cloud model to obtain a superimposed model. The superimposed model contains building components. For UAV navigation obstacles such as information and non-building component information, the terminal generates a navigation route to the destination location according to the superimposed model, and controls the UAV to operate according to the navigation route. Specifically, step S30 includes:

Step c1: Determine the reference position corresponding to the initial position in the preset BIM model, and compare the edge information in the point cloud model with the edge information at the reference position in the preset BIM model to obtain the result The minimum distance between the point cloud model and the preset BIM model;

Step c2, superimpose the point cloud model and the preset BIM model according to the minimum distance to obtain a superimposed model;

Step c3, trace back the path from the initial position according to the superimposed model, obtain a navigation route to the destination position, and control the UAV to operate according to the navigation route.

The terminal determines the reference position corresponding to the initial position in the preset BIM model. The terminal compares the image of the subject in the point cloud model with the image at the reference position in the preset BIM model to obtain the minimum distance between the edge feature points of the two images. The point cloud model and the preset BIM model are superimposed at the minimum distance to obtain the superimposed model. The terminal traces the path from the initial position according to the superimposed model, obtains the navigation route to the destination position, and controls the drone to operate according to the navigation route.

The technical solution of this embodiment does not require additional hardware costs, and the information of building components, doors and windows and other UAV navigation obstacles can be accurately determined through the superimposed model, so that the UAV can better avoid obstacles and reduce the incidence of accidents. The indoor automatic navigation of the UAV is realized, and the accuracy of the indoor navigation of the UAV is improved.

Further, on the basis of the first embodiment of the present application, a second embodiment of the indoor navigation method for drones of the present application is proposed.

This embodiment is a refinement of step S40 in the first embodiment. The difference between this embodiment and the first embodiment of this application lies in:

Step S41: Perform path traceability along the destination position from the initial position in the overlay model to determine whether there are obstacles in the traceability path, whether the traceability path repetition rate is greater than a preset repetition rate, and/or whether there are at least two Trace path

The terminal traces the path along the destination from the initial position in the superimposed model, that is, the superimposed model contains building component information and non-building component information, the terminal uses the building component information and non-building component information as obstacles, and the terminal avoids the obstacles. Path tracing, specifically, the terminal determines whether there are obstacles in the tracing path (obstacles can be walls, lamps, decorations, etc.), and whether the repetition rate of the traced path is greater than the preset repetition rate (the preset repetition rate refers to the preset repetition rate). The ratio of the full path to the repeated path, for example, the preset repetition rate is set to 30%) and/or whether there are at least two retrospective paths.

Step S42, if there are obstacles in the traceability path, change the traceability direction of the trace; if the traceability path repetition rate is greater than the preset repetition rate, then discard the traceability path; and/or if at least two traceability paths are obtained, the trace with the shortest distance The path is used as the UAV navigation route, and the UAV is controlled to operate according to the navigation route.

If there are obstacles in the tracing path, the terminal determines that the path has reached the end, and the terminal changes the path tracing direction; if the repetition rate of the tracing path is greater than the preset repetition rate, the terminal determines that the path is a repetitive path, and then abandons the tracing path; and/or if it is obtained There are at least two tracing paths. The terminal uses the shortest tracing path as the drone navigation route and controls the drone to operate according to the navigation route. The path generation method is given in this embodiment, which effectively ensures the rationality of the UAV navigation route and makes the UAV navigation more accurate.

Further, on the basis of the foregoing embodiments of the present application, a third embodiment of the indoor navigation method for drones of the present application is proposed.

This embodiment is a step after step S40 in the first embodiment. The difference between this embodiment and the first embodiment of the application lies in:

Step S50: When it is detected that the UAV deviates from the navigation route, a route control instruction is sent to the UAV to make the UAV return to the navigation route.

The terminal monitors the drone's running path information in real time. The running path information includes the running speed, running route, and running time. The terminal judges whether the drone deviates from the navigation route based on the drone's running route information. If it deviates from the navigation route, the terminal sends a route control instruction to the UAV so that the UAV can return to the navigation route according to the route control instruction.

Step S60: If the UAV does not return to the navigation route within a preset time period, send an information collection instruction to the UAV so that the UAV feeds back current operating parameters.

If the drone does not return to the navigation route within the preset time period (the preset time period is set according to the specific scenario, for example, the preset time period is set to 2 minutes), the terminal sends an information collection instruction to the drone, and the drone receiving terminal sends it The UAV obtains the current operating parameters. The operating parameters include operating time and operating route. The UAV feeds back the current operating parameters to the mobile terminal.

Step S70: Receive current operating parameters fed back by the drone, and if the current operating parameters are abnormal, output prompt information.

The terminal receives the current operating parameters fed back by the drone. The terminal compares the current operating parameters with the preset standard operating parameters to determine whether the current operating parameters meet the standard operating parameters. If the current operating parameters do not meet the standard operating parameters, the terminal determines the current operation If the parameter is abnormal, the terminal judges that the drone is faulty, and the terminal outputs prompt information. In this embodiment, the terminal monitors the operating status of the drone. When the drone fails, the terminal can output prompt information in real time to perform timely maintenance of the drone.

In addition, referring to Fig. 3, an embodiment of the present application also proposes an indoor navigation device for a drone, and the indoor navigation device for a drone includes:

The request receiving module 10 is used to obtain the initial position and the target position of the UAV when the UAV navigation request is received;

The information collection module 20 is configured to collect the operating state information of the drone through the first collection device in the drone, and collect the different heights at the initial position through the second collection device in the drone And surrounding environment information from different shooting angles;

The model construction module 30 is configured to construct a feature point cloud of the shooting object according to the operating state information and the surrounding environment information, and process the feature point cloud to obtain a point cloud model of the shooting object;

The route generation module 40 is configured to superimpose the point cloud model and the preset BIM model to obtain a superimposed model, generate a navigation route to the destination location according to the superimposed model, and control the drone to follow the navigation route run.

In an embodiment, the first acquisition device includes at least one inertial measurement device and at least one perception camera, and the second acquisition device includes at least one depth camera;

The information collection module 20 includes:

The first collection module is used to adjust the height and shooting angle of the drone at the initial position, collect the direction information of the drone through the inertial measurement device, collect characteristic images through the sensing camera, and analyze the Obtaining the relative position information of the drone by using the characteristic image, and using the direction information and the relative position information as the operating state information of the drone;

The second acquisition module is used to transmit infrared pulses to the subject through the depth camera, receive the infrared pulse reflected by the subject and the reflection time of the infrared pulse, process the reflection time to obtain the depth image information of the subject, The depth image information is used as surrounding environment information.

In an embodiment, the model construction module 30 includes:

The attitude calculation unit is used to extract the direction information and relative position information in the operating state information, and iterate the direction information and the relative position information to obtain the attitude change value of the first collecting device in the UAV ；

A point cloud determining unit, configured to extract the depth image information in the surrounding environment information, iterate the depth image information according to the attitude change value, and obtain the characteristic point cloud of the drone photographed object;

The model generating unit is configured to process the characteristic point cloud by using a preset SLAM algorithm to obtain a point cloud model of the shooting object.

In an embodiment, the route generation module 40 includes:

The information comparison sub-module is used to determine the reference position corresponding to the initial position in the preset BIM model, and compare the edge information in the point cloud model with the edge information at the reference position in the preset BIM model Compare to obtain the minimum distance between the point cloud model and the preset BIM model;

The model superimposition sub-module is used to superimpose the point cloud model and the preset BIM model according to the minimum distance to obtain a superimposed model;

The route generation sub-module is used to trace the path from the initial position according to the overlay model to obtain the navigation route to the destination position, and control the drone to operate according to the navigation route.

In an embodiment, the route generation sub-module includes:

The retrospective judgment unit is used to trace the path from the initial position in the superimposition model along the destination location to determine whether there are obstacles in the retrospective path, whether the retrospective path repetition rate is greater than a preset repetition rate and/or whether there is At least two tracing paths;

The control operation unit is used to change the path tracing direction if there are obstacles in the tracing path; if the repetition rate of the tracing path is greater than the preset repetition rate, the tracing path is abandoned; and/or if at least two tracing paths are obtained, the distance is changed The shortest traceability path is used as the drone navigation route, and the drone is controlled to operate according to the navigation route.

In an embodiment, the indoor navigation device for drones includes:

A route monitoring module, configured to send a route control instruction to the drone when it is detected that the drone deviates from the navigation route, so that the drone returns to the navigation route;

An instruction sending module, configured to send an information collection instruction to the drone if the drone does not return to the navigation route within a preset time period, so that the drone can feed back current operating parameters;

The prompt output module is used to receive the current operating parameters fed back by the drone, and output prompt information if the current operating parameters are abnormal.

Among them, the steps implemented by the various functional modules of the UAV indoor navigation device can refer to the various embodiments of the UAV indoor navigation method of the present application, which will not be repeated here.

In addition, the embodiment of the present application also proposes a computer storage medium, and the computer-readable storage medium may be non-volatile or volatile. The computer storage medium stores a computer program that, when executed by a processor, implements the operations in the UAV indoor navigation method provided in the above embodiments, wherein the UAV indoor navigation method includes the following steps: When receiving the drone navigation request, obtain the initial position and the target position of the drone; collect the operating state information of the drone through the first acquisition device in the drone, and use the drone The second collecting device in the S2 collects surrounding environment information at different heights and different shooting angles at the initial position; constructs a feature point cloud of the shooting object according to the operating state information and the surrounding environment information, and processes the feature point cloud to obtain The point cloud model of the shooting object; superimpose the point cloud model and the preset BIM model to obtain a superimposed model, generate a navigation route to the target location according to the superimposed model, and control the drone to follow the The navigation route runs.

It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity/operation/object from another entity/operation/object, and do not necessarily require or imply these There is any such actual relationship or order between entities/operations/objects; the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, An article or system includes not only those elements, but also other elements that are not explicitly listed, or include elements inherent to the process, method, article, or system. Without more restrictions, the element defined by the sentence "including a..." does not exclude the existence of other identical elements in the process, method, article, or system that includes the element.

As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment. The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separate. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solution of the present application. Those of ordinary skill in the art can understand and implement without creative work.

The serial numbers of the foregoing embodiments of the present application are for description only, and do not represent the superiority or inferiority of the embodiments.

Through the description of the above implementation manners, those skilled in the art can clearly understand that the above-mentioned embodiment method can be implemented by means of software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is better.的实施方式。 Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM/RAM) as described above. , Magnetic disks, optical disks), including several instructions to make a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the method described in each embodiment of the present application.

The above are only the preferred embodiments of the application, and do not limit the scope of the patent for this application. Any equivalent structure or equivalent process transformation made using the content of the description and drawings of the application, or directly or indirectly applied to other related technical fields , The same reason is included in the scope of patent protection of this application.

Claims (20)

An indoor navigation method for an unmanned aerial vehicle, wherein the indoor navigation method for an unmanned aerial vehicle includes the following steps: When receiving the drone navigation request, get the initial position and destination position of the drone; Collect the operating state information of the drone through the first collection device in the drone, and collect the surrounding environment at different heights and different shooting angles at the initial position through the second collection device in the drone information; Constructing a feature point cloud of the shooting object according to the operating state information and the surrounding environment information, and processing the feature point cloud to obtain a point cloud model of the shooting object; The point cloud model and the preset BIM model are superimposed to obtain a superimposed model, a navigation route to the destination location is generated according to the superimposed model, and the drone is controlled to operate according to the navigation route. The indoor navigation method for a UAV according to claim 1, wherein the step of obtaining the initial position and the target position of the UAV when receiving the UAV navigation request comprises: When receiving the drone navigation request, obtain the building identifier of the building where the drone is currently located, and the preset BIM model associated with the building identifier; Construct a three-dimensional coordinate system based on the preset BIM model, use the three-dimensional coordinates of the current position of the drone as the initial position of the drone, obtain the navigation destination corresponding to the drone navigation request, and set the The three-dimensional navigation destination is used as the destination position of the drone. The indoor navigation method for an unmanned aerial vehicle according to claim 1, wherein the first acquisition device includes at least one inertial measurement device and at least one perception camera, and the second acquisition device includes at least one depth camera; The first collecting device in the unmanned aerial vehicle collects the operating state information of the unmanned aerial vehicle, and the second collecting device in the unmanned aerial vehicle collects the information of different heights and different shooting angles at the initial position. The steps of surrounding environment information include: The height and shooting angle of the drone are adjusted at the initial position, the direction information of the drone is collected by the inertial measurement device, the characteristic image is collected by the sensing camera, and the characteristic image is analyzed to obtain the The relative position information of the man-machine, using the direction information and the relative position information as the operating state information of the drone; Transmit infrared pulses to the subject through the depth camera, receive the infrared pulse reflected by the subject and the reflection time of the infrared pulse, process the reflection time to obtain the depth image information of the subject, and use the depth image information as Surrounding environment information. The UAV indoor navigation method according to claim 1, wherein the feature point cloud of the shooting object is constructed according to the operating state information and the surrounding environment information, and the feature point cloud is processed to obtain the image of the shooting object The steps of the point cloud model include: Extracting direction information and relative position information in the operating state information, and iterating the direction information and the relative position information to obtain the attitude change value of the first collecting device in the drone; Extracting the depth image information in the surrounding environment information, and iterating the depth image information according to the attitude change value to obtain a feature point cloud of the drone photographed object; The characteristic point cloud is processed by a preset SLAM algorithm to obtain a point cloud model of the shooting object. The UAV indoor navigation method according to claim 1, wherein said superimposing said point cloud model and a preset BIM model to obtain a superimposed model, and generating a navigation route to said destination position according to said superimposed model, and The steps of controlling the drone to operate according to the navigation route include: Determine the reference position corresponding to the initial position in the preset BIM model, and compare the edge information in the point cloud model with the edge information at the reference position in the preset BIM model to obtain the point cloud The minimum distance between the model and the preset BIM model; Superimposing the point cloud model and the preset BIM model according to the minimum distance to obtain a superimposed model; Trace the path from the initial position according to the superimposed model, obtain a navigation route to the destination position, and control the drone to operate according to the navigation route. The indoor navigation method for drones according to claim 5, wherein the path traceability is performed from the initial position according to the superimposed model to obtain a navigation route to the destination position, and control the unmanned The steps for the machine to operate according to the navigation route include: Perform path tracing along the destination position from the initial position in the superimposition model to determine whether there are obstacles in the tracing path, whether the repetition rate of the tracing path is greater than a preset repetition rate, and/or whether there are at least two tracing paths; If there are obstacles in the tracing path, the path tracing direction is changed; if the repetition rate of the tracing path is greater than the preset repetition rate, the tracing path is abandoned; and/or if at least two tracing paths are obtained, the tracing path with the shortest distance is regarded as none The man-machine navigates the route, and controls the UAV to operate according to the navigation route. The UAV indoor navigation method according to any one of claims 1 to 6, wherein the point cloud model and the preset BIM model are superimposed to obtain a superimposed model, and the destination position is generated according to the superimposed model. After the steps of controlling the UAV to operate according to the navigation route, the steps include: When it is detected that the UAV deviates from the navigation route, sending a route control instruction to the UAV to make the UAV return to the navigation route; If the UAV does not return to the navigation route within the preset time period, sending an information collection instruction to the UAV so that the UAV feeds back current operating parameters; Receive the current operating parameters fed back by the drone, and output prompt information if the current operating parameters are abnormal. An indoor navigation device for an unmanned aerial vehicle, wherein the indoor navigation device for an unmanned aerial vehicle includes: The request receiving module is used to obtain the initial position and destination position of the drone when receiving the drone navigation request; The information collection module is used to collect the operating state information of the UAV through the first collection device in the UAV, and collect the different heights and heights at the initial position through the second collection device in the UAV. Surrounding environment information at different shooting angles; A model construction module, configured to construct a feature point cloud of the shooting object according to the operating state information and the surrounding environment information, and process the feature point cloud to obtain a point cloud model of the shooting object; The route generation module is used to superimpose the point cloud model and the preset BIM model to obtain a superimposed model, generate a navigation route to the destination location according to the superimposed model, and control the drone to operate according to the navigation route . An indoor navigation device for an unmanned aerial vehicle, wherein the indoor navigation device for an unmanned aerial vehicle includes: a memory, a processor, and a computer program stored on the memory and running on the processor, wherein: When the computer program is executed by the processor, the steps of a UAV indoor navigation method are realized, wherein the UAV indoor navigation method includes the following steps: When receiving the drone navigation request, get the initial position and destination position of the drone; Collect the operating state information of the drone through the first collection device in the drone, and collect the surrounding environment at different heights and different shooting angles at the initial position through the second collection device in the drone information; Constructing a feature point cloud of the shooting object according to the operating state information and the surrounding environment information, and processing the feature point cloud to obtain a point cloud model of the shooting object; The point cloud model and the preset BIM model are superimposed to obtain a superimposed model, a navigation route to the destination location is generated according to the superimposed model, and the drone is controlled to operate according to the navigation route. The UAV indoor navigation device according to claim 9, wherein the step of obtaining the initial position and the target position of the UAV when the UAV navigation request is received comprises: When receiving the drone navigation request, obtain the building identifier of the building where the drone is currently located, and the preset BIM model associated with the building identifier; Construct a three-dimensional coordinate system based on the preset BIM model, use the three-dimensional coordinates of the current position of the drone as the initial position of the drone, obtain the navigation destination corresponding to the drone navigation request, and set the The three-dimensional navigation destination is used as the destination position of the drone. The UAV indoor navigation device according to claim 9, wherein the first acquisition device includes at least one inertial measurement device and at least one perception camera, and the second acquisition device includes at least one depth camera; The first collecting device in the unmanned aerial vehicle collects the operating state information of the unmanned aerial vehicle, and the second collecting device in the unmanned aerial vehicle collects the information of different heights and different shooting angles at the initial position. The steps of surrounding environment information include: The height and shooting angle of the drone are adjusted at the initial position, the direction information of the drone is collected by the inertial measurement device, the characteristic image is collected by the sensing camera, and the characteristic image is analyzed to obtain the The relative position information of the man-machine, using the direction information and the relative position information as the operating state information of the drone; Transmit infrared pulses to the subject through the depth camera, receive the infrared pulse reflected by the subject and the reflection time of the infrared pulse, process the reflection time to obtain the depth image information of the subject, and use the depth image information as Surrounding environment information. The UAV indoor navigation device according to claim 9, wherein the feature point cloud of the shooting object is constructed according to the operating state information and the surrounding environment information, and the feature point cloud is processed to obtain the image of the shooting object The steps of the point cloud model include: Extracting direction information and relative position information in the operating state information, and iterating the direction information and the relative position information to obtain the attitude change value of the first collecting device in the drone; Extracting the depth image information in the surrounding environment information, and iterating the depth image information according to the attitude change value to obtain a feature point cloud of the object photographed by the drone; The characteristic point cloud is processed by a preset SLAM algorithm to obtain a point cloud model of the shooting object. The UAV indoor navigation device according to claim 9, wherein the superimposed model is obtained by superimposing the point cloud model and the preset BIM model, and generating a navigation route to the destination location according to the superimposed model, and The steps of controlling the drone to operate according to the navigation route include: Determine the reference position corresponding to the initial position in the preset BIM model, and compare the edge information in the point cloud model with the edge information at the reference position in the preset BIM model to obtain the point cloud The minimum distance between the model and the preset BIM model; Superimposing the point cloud model and the preset BIM model according to the minimum distance to obtain a superimposed model; Trace the path from the initial position according to the superimposed model, obtain a navigation route to the destination position, and control the drone to operate according to the navigation route. The UAV indoor navigation device according to claim 13, wherein the path is traced from the initial position according to the superimposed model to obtain a navigation route to the destination position, and control the unmanned The steps for the machine to operate according to the navigation route include: Perform path tracing along the destination position from the initial position in the superimposition model to determine whether there are obstacles in the tracing path, whether the repetition rate of the tracing path is greater than a preset repetition rate, and/or whether there are at least two tracing paths; If there are obstacles in the tracing path, the path tracing direction is changed; if the repetition rate of the tracing path is greater than the preset repetition rate, the tracing path is abandoned; and/or if at least two tracing paths are obtained, the tracing path with the shortest distance is regarded as none The man-machine navigates the route, and controls the UAV to operate according to the navigation route. A computer storage medium, wherein a computer program is stored on the computer storage medium, and when the computer program is executed by a processor, the steps of an indoor navigation method for an unmanned aerial vehicle are realized, wherein the indoor navigation method for an unmanned aerial vehicle It includes the following steps: When receiving the drone navigation request, get the initial position and destination position of the drone; Collect the operating state information of the drone through the first collection device in the drone, and collect the surrounding environment at different heights and different shooting angles at the initial position through the second collection device in the drone information; Constructing a feature point cloud of the shooting object according to the operating state information and the surrounding environment information, and processing the feature point cloud to obtain a point cloud model of the shooting object; The point cloud model and the preset BIM model are superimposed to obtain a superimposed model, a navigation route to the destination location is generated according to the superimposed model, and the drone is controlled to operate according to the navigation route. 15. The computer storage medium of claim 15, wherein the step of obtaining the initial position and the target position of the drone upon receiving the drone navigation request comprises: When receiving the drone navigation request, obtain the building identifier of the building where the drone is currently located, and the preset BIM model associated with the building identifier; Construct a three-dimensional coordinate system based on the preset BIM model, use the three-dimensional coordinates of the current position of the drone as the initial position of the drone, obtain the navigation destination corresponding to the drone navigation request, and set the The three-dimensional navigation destination is used as the destination position of the drone. 15. The computer storage medium of claim 15, wherein the first acquisition device includes at least one inertial measurement device and at least one sensory camera, and the second acquisition device includes at least one depth camera; The first collecting device in the unmanned aerial vehicle collects the operating state information of the unmanned aerial vehicle, and the second collecting device in the unmanned aerial vehicle collects the information of different heights and different shooting angles at the initial position. The steps of surrounding environment information include: The height and shooting angle of the drone are adjusted at the initial position, the direction information of the drone is collected by the inertial measurement device, the characteristic image is collected by the sensing camera, and the characteristic image is analyzed to obtain the The relative position information of the man-machine, using the direction information and the relative position information as the operating state information of the drone; Transmit infrared pulses to the subject through the depth camera, receive the infrared pulse reflected by the subject and the reflection time of the infrared pulse, process the reflection time to obtain the depth image information of the subject, and use the depth image information as Surrounding environment information. 15. The computer storage medium according to claim 15, wherein the feature point cloud of the shooting object is constructed according to the operating state information and the surrounding environment information, and the feature point cloud is processed to obtain the point cloud model of the shooting object The steps include: Extracting direction information and relative position information in the operating state information, and iterating the direction information and the relative position information to obtain the attitude change value of the first collecting device in the drone; Extracting the depth image information in the surrounding environment information, and iterating the depth image information according to the attitude change value to obtain a feature point cloud of the drone photographed object; The characteristic point cloud is processed by a preset SLAM algorithm to obtain a point cloud model of the shooting object. The computer storage medium according to claim 15, wherein the superimposed model is obtained by superimposing the point cloud model and the preset BIM model, and generating a navigation route to the destination position according to the superimposed model, and controlling the The steps for the drone to operate according to the navigation route include: Determine the reference position corresponding to the initial position in the preset BIM model, and compare the edge information in the point cloud model with the edge information at the reference position in the preset BIM model to obtain the point cloud The minimum distance between the model and the preset BIM model; Superimposing the point cloud model and the preset BIM model according to the minimum distance to obtain a superimposed model; Trace the path from the initial position according to the superimposed model, obtain a navigation route to the destination position, and control the drone to operate according to the navigation route. The computer storage medium according to claim 19, wherein the path is traced from the initial position according to the superimposed model to obtain a navigation route to the destination position, and the drone is controlled to follow the path Describe the steps of navigation route operation, including: Perform path tracing along the destination position from the initial position in the superimposition model to determine whether there are obstacles in the tracing path, whether the repetition rate of the tracing path is greater than a preset repetition rate, and/or whether there are at least two tracing paths; If there are obstacles in the tracing path, the path tracing direction is changed; if the repetition rate of the tracing path is greater than the preset repetition rate, the tracing path is abandoned; and/or if at least two tracing paths are obtained, the tracing path with the shortest distance is regarded as none The man-machine navigates the route, and controls the UAV to operate according to the navigation route.

Images