A hybrid positioning system and method for indoor robots

By building a hybrid map of two-dimensional and three-dimensional maps, the robot achieves rapid and accurate positioning under normal and abnormal conditions, solving the problems of relocation difficulties and unreliability in the existing technology, and achieving reliable relocation effect without auxiliary means.

CN108663048BActive Publication Date: 2024-11-08BEIJING MIWEN POWER TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN201710199128.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2017-03-29
Publication Date
2024-11-08
Estimated Expiration
2037-03-29

AI Technical Summary

Technical Problem

In the prior art, robots cannot reposition independently after the system is turned off or powered off, and human intervention is required. The amount of two-dimensional laser positioning information is insufficient and the pure visual positioning reliability is low, resulting in difficulty and unreliability of repositioning.

Method used

Using the hybrid positioning method, by constructing a hybrid map composed of two-dimensional maps and three-dimensional maps, the robot obtains coordinate positions during normal startup, and initializes and positions using the relationship between mixed maps and two-dimensional and three-dimensional maps during abnormal startup, so as to achieve no auxiliary means. Reliable relocation.

Benefits of technology

It realizes rapid and accurate positioning of the robot during normal operation, and is reliable repositioning in abnormal situations without the need for other technical means, improving the accuracy and reliability of positioning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN108663048B_ABST
    Figure CN108663048B_ABST
Patent Text Reader

Abstract

The present application discloses a hybrid positioning method for an indoor robot, characterized in that it includes the following steps: when the robot is started normally, two-dimensional information and three-dimensional information are obtained, the two-dimensional information and three-dimensional information are matched to the hybrid map, and the coordinate position of the robot in the hybrid map is obtained; when the robot is started abnormally, the original coordinate information is obtained based on the hybrid map; the original position is matched to the two-dimensional map, and then the positioning of the two-dimensional map is initialized, and the hybrid map is adjusted according to the initialized two-dimensional map; the coordinate position of the robot is obtained according to the steps of normal startup; wherein the hybrid map is composed of a two-dimensional map and a three-dimensional map. The beneficial technical effect achieved by the present application is that the robot can quickly and accurately achieve positioning when it is started normally, and can reliably complete repositioning when it is started abnormally.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a robot positioning system and a positioning method, and in particular to an indoor robot hybrid positioning system and a positioning method. Background Art

[0002] At present, mobile robots use sensors to perceive the environment and their own status, and then realize autonomous movement towards the target in an environment with obstacles. This is usually called the navigation technology of intelligent autonomous mobile robots. Positioning is to determine the position of the mobile robot in the working environment relative to the global coordinates and its own posture, which is the basic link of mobile robot navigation.

[0003] However, when the robot's system is shut down or the power is off, the robot's position and state change. After the robot is started, it cannot locate its map position and state. At this time, it is usually necessary to manually move the robot to the initial position and restart the system to obtain the initial position and state before autonomous navigation can be performed. Therefore, in order to achieve automatic positioning of the robot in abnormal situations without human intervention, the robot needs to be relocated.

[0004] Currently, the indoor robot repositioning methods provided in the related art include two-dimensional laser positioning and pure visual positioning technology.

[0005] However, two-dimensional laser positioning has the problem of less information and difficulty in repositioning. It needs to be assisted by other means for repositioning. Although pure visual positioning technology can solve the repositioning problem well, it is easily affected by factors such as light and image quality and has low reliability.

[0006] Therefore, how to enable the robot to complete reliable repositioning without the assistance of other means has become a technical problem that needs to be solved urgently. Summary of the invention

[0007] The main problem solved by the present application is to provide a hybrid positioning method for indoor robots to solve the technical problems of difficult robot repositioning and unreliable positioning.

[0008] In order to solve the above technical problems, the present invention provides an indoor robot hybrid positioning method, comprising the following steps:

[0009] When the robot starts normally, the two-dimensional information and the three-dimensional information are obtained, the two-dimensional information and the three-dimensional information are matched to the hybrid map, and the coordinate position of the robot in the hybrid map is obtained;

[0010] When the robot is abnormally started, the original coordinate information is obtained based on the hybrid map, the original position is matched to the two-dimensional map, and then the positioning of the two-dimensional map is initialized, and the hybrid map is adjusted according to the initialized two-dimensional map; the coordinate position of the robot is obtained according to the steps of normal startup;

[0011] Wherein, the hybrid map is composed of a two-dimensional map and a three-dimensional map;

[0012] The hybrid map is composed of a two-dimensional map and a three-dimensional map.

[0013] Preferably, when obtaining the coordinate position of the robot in the mixed map, the weights of the matched two-dimensional information and three-dimensional information are different.

[0014] Preferably, the two-dimensional map is constructed by two-dimensional information collected by a two-dimensional information collection device.

[0015] Preferably, the three-dimensional map is constructed by three-dimensional information collected by a three-dimensional information collection device.

[0016] The present application also provides an indoor robot hybrid positioning system, including: an information acquisition module, a coordinate position module, a positioning module, and a repositioning module.

[0017] The information acquisition module is connected to the coordinate position module, the positioning module, and the repositioning module, and is used for the acquisition module to acquire two-dimensional information and three-dimensional information;

[0018] The coordinate location module includes a hybrid map, connected to the positioning module and the repositioning module, and the hybrid map is composed of a two-dimensional map and a three-dimensional map;

[0019] The positioning module is used to match the two-dimensional information and the three-dimensional information to the coordinate position module to determine the coordinate position of the robot;

[0020] The repositioning module is used to obtain original coordinate information based on the hybrid map, preferably obtain the original coordinate information of the hybrid map based on the three-dimensional information, match the original position to the two-dimensional map, and then initialize the positioning of the two-dimensional map, adjust the hybrid map according to the initialized two-dimensional map; obtain the coordinate position of the robot according to the normal startup steps;

[0021] The hybrid map is composed of a two-dimensional map and a three-dimensional map.

[0022] Preferably, it also includes: a self-check module, which is used for the self-check step before positioning. If the positioning self-check is normal, the robot position is positioned according to the normal start. If the positioning self-check is abnormal, the robot position is positioned according to the abnormal start.

[0023] Preferably, the information acquisition module includes a two-dimensional information acquisition unit and a three-dimensional information acquisition unit.

[0024] The two-dimensional information acquisition unit is used to acquire two-dimensional information;

[0025] The three-dimensional information acquisition unit is used to acquire three-dimensional information.

[0026] Preferably, it comprises: a laser, and the two-dimensional information comprises: laser point cloud information;

[0027] The three-dimensional information acquisition unit includes a binocular camera, and the three-dimensional information includes visual image information.

[0028] Preferably, the laser is a linear laser, the two imaging components of the binocular camera are located on the same horizontal line, and the linear laser is located below the binocular camera and parallel to the binocular camera.

[0029] Compared with the prior art, the hybrid positioning method and system for indoor robots described in this application achieve the following effects:

[0030] The indoor robot hybrid positioning method proposed in this application is based on a hybrid map constructed by a two-dimensional map and a three-dimensional map to enable the robot to achieve fast and accurate positioning during normal operation. During abnormal startup, the robot can be repositioned reliably based on the relationship between the hybrid map, the three-dimensional map and the two-dimensional map. No other auxiliary technical means are required during repositioning, and the repositioning is accurate and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0032] Figure 1 This is a schematic diagram of the structure of the indoor robot hybrid positioning system proposed in the embodiment of the present application;

[0033] Figure 2 This is a flow chart of the indoor robot hybrid positioning method proposed in the embodiment of the present application;

[0034] Figure 3 This is a schematic diagram of an installation position of the information acquisition module on a robot proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In view of the problems mentioned in the background technology of this application, when using the two-dimensional laser positioning method to reposition the robot, due to the small amount of information, if two-dimensional laser positioning is needed, other technical means must be used to assist in repositioning, which makes repositioning difficult. Although the use of pure visual positioning technology can better solve the repositioning problem, it is easily affected by factors such as light and image quality, and has low reliability.

[0036] like Figure 2 The figure shows a flow chart of the indoor robot hybrid positioning method proposed in the embodiment of the present application. The indoor robot hybrid positioning method proposed in the present application is described in detail below through the above-mentioned drawings.

[0037] The present application provides a hybrid positioning method for an indoor robot, comprising the following steps:

[0038] Starting the robot positioning system 101;

[0039] When the robot starts normally, it obtains two-dimensional information and three-dimensional information 201, matches the two-dimensional information and three-dimensional information to the hybrid map 202, and obtains the coordinate position of the robot in the hybrid map 400;

[0040] When the robot is abnormally started, the original coordinate information is obtained based on the hybrid map 301, the original position is matched to the two-dimensional map 302, and then the positioning of the two-dimensional map is initialized 303, and the hybrid map is initialized according to the initialized two-dimensional map 304; the coordinate position of the robot is obtained according to the steps of normal startup 400;

[0041] The hybrid map is composed of a two-dimensional map and a three-dimensional map.

[0042] Preferably, the method further includes a self-check step before positioning. If the positioning self-check is normal, the robot position is positioned according to the normal start. If the positioning self-check is abnormal, the robot position is positioned according to the abnormal start.

[0043] In specific application scenarios, after the robot starts normally, when obtaining the coordinate position of the robot in the hybrid map, the robot can match the two-dimensional information and three-dimensional information with different weights to the hybrid map according to the complexity of the actual map to obtain the position of the robot in the hybrid map. When the map is relatively simple, you can choose to increase the weight of the two-dimensional map appropriately to locate the robot's position more efficiently; when the map is relatively complex, you can increase the weight of the three-dimensional map appropriately to locate the robot's position more accurately.

[0044] The two-dimensional map is constructed by two-dimensional information collected by a two-dimensional information collection device; and the three-dimensional map is constructed by three-dimensional information collected by a three-dimensional information collection device.

[0045] Among them, the two-dimensional information includes: laser point cloud information; the three-dimensional information includes: visual image information.

[0046] Compared with the prior art, the beneficial technical effects of the technical solution proposed in the embodiment of the present application include:

[0047] The indoor robot hybrid positioning method proposed in this application is based on a hybrid map constructed by a two-dimensional map and a three-dimensional map, which enables the robot to achieve fast and accurate positioning during normal operation. In the event of abnormal startup, the robot can be repositioned reliably based on the relationship between the hybrid map, the three-dimensional map and the two-dimensional map.

[0048] like Figure 1 The figure is a schematic diagram of the structure of the indoor robot hybrid positioning system proposed in the embodiment of the present application. The indoor robot hybrid positioning system proposed in the present application is described in detail below through the above drawings.

[0049] The present application also provides an indoor robot hybrid positioning system, which is characterized by comprising: an information acquisition module 100, a coordinate position module 200, a positioning module 300, and a repositioning module 400.

[0050] The information acquisition module 100 is connected to the coordinate position module 200, the positioning module 300, and the repositioning module 400, and is used for the acquisition module to acquire two-dimensional information and three-dimensional information;

[0051] The coordinate location module 200 includes a hybrid map 210, which is connected to the positioning module 300 and the positioning module 400. The hybrid map 210 is composed of a two-dimensional map 211 and a three-dimensional map 212.

[0052] The positioning module 300 is used to match the two-dimensional information and the three-dimensional information to the coordinate position module 200 to determine the coordinate position of the robot;

[0053] The relocation module 400 is used to match the three-dimensional information to the hybrid map 210 to obtain the original position of the robot in the hybrid map, match the original position to the two-dimensional map 211, and then initialize the positioning of the two-dimensional map 211, and then initialize the positioning of the two-dimensional map 211, and initialize the hybrid map 210 according to the initialized two-dimensional map 211; and obtain the coordinate position of the robot according to the normal startup steps. The hybrid map is composed of the two-dimensional map 211 and the three-dimensional map 212.

[0054] Preferably, it also includes: a self-check module, which is used for the self-check step before positioning. If the positioning self-check is normal, the robot position is positioned according to the normal start. If the positioning self-check is abnormal, the robot position is positioned according to the abnormal start.

[0055] The information acquisition module 100 includes a two-dimensional information acquisition device and a three-dimensional information acquisition device.

[0056] The two-dimensional information acquisition device is used to acquire two-dimensional information; the three-dimensional information acquisition device is used to acquire three-dimensional information.

[0057] In a specific application scenario, the two-dimensional information acquisition device includes: a laser 110, which can acquire laser point cloud information;

[0058] The three-dimensional information acquisition device includes: a binocular camera 120, which can acquire visual image information.

[0059] like Figure 3 The figure shows a schematic diagram of an installation position of the information collection device on the robot in this embodiment. Preferably, the laser is a linear laser, the two camera components of the binocular camera are located on the same horizontal line, and the linear laser is located below the binocular camera 120 and parallel to the binocular camera.

[0060] Compared with the prior art, the beneficial technical effects of the technical solution proposed in the embodiment of the present application include:

[0061] The indoor robot hybrid positioning system provided by the present application can realize reliable repositioning of the robot without the assistance of other technical means when the robot is abnormally started. During normal operation, the robot can realize fast and accurate positioning of the robot based on a hybrid map constructed by a two-dimensional map and a three-dimensional map.

[0062] For example, certain words are used in the specification and claims to refer to specific components. Those skilled in the art should understand that hardware manufacturers may use different nouns to refer to the same component. This specification and claims do not use differences in names as a way to distinguish components, but use differences in the functions of components as the criteria for distinction. As mentioned throughout the specification and claims, "including" is an open term, so it should be interpreted as "including but not limited to". "Approximately" means that within an acceptable error range, those skilled in the art can solve the technical problem within a certain error range and basically achieve the technical effect. The subsequent description of the specification is a preferred embodiment of the present application, but the description is for the purpose of illustrating the general principles of the present application, and is not used to limit the scope of the present application. The scope of protection of the present application shall be determined by the attached claims.

[0063] The above description shows and describes several preferred embodiments of the present application, but as mentioned above, it should be understood that the present application is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be modified within the scope of the application concept described herein through the above teachings or the technology or knowledge of the relevant field. The changes and modifications made by those skilled in the art do not deviate from the spirit and scope of the present application, and should be within the scope of protection of the claims attached to the present application.

Claims

1. A hybrid positioning system for indoor robots, characterized in that: include: An information acquisition module, a coordinate position module, a positioning module, and a repositioning module. The information acquisition module is connected to the coordinate position module, the positioning module, and the repositioning module, and is used for the acquisition module to acquire two-dimensional information and three-dimensional information; the coordinate position module includes a hybrid map, which is connected to the positioning module and the positioning module, and the hybrid map is composed of a two-dimensional map and a three-dimensional map; The positioning module is used to match the two-dimensional information and the three-dimensional information to the coordinate position module to determine the coordinate position of the robot; The relocation module is used to match the three-dimensional information to the hybrid map to obtain the original position of the robot in the hybrid map, match the original position to the two-dimensional map, and then initialize the positioning of the two-dimensional map, and initialize the hybrid map according to the initialized two-dimensional map; The coordinate position of the robot is obtained according to the steps of normal startup; wherein the hybrid map is composed of a two-dimensional map and a three-dimensional map; it also includes: a self-check module, the self-check module is used for the steps of self-check before positioning, if the positioning self-check is normal, the robot position is positioned according to the normal startup, if the positioning self-check is abnormal, the robot position is positioned according to the abnormal startup; wherein, the information acquisition module includes a two-dimensional information acquisition device and a three-dimensional information acquisition device; the two-dimensional information acquisition device is used to collect two-dimensional information; the three-dimensional information acquisition device is used to collect three-dimensional information; the two-dimensional information acquisition device includes: a laser, the laser can collect laser point cloud information; the three-dimensional information acquisition device includes: a binocular camera, the binocular camera can collect visual image information; when the system is working, it includes the following steps: starting the robot positioning system; when the robot starts normally, obtaining two-dimensional information and three-dimensional information, matching the two-dimensional information and three-dimensional information to the hybrid map, The robot coordinate position in the hybrid map is obtained; when the robot is abnormally started, the original coordinate information is obtained based on the hybrid map, and the original position is matched to the two-dimensional map. After that, the positioning of the two-dimensional map is initialized, and the hybrid map is initialized according to the initialized two-dimensional map; the robot coordinate position is obtained according to the normal startup steps; wherein, the hybrid map is composed of a two-dimensional map and a three-dimensional map; the robot also includes a self-check step before positioning, if the positioning self-check is normal, the robot position is positioned according to the normal startup, if the positioning self-check is abnormal, the robot position is positioned according to the abnormal startup; after the robot is normally started, when the robot coordinate position in the hybrid map is obtained, the robot matches the two-dimensional information and the three-dimensional information of different weights to the hybrid map according to the complexity of the actual map to obtain the robot position in the hybrid map; when the map is relatively simple, the weight of the two-dimensional map is appropriately increased; when the map is relatively complex, the weight of the three-dimensional map is appropriately increased.