A reflector map generation method and system for indoor robots

By combining indoor map data and lidar data, optimizing the position of the reflector, and using nonlinear fitting and clustering methods to generate a reflector point cloud map, the problem of insufficient positioning accuracy and robustness of indoor robots is solved, and more efficient reflector map construction and robot navigation.

CN113984065BActive Publication Date: 2024-11-19SHANDONG ALESMART INTELLIGENT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111256915.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-10-27
Publication Date
2024-11-19
Estimated Expiration
2041-10-27

AI Technical Summary

Technical Problem

The prior art has shortcomings in the positioning accuracy and algorithm robustness of indoor mobile robots, especially in complex scenarios, it is difficult to ensure that the robot completes tasks accurately and efficiently. The reflector map construction accuracy is low and does not match the traditional laser SLAM map.

Method used

A reflector map generation method is adopted to extract reflector pose data by obtaining indoor map data and lidar data, combining light intensity change rate and robot position pose, and optimize reflector point cloud using nonlinear fitting and clustering methods. Map, match with raster maps to improve positioning accuracy.

Benefits of technology

The on-site construction steps for reflector drawing construction have been greatly reduced, the accuracy of reflector drawing construction has been improved, and more efficient indoor robot positioning and navigation have been achieved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113984065B_ABST
    Figure CN113984065B_ABST
Patent Text Reader

Abstract

The present invention provides a reflector map generation method and system for an indoor robot, which obtain map data of an indoor space; obtain the current posture of the indoor robot according to the obtained map data and laser radar data of the indoor robot; obtain reflector posture data according to the light intensity change rate in the laser radar data and the current posture of the indoor robot and store them in a corresponding reflector sub-table; extract reflector posture data when the indoor robot is located at different positions in turn to obtain all reflector sub-tables, combine the reflector posture data in all reflector sub-tables to obtain a complete reflector point cloud map; the present invention greatly reduces the on-site construction steps of reflector mapping and improves the accuracy of reflector mapping.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of high-precision positioning of indoor mobile robots, and in particular to a reflector map generation method and system for indoor robots. Background Art

[0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art.

[0003] Map building technology is the basis for realizing robot autonomous navigation. As the application environment becomes increasingly complex, mobile robots still have many shortcomings in positioning accuracy, algorithm robustness and adaptability to complex scenarios, making it difficult to ensure that robots can complete tasks accurately and efficiently.

[0004] The inventors found that the reflector map has high positioning accuracy, strong anti-interference ability, and broad application prospects. However, in most actual working conditions, a large number of reflectors need to be laid, and the position of each reflector needs to be accurately measured, which has low accuracy, low intelligence level, and mismatch with traditional laser SLAM maps. Summary of the invention

[0005] In order to address the deficiencies of the prior art, the present invention provides a reflector map generation method and system for an indoor robot, which greatly reduces the on-site construction steps for reflector mapping and improves the reflector mapping accuracy.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A first aspect of the present invention provides a reflector map generation method for an indoor robot.

[0008] A reflector map generation method for an indoor robot includes the following steps:

[0009] Get map data of indoor space;

[0010] According to the acquired map data and the laser radar data of the indoor robot, the current position of the indoor robot is obtained;

[0011] According to the light intensity change rate in the laser radar data and the current posture of the indoor robot, the reflector posture data is obtained and stored in the corresponding reflector sub-table;

[0012] The reflector pose data when the indoor robot is located at different positions are extracted in turn to obtain all reflector sub-tables, and the reflector pose data in all reflector sub-tables are combined to obtain a complete reflector point cloud map.

[0013] Furthermore, when the number of times a reflector with the same posture appears is greater than a set threshold, the posture data is stored in the corresponding reflector sub-table. After the reflector sub-table is completed, the reflector posture points in the reflector sub-table are combined into a frame of data, which is then matched with the map data to obtain the corrected posture data, and the corrected sub-table is obtained based on the corrected posture data.

[0014] Furthermore, when the reflector appears multiple times in the same posture and the number of appearances is greater than a set threshold, the posture is recorded as reflector data and stored and counted. When the stored reflector posture data reaches a set value, the group of data is stored as a reflector sub-table.

[0015] Furthermore, when a reflector sub-table is formed, all the reflector posture data in the group of data are taken and combined into a frame of the to-be-matched data set, and the to-be-matched data set is matched with the map data to obtain the optimized posture data, and based on the optimized posture data, the posture of the group of reflector lists is updated to obtain the optimized reflector sub-table.

[0016] Furthermore, all optimized reflector sub-tables are optimized as a whole based on a nonlinear fitting method, and all reflector data are updated according to the optimized sub-table poses.

[0017] Furthermore, the current posture of the indoor robot and the light intensity feature extraction results of the point cloud data are combined to determine the posture of the reflector corresponding to the point cloud;

[0018] A clustering method based on light intensity density is used to determine the point cloud cluster corresponding to the reflector;

[0019] According to the point cloud cluster to which the reflector belongs, the pose mean of the point cloud cluster is used as the pose of the reflector and stored in the corresponding reflector subtable.

[0020] Further, according to the size of the indoor range, the position point data in the reflective board sub-table are combined to form multiple map data;

[0021] According to the spatial position relationship, multiple map data are processed by nonlinear fitting to splice multiple maps into one map;

[0022] The point cloud data of the entire map data is nonlinearly fitted with the overall indoor grid map to obtain a reflector point cloud map matching the grid.

[0023] A second aspect of the present invention provides a reflector map generation system for an indoor robot.

[0024] A reflector map generation system for an indoor robot, comprising:

[0025] The data acquisition module is configured to: acquire map data of the indoor space;

[0026] The robot posture calculation module is configured to: obtain the current posture of the indoor robot according to the acquired map data and the laser radar data of the indoor robot;

[0027] The reflector posture calculation module is configured to: obtain the reflector posture data according to the light intensity change rate in the laser radar data and the current posture of the indoor robot, and store it in the corresponding reflector sub-table;

[0028] The reflector map generation module is configured to: extract the reflector posture data when the indoor robot is located at different positions in turn, obtain all reflector sub-tables, combine the reflector posture data in all reflector sub-tables, and obtain a complete reflector point cloud map.

[0029] The third aspect of the present invention provides a computer-readable storage medium having a program stored thereon, characterized in that when the program is executed by a processor, the steps of the reflector map generation method for an indoor robot as described in the first aspect of the present invention are implemented.

[0030] The fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the reflector map generation method for an indoor robot as described in the first aspect of the present invention are implemented.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The method, system, medium or electronic device described in the present invention calculates the pose data of the laser point cloud, extracts the characteristic pose point cloud of the reflector based on the pose data of the laser point cloud, calculates the exact pose of each reflector sub-image based on the point cloud data and the corresponding pose of the reflector by a nonlinear fitting method, splices different reflector sub-images into a complete map, matches them with the grid map corresponding to the environment, and optimizes and updates to obtain the final reflector map, which can greatly reduce the on-site construction steps of reflector mapping and improve the accuracy of reflector mapping.

[0033] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0035] Figure 1 A schematic flow chart of a reflector map generation method for an indoor robot provided in Example 1 of the present invention.

[0036] Figure 2 Schematic diagram for optimizing the creation of a reflector sub-image provided in Example 1 of the present invention DETAILED DESCRIPTION

[0037] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0038] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0039] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0040] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0041] Embodiment 1:

[0042] like Figure 1 As shown, Embodiment 1 of the present invention provides a method for generating a reflector map for an indoor robot, which utilizes the reflectivity characteristics of a laser radar sensor, realizes the recognition of reflector data through feature extraction and cluster analysis, and thus realizes the automatic creation of a reflector map. Specifically, the method includes the following processes:

[0043] S1: Using simultaneous localization and mapping to build a map of the work environment

[0044] S1.1: Use LiDAR to scan the working environment and obtain odometer and gyroscope data at the same time;

[0045] S1.2: Create maps of the operating environment using simultaneous localization and mapping methods.

[0046] Specifically, the gyroscope provides the angle, angular velocity and linear acceleration of the indoor robot. The encoder uses an incremental rotary encoder to provide the wheel change increment. Based on the incremental data, the position increment is obtained through the differential model. The laser radar is used as a laser sensor to scan the working environment. The contour features of the working environment and the reflector features corresponding to the light intensity are obtained through the laser radar. Based on the data of the above three sensors, the environmental information of the indoor robot is expressed to obtain a map of the working environment.

[0047] S2: Using LiDAR data to match maps

[0048] The laser radar data is matched with the map established by S1 to obtain the matching posture of the indoor robot. The matching posture is the coordinate value of the robot relative to the map.

[0049] In this embodiment, the position and posture of the indoor robot is determined by natural laser positioning, and the position and posture of the reflector on the map is obtained by superimposing the relative position and posture of the laser radar to the reflector relative to the position and posture of the indoor robot.

[0050] S3: The laser point cloud feature extraction and cluster analysis method are used to obtain the reflector’s position data:

[0051] S3.1: Based on the matching posture obtained in S2, extract the light intensity features of the laser radar point cloud data to determine the posture of the reflector corresponding to the point cloud;

[0052] S3.2: Using a clustering method based on light intensity density, determine the point cloud cluster corresponding to the reflector;

[0053] S3.3: Analyze the point cloud cluster to which the reflector belongs, obtain the mean value of the point cloud cluster pose as the pose of the reflector, and store it in the corresponding reflector list.

[0054] Specifically, by calculating the slope of each point in the point cloud according to the light intensity and judging by the threshold, the points with the largest light intensity change in the point cloud are obtained as the reference points of the reflector posture; in a density-based manner, the point cloud clusters near the feature points are obtained as the overall reflector point cloud.

[0055] S4: Reflector map creation

[0056] S4.1: According to the range size, the position point data in the list of some reflectors are combined to form multiple map data. Specifically, the range refers to the movement range of the robot. After the robot moves a certain distance, the reflector positions within the movement range are combined into a map.

[0057] S4.2: Using nonlinear fitting processing on the multiple map data to be optimized according to the spatial position relationship, the multiple maps are spliced ​​into one map;

[0058] S4.3: Perform nonlinear pose fitting processing on the point cloud data of the entire map data and the overall grid map to obtain a new reflector point cloud map that matches the grid.

[0059] Nonlinear fitting processing refers to building a residual model, constructing an error equation between the point cloud pose to be optimized and the target point cloud, and inputting data such as timestamps, encoder pulses, indoor robot chassis parameters, and IMU angular velocity into the residual model to obtain the variables to be optimized. The initial value is given by the current pose of the indoor robot, and the calculation is performed. The current pose is re-corrected with the calculation result, and it is iterated until the calculation result is small enough.

[0060] The map stitching described in this embodiment refers to stitching multiple maps into the same map by using the pose information of multiple maps as the matching initial pose and utilizing a nonlinear fitting method to derive the spatial pose relationship between the maps.

[0061] Embodiment 2:

[0062] Embodiment 2 of the present invention provides a reflector map generation system for an indoor robot, comprising:

[0063] The data acquisition module is configured to: acquire map data of the indoor space;

[0064] The robot posture calculation module is configured to: obtain the current posture of the indoor robot according to the acquired map data and the laser radar data of the indoor robot;

[0065] The reflector posture calculation module is configured to: obtain the reflector posture data according to the light intensity change rate in the laser radar data and the current posture of the indoor robot, and store it in the corresponding reflector sub-table;

[0066] The reflector map generation module is configured to: extract the reflector posture data when the indoor robot is located at different positions in turn, obtain all reflector sub-tables, combine the reflector posture data in all reflector sub-tables, and obtain a complete reflector point cloud map.

[0067] The working method of the system is the same as the reflector map generation method for an indoor robot provided in Example 1, and will not be repeated here.

[0068] Embodiment 3:

[0069] Embodiment 3 of the present invention provides a computer-readable storage medium having a program stored thereon, characterized in that when the program is executed by a processor, the steps of the reflector map generation method for an indoor robot as described in Embodiment 1 of the present invention are implemented.

[0070] Embodiment 4:

[0071] Embodiment 4 of the present invention provides an electronic device, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the reflector map generation method for an indoor robot as described in Embodiment 1 of the present invention are implemented.

[0072] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0073] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0074] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0075] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0076] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0077] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A reflector map generation method for an indoor robot, characterized in that: The process includes: Obtain map data of indoor space; use LiDAR to scan the indoor space working environment and obtain odometer and gyroscope data at the same time; use simultaneous positioning and mapping methods to create a map of the working environment; According to the acquired map data and the laser radar data of the indoor robot, the current position of the indoor robot is obtained; According to the light intensity change rate in the laser radar data and the current posture of the indoor robot, the reflector posture data is obtained and stored in the corresponding reflector sub-table; Specifically: Combine the current posture of the indoor robot and the light intensity feature extraction results of the point cloud data to determine the posture of the point cloud corresponding to the reflector; use the clustering method based on light intensity density to determine the point cloud cluster corresponding to the reflector; according to the point cloud cluster to which the reflector belongs, use the posture mean of the point cloud cluster as the posture of the reflector and store it in the corresponding reflector subtable; Extract the reflector pose data when the indoor robot is located at different positions in turn to obtain all reflector sub-tables, combine the reflector pose data in all reflector sub-tables, and obtain a complete reflector point cloud map; specifically: According to the robot's moving range, the posture data in the reflector sub-table are combined to form multiple map data; the multiple map data are processed by nonlinear fitting according to the spatial posture relationship, and the multiple maps are spliced ​​into one map; the point cloud data of the entire map data is nonlinearly fitted with the overall indoor grid map to obtain the reflector point cloud map matching the grid.

2. The reflector map generation method for an indoor robot according to claim 1, characterized in that: When the number of times a reflector with the same posture appears is greater than a set threshold, the posture data is stored in the corresponding reflector sub-table. After the reflector sub-table is completed, the reflector posture points in the reflector sub-table are combined into a frame of data, which is then matched with the map data to obtain the corrected posture data, and the corrected sub-table is obtained based on the corrected posture data.

3. The reflector map generation method for an indoor robot according to claim 2, characterized in that: When the reflector appears multiple times in the same posture and the number of appearances is greater than the set threshold, the posture is recorded as reflector data and the count is accumulated. When the stored reflector posture data reaches the set value, the group of data is stored as a reflector sub-table.

4. The reflector map generation method for an indoor robot according to claim 3, characterized in that: When a reflector sub-table is formed, all the reflector posture data in the group of data are taken and combined into a frame of the to-be-matched data set. The to-be-matched data set is matched with the map data to obtain the optimized posture data. Based on the optimized posture data, the posture of the reflector list of this group is updated to obtain the optimized reflector sub-table.

5. The reflector map generation method for an indoor robot according to claim 4, characterized in that: All optimized reflector sub-tables are optimized as a whole based on nonlinear fitting, and all reflector data are updated according to the optimized sub-table poses.

6. A reflector map generation system for an indoor robot, using the reflector map generation method for an indoor robot as claimed in claim 1, characterized in that: include: The data acquisition module is configured to: acquire map data of the indoor space; The robot posture calculation module is configured to: obtain the current posture of the indoor robot according to the acquired map data and the laser radar data of the indoor robot; The reflector posture calculation module is configured to: obtain the reflector posture data according to the light intensity change rate in the laser radar data and the current posture of the indoor robot, and store it in the corresponding reflector sub-table; The reflector map generation module is configured to: extract the reflector posture data when the indoor robot is located at different positions in turn, obtain all reflector sub-tables, combine the reflector posture data in all reflector sub-tables, and obtain a complete reflector point cloud map.

7. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps in the reflector map generation method for an indoor robot as described in any one of claims 1 to 5 are implemented.

8. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the reflector map generation method for an indoor robot as described in any one of claims 1 to 5 are implemented.