CN116449379A - AGV positioning method and device based on special shape recognition - Google Patents

Abstract

The invention discloses an improved AGV positioning method based on special shape recognition, comprising: according to the actual working environment of an intelligent handling robot AGV, acquiring laser data of the actual environment, and setting a target object in the actual working environment as a special object shape to be identified; Preprocess the shape of special objects and extract the feature information of the shape, re-encode and sort based on the feature information to form the unique variable of the shape of the special object; preprocess the laser data and extract the feature information of the laser data, based on the unique variable, match through the feature matching model For the calculation of the accuracy rate, the highest accuracy rate calculated is selected as the final positioning result. By calculating the matching accuracy rate, the present invention enables the intelligent handling robot AGV to realize precise positioning by identifying special-shaped objects in complex and frequently changing scenes, without adding any hardware and on-site deployment work, and the cost is low and the positioning accuracy is improved.

Description

An improved AGV positioning method and device based on special shape recognition

technical field

The invention relates to the technical field of intelligent mobile robots, in particular to an improved AGV positioning method and device based on special shape recognition.

Background technique

Lidar technology is widely used in intelligent handling robot (Automated Guided Vehicle) AGV, unmanned driving and other fields. AGV based on Lidar technology relies on its high stability, high positioning accuracy, and small dependence on the scene. , Widely used in cargo transportation, express transportation and other fields. LiDAR is mainly used for the self-positioning of AGV. The current mainstream positioning method is the triangulation positioning algorithm based on the reflector. However, this algorithm has natural limitations and requires a strict layout of the reflector, which cannot guarantee the precise positioning of the AGV in complex and frequently changing scenes, resulting in inaccurate positioning of the AGV.

Contents of the invention

The purpose of this section is to outline some aspects of embodiments of the invention and briefly describe some preferred embodiments. Some simplifications or omissions may be made in this section, as well as in the abstract and titles of this application, to avoid obscuring the purpose of this section, abstract and titles, and such simplifications or omissions should not be used to limit the scope of the invention.

In view of the above existing problems, the present invention is proposed.

Therefore, the present invention provides an improved AGV positioning method and device based on special shape recognition to solve the problem that the existing laser positioning technology cannot guarantee the precise positioning of the AGV in complex and frequently changing scenarios.

In order to solve the above technical problems, the present invention provides the following technical solutions:

In the first aspect, the embodiment of the present invention provides an improved AGV positioning method based on special shape recognition, including:

According to the actual working environment of the intelligent handling robot AGV, the laser data of the actual environment is obtained, and the target object in the actual working environment is set as a special object shape to be recognized;

Preprocessing the shape of the special object and extracting the feature information of the shape, and re-encoding and sorting based on the feature information to form the unique variable of the shape of the special object;

Preprocessing the laser data and extracting the feature information of the laser data, calculating the matching accuracy rate through the feature matching model based on the unique variable, and selecting the highest calculated accuracy rate as the final positioning result.

As a preferred solution of the improved AGV positioning method based on special shape recognition in the present invention, wherein: preprocessing the special object shape includes:

False detection of input special object shapes;

Based on the actual shape of the target object, the composition of the special object shape is divided into a straight line L type and an arc C type, and feature information of the types is extracted respectively.

As a preferred solution of the improved AGV positioning method based on special shape recognition described in the present invention, wherein: extracting the feature information of the shape includes:

The feature information F _L of the straight line L class is expressed as:

A*x+B*y+C＝0

Among them, A is the first coefficient, B is the second coefficient, A and B are not 0 at the same time, x is the first variable, and y is the second variable;

The feature information F _C of the class C of the arc is expressed as:

(xa) ² +(yb) ² ＝r ²

Among them, (a, b) is the center of the circle, r is the radius of the circle, x is the first variable, and y is the second variable.

As a preferred solution of the improved AGV positioning method based on special shape recognition in the present invention, wherein: the feature information is re-encoded and sorted to form the only variable of the shape of a special object, including:

Sorting according to the shape characteristics of the actual object to obtain the unique variable, expressed as:

T＝{F _L1 ,F _C2 ,F _L2 ,F _C1 }

Wherein, F _L1 is the first straight line feature information, F _L2 is the second straight line feature information, F _C1 is the first circular arc feature information, and F _C2 is the second circular arc feature information.

As a preferred solution of the improved AGV positioning method based on special shape recognition described in the present invention, wherein: the noise in the laser data is removed;

The removal of the noise data is based on the original data of the laser radar, and the denoising is completed by using a denoising processing function.

As a preferred solution of the improved AGV positioning method based on special shape recognition described in the present invention, wherein: extracting the straight line and arc features in the laser data includes:

Based on the processed laser data, use the findLine function to extract the data describing the straight line in the laser point cloud;

Use the findCurve function to extract the data describing the arc in the laser point cloud.

As a preferred solution of the improved AGV positioning method based on special shape recognition described in the present invention, wherein: the accuracy rate is calculated by the feature matching model, including:

Calculate the matching accuracy rate based on the actual matching model Model through the unique variable and the straight line feature information and the arc feature information;

Sorting the accuracy rate based on the matching order of the laser data and the unique variable, and according to the permutation and combination results;

When the combined accuracy rate is the highest, the combination is selected as the final matching result, and the positioning accuracy of the final matching is calculated to obtain the final high-precision positioning result.

In the second aspect, the embodiment of the present invention provides an improved AGV positioning device based on special shape recognition, including:

The data acquisition setting module is used to obtain the laser data of the actual environment according to the actual working environment of the intelligent handling robot AGV, and set the target environment in the actual working environment as a special object shape to be recognized;

The shape analysis module is used for preprocessing the shape of the special object and extracting the feature information of the shape, and re-encoding and sorting based on the feature information to form the unique variable of the shape of the special object;

The shape recognition module is used to preprocess the laser data and extract the feature information of the laser data. Based on the unique variable, the feature matching model is used to calculate the matching accuracy rate, and the highest calculated accuracy rate is selected as the final positioning result. .

In a third aspect, an embodiment of the present invention provides a computing device, including:

memory and processor;

The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the one or more programs are executed by the one or more processors, the one or more The processor implements the improved AGV positioning method based on special shape recognition as described in any embodiment of the present invention.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the improved AGV positioning method based on special shape recognition is implemented.

Compared with the prior art, the beneficial effect of the present invention is that by calculating the matching accuracy rate, the present invention enables the intelligent handling robot AGV to realize precise positioning by identifying objects with special shapes in complex and frequently changing scenes without adding any hardware As well as on-site deployment work, the cost is low and the positioning accuracy is improved.

Description of drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For Those of ordinary skill in the art can also obtain other drawings based on these drawings without any creative effort. in:

Fig. 1 is an overall flowchart of an improved AGV positioning method and device based on special shape recognition according to an embodiment of the present invention;

Fig. 2 is a flow chart of the shape analysis module of an improved AGV positioning method and device based on special shape recognition described in an embodiment of the present invention;

Fig. 3 is a flow chart of a shape recognition module based on a special shape recognition improved AGV positioning method and device according to an embodiment of the present invention;

Fig. 4 is a special shape example diagram of an improved AGV positioning method and device based on special shape recognition according to an embodiment of the present invention;

Fig. 5 is a data diagram of the matching accuracy rate of an improved AGV positioning method and device based on special shape recognition according to an embodiment of the present invention;

Fig. 6 is a comparison diagram of positioning accuracy of an improved AGV positioning method and device based on special shape recognition according to an embodiment of the present invention.

Detailed ways

In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation modes of the present invention will be described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Example. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative efforts shall fall within the protection scope of the present invention.

In the following description, a lot of specific details are set forth in order to fully understand the present invention, but the present invention can also be implemented in other ways different from those described here, and those skilled in the art can do it without departing from the meaning of the present invention. By analogy, the present invention is therefore not limited to the specific examples disclosed below.

Second, "one embodiment" or "an embodiment" referred to herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. "In one embodiment" appearing in different places in this specification does not all refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

The present invention is described in detail in conjunction with schematic diagrams. When describing the embodiments of the present invention in detail, for the convenience of explanation, the cross-sectional view showing the device structure will not be partially enlarged according to the general scale, and the schematic diagram is only an example, which should not limit the present invention. scope of protection. In addition, the three-dimensional space dimensions of length, width and depth should be included in actual production.

At the same time, in the description of the present invention, it should be noted that the orientation or positional relationship indicated by "upper, lower, inner and outer" in the terms is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention. The invention and the simplified description do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and thus should not be construed as limiting the present invention. In addition, the terms "first, second or third" are used for descriptive purposes only, and should not be construed as indicating or implying relative importance.

Unless otherwise specified and limited in the present invention, the term "installation, connection, connection" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integrated connection; it can also be a mechanical connection, an electrical connection or a direct connection. A connection can also be an indirect connection through an intermediary, or it can be an internal communication between two elements. Those of ordinary skill in the art can understand the specific meanings of the above terms in the present invention in specific situations.

Example 1

Referring to Figures 1 to 4, it is an embodiment of the present invention, which provides an improved AGV positioning method based on special shape recognition, including:

S1: According to the actual working environment of the intelligent handling robot AGV, obtain the laser data of the actual environment, and set the target object in the actual working environment as a special object shape to be recognized;

S2: Preprocess the shape of the special object and extract the feature information of the shape, re-encode and sort based on the feature information, and form the only variable of the shape of the special object;

Further, preprocessing special object shapes, including:

False detection of input special object shapes;

Based on the actual shape of the target object, the composition of the special object shape is divided into straight line L and arc C, and the feature information of each category is extracted.

It should be noted that false detection refers to the detection of overlap and smoothness of the shape of the special object to be recognized and other detections that do not meet the recognition standards.

Further, the feature information of the shape is extracted, including:

The feature information F _L of the straight line L class is expressed as:

A*x+B*y+C＝0

Among them, A is the first coefficient, B is the second coefficient, A and B are not 0 at the same time, x is the first variable, and y is the second variable;

The feature information F _C of the arc C class is expressed as:

(xa) ² +(yb) ² ＝r ²

Among them, (a, b) is the center of the circle, r is the radius of the circle, x is the first variable, and y is the second variable.

Specifically, the feature information is re-encoded and sorted to form the unique variable of the shape of a special object, including:

Sorting according to the shape characteristics of the actual object to obtain the unique variable, expressed as:

T＝{F _L1 ,F _C2 ,F _L2 ,F _C1 }

Wherein, F _L1 is the first straight line feature information, F _L2 is the second straight line feature information, F _C1 is the first circular arc feature information, and F _C2 is the second circular arc feature information.

S3: Preprocessing the laser data and extracting the feature information of the laser data, based on the unique variable, performing the calculation of the matching accuracy rate through the feature matching model, and selecting the calculated highest accuracy rate as the final positioning result;

Furthermore, preprocessing the laser data includes: removing noise in the laser data;

The removal of noise data is based on the original data of lidar, and the denoising is completed by using the denoising processing function.

Furthermore, the features of straight lines and arcs in the laser data are extracted, including:

Based on the processed laser data, use the findLine function to extract the data describing the straight line in the laser point cloud;

Use the findCurve function to extract the data describing the arc in the laser point cloud.

Furthermore, the accuracy rate is calculated through the feature matching model, including:

Calculate the matching accuracy rate based on the actual matching model Model through the unique variable and the feature information of the straight line and the arc feature information;

Based on the matching order of laser data and unique variables, the accuracy rate is sorted according to the permutation and combination results;

When the combination accuracy is the highest, the combination is selected as the final matching result, and the positioning accuracy of the final matching is calculated to obtain the final high-precision positioning result.

The above is a schematic solution of an improved AGV positioning method based on special shape recognition in this embodiment. It should be noted that the technical solution for improving the AGV positioning device based on special shape recognition and the above-mentioned technical solution for improving the AGV positioning method based on special shape recognition belong to the same concept. In this embodiment, the technical solution for improving the AGV positioning device based on special shape recognition For details that are not described in detail, please refer to the above description of the technical solution for improving the AGV positioning method based on special shape recognition.

In this embodiment, the AGV positioning device is improved based on special shape recognition, including:

The data acquisition setting module is used to obtain the laser data of the actual environment according to the actual working environment of the intelligent handling robot AGV, and set the target environment in the actual working environment as the shape of the special object to be recognized;

The shape analysis module is used to preprocess the shape of special objects and extract the feature information of the shape, and re-encode and sort based on the feature information to form the only variable of the shape of special objects;

The shape recognition module is used to preprocess the laser data and extract the feature information of the laser data. Based on the unique variable, the feature matching model is used to calculate the matching accuracy rate, and the highest calculated accuracy rate is selected as the final positioning result.

In an optional embodiment, the shape analysis module extracts the characteristic information of the shape of the selected special object, and uploads the characteristic information to the shape recognition module, and the shape recognition module receives the information and combines the laser point cloud data to calculate the accuracy of multiple matching models. rate, select the one with the highest value as the final high-precision positioning result.

This embodiment also provides a computing device, which is suitable for improving the AGV positioning method based on special shape recognition, including:

Memory and processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the improved AGV positioning method based on special shape recognition as proposed in the above-mentioned embodiment.

The computer equipment may be a terminal, and the computer equipment includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Wherein, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, an operator network, NFC (Near Field Communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a button, a trackball or a touch pad provided on the casing of the computer device , and can also be an external keyboard, touchpad, or mouse.

This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, the implementation of the improved AGV positioning method based on special shape recognition as proposed in the above embodiment is realized.

The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept, the technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same benefits as the above embodiment Effect.

Example 2

Referring to Figures 1-6, it is an embodiment of the present invention, which is scientifically verified through comparative experiments.

From the actual working environment of the AGV, select the shape of an object as a special shape, and the shape analysis module extracts the feature information of the selected special shape, as shown in Figure 4. The selected shape is composed of feature information F _L and F _C , respectively F _L1 , F _L2 , F _C1 , F _C2 , according to the order of shape features, T={F _L1 , F _C2 , F _L2 , F _C1 }.

The shape recognition module first preprocesses the laser data to remove the noise in the laser radar data,

LaserData = remove_outliers(raw_data),

Among them, raw_data is the original data of the lidar, including noise data, remove_outliers is the noise removal processing function, and LaserData is the laser data after processing.

Then, look for straight line and arc features in the laser data:

Data_line = findLine(LaserData),

Among them, Data_line represents the data describing the straight line in the laser point cloud.

Data_curve = findCurve(LaserData),

Among them, Data_curve represents the data describing the arc in the laser point cloud.

Build a matching model and calculate the accuracy:

precision_rate = Model(T, Data_line, Data_curve, loc_accuracy),

Among them, T is the above-mentioned variable that can uniquely describe the actual shape, Data_line is the linear feature data, Data_curve is the arc feature data, loc_accuracy indicates the calculated positioning accuracy, and Model is the actual matching model.

Bring the laser data and the shape variable T into the model to calculate the matching accuracy; as shown in Figure 5, multiple sets of data will be calculated in the actual scene, and the group with better results will be selected as the final result, and the accuracy will be sorted, and the highest will be selected A combination of is used as the final result, and the sorting results are as follows:

precision_rate1=Model(T,Data_line1,Data_curve1,loc_accuracy1),

precision_rate2=Model(T,Data_line2,Data_curve2,loc_accuracy2),

precision_rate3=Model(T,Data_line3,Data_curve3,loc_accuracy3),

...

p_rate_final=sort(precision_rate1,precision_rate2,precision_rate3,...)

Among them, p_rate_final has the highest accuracy rate, and the corresponding positioning accuracy is used as the final high-precision positioning result.

It can be seen from Figure 6 that compared with the traditional method, the AGV of the present invention can improve the positioning accuracy by identifying objects with special shapes in complex and frequently changing scenes, and the positioning accuracy is much higher than the traditional method. The shape analysis module preprocesses, extracts features, and recodes the shape of objects in the environment. The shape recognition module establishes a matching model, and brings the recoding results and laser data into the matching model to calculate the matching accuracy rate; multiple sets of data are brought into the matching model. Multiple accuracy rates will be obtained, sorted, and the higher group is selected as the final result. The present invention does not need to add any hardware and does not require on-site deployment work. It is easy to operate, low in cost, improves positioning accuracy, and has extensive practical significance.

It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention without limitation, although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be carried out Modifications or equivalent replacements without departing from the spirit and scope of the technical solutions of the present invention shall be covered by the claims of the present invention.

Claims (10)

1. An improved AGV positioning method based on special shape recognition, comprising:

acquiring laser data of an actual working environment according to the actual working environment of an AGV, and setting a target object in the actual working environment as a special object shape to be identified;

preprocessing the special object shape, extracting characteristic information of the shape, and carrying out coding sequencing again based on the characteristic information to form a unique variable of the special object shape;

preprocessing the laser data, extracting characteristic information of the laser data, calculating the matching accuracy through a characteristic matching model based on the unique variable, and selecting the highest accuracy obtained by calculation as a final positioning result.

2. The method of improving AGV positioning based on special shape recognition according to claim 1 wherein preprocessing the special object shape comprises:

performing error detection on the input special object shape;

and dividing the composition of the special object shape into a straight line L class and an arc C class based on the actual shape of the target object, and respectively extracting the characteristic information of the class.

3. The method of improving AGV positioning based on special shape recognition as set forth in claim 2, wherein extracting characteristic information of the shape comprises:

the straight line L-shaped characteristic information F _L Expressed as:

A*x+B*y+C＝0

wherein A is a first coefficient, B is a second coefficient, A and B are not 0 at the same time, x is a first variable, and y is a second variable;

the arc C type characteristic information F _C Expressed as:

(x-a) ² +(y-b) ² ＝r ²

wherein, (a, b) is the center of a circle, r is the radius of the circle, x is a first variable, and y is a second variable.

4. The improved AGV positioning method based on special shape recognition as set forth in claim 3, wherein said feature information reorders the code ordering to form a unique variable for the special object shape comprising:

sorting according to the shape characteristics of the actual object to obtain a unique variable, wherein the unique variable is expressed as:

T＝{F _L1 ,F _C2 ,F _L2 ,F _C1 }

wherein F is _L1 For the first straight line characteristic information, F _L2 For the second straight line characteristic information, F _C1 F is the first arc characteristic information _C2 And the second arc characteristic information.

5. The method of improving AGV positioning based on special shape recognition according to claim 4 wherein preprocessing the laser data comprises: removing noise points in the laser data;

the removing of the noise data is based on the original data of the laser radar, and the denoising is completed by using a noise removing processing function.

6. The method of improving AGV positioning based on special shape recognition according to claim 5 wherein extracting straight line and arc features from laser data comprises:

extracting data describing a straight line in a laser point cloud by utilizing a findLine function based on the processed laser data;

and extracting data describing the circular arc in the laser point cloud by utilizing the findCURVE function.

7. The method of improving AGV positioning based on special shape recognition according to claim 6 wherein calculating accuracy by a feature matching model comprises:

calculating matching accuracy based on an actual matching Model through the unique variable and the linear characteristic information and the circular arc characteristic information;

based on the matching sequence mode of the laser data and the unique variable, sequencing the accuracy according to the arrangement and combination result;

when the combination accuracy is highest, the combination is selected as a final matching result, and the final high-precision positioning result is obtained by calculating the final matching positioning precision.

8. An improved AGV positioning device based on special shape recognition, comprising,

the data acquisition setting module is used for acquiring laser data of an actual environment according to the actual working environment of the AGV, and setting a target environment in the actual working environment as a special object shape to be identified;

the shape analysis module is used for preprocessing the shape of the special object, extracting the characteristic information of the shape, and carrying out coding sequencing again based on the characteristic information to form a unique variable of the shape of the special object;

the shape recognition module is used for preprocessing the laser data, extracting the characteristic information of the laser data, calculating the matching accuracy through a characteristic matching model based on the unique variable, and selecting the highest accuracy obtained by calculation as a final positioning result.

9. A computing device, comprising:

a memory and a processor;

the memory is configured to store computer executable instructions that when executed by the processor perform the steps of the improved AGV positioning method based on special shape recognition as defined in any one of claims 1 to 7.

10. A computer readable storage medium storing computer executable instructions which when executed by a processor perform the steps of the improved AGV positioning method based on special shape recognition of any one of claims 1 to 7.