Robot indoor repositioning method and system based on iros

Abstract

The application discloses a robot indoor repositioning method and system based on IROS, and belongs to the technical field of intelligent robots. The technical problem to be solved by the application is how to reposition during robot operation, shorten repositioning time, reduce misjudgment rate, and thus improve the fluency of robot operation. The technical scheme adopted is as follows: the method is based on the intelligent robot operating system (IROS) to develop and deploy a positioning node and a navigation node. Sensor data of a laser radar, vision and IMU are collected in real time into a series of topics of an rMQ node of the intelligent robot operating system (IROS). The positioning node subscribes to the sensor data of the topics in the rMQ node and generates local mapping information and position information. The position information is saved in the form of parameters in an rParamter node of the intelligent robot operating system (IROS) to form a positioning DB library. The navigation node plans and navigates by using the position information. When the positioning node fails to position and encounters a similar environment, a repositioning process is triggered.

Description

Technical Field

[0001] This invention relates to the field of intelligent robot technology, specifically to an indoor robot repositioning method and system based on IROS. Background Technology

[0002] Since the birth of the first robot, robots have evolved from simple to complex. Modern intelligent robots can acquire environmental information through various sensors and use artificial intelligence to identify, understand, reason, judge, and make decisions to complete specific tasks. Therefore, in addition to environmental perception, intelligent robots also possess strong recognition, understanding, and decision-making capabilities. Autonomous mobile robots are currently a hot topic and a key focus of development, especially in the field of service robots, where the scenarios involved are quite complex, requiring robots to possess autonomous positioning and navigation technology. The robot's positioning problem is about determining its position in the current environment based on observed information. Once the position is determined, a goal can be set, and a global path can be planned to achieve that goal—point-to-point navigation.

[0003] During navigation, robots may encounter obstacles or changes in the environment. Due to deviations in sensor data, continuous localization (or relocalization) is necessary to refine the path through local planning. Relocalization typically utilizes visual images and / or laser information obtained from sensors to first create a local map, then compares and queries it against a pre-built global map to determine the current position. In navigation, robots often encounter environments with high similarity, such as corners, corridors with white walls on both sides, or passageways between rows of server racks in a server room. In complex environments, robots may struggle to determine their correct location, necessitating relocalization. Indoor relocalization generally involves circling in place to collect environmental information and using algorithms to identify subtle differences in the environment and match them with a global map to determine the current position. These methods can generally solve most relocalization problems, but they can lead to higher false positive rates and longer localization times in highly similar environments.

[0004] Therefore, how to perform relocation during robot operation, shorten the relocation time while reducing the misjudgment rate, and thus improve the smoothness of robot operation is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] The technical objective of this invention is to provide an indoor robot relocation method and system based on IROS to solve the problem of how to perform relocation during robot operation, shorten the relocation time while reducing the misjudgment rate, and thus improve the smoothness of robot operation.

[0006] The technical objective of this invention is achieved as follows: an indoor robot relocalization method based on IROS. This method involves developing and deploying localization and navigation nodes based on the intelligent robot operating system IROS. Sensor data from LiDAR, vision, and IMU are collected in real time and fed into a series of topics on the rMQ node of the intelligent robot operating system IROS. The localization node subscribes to the sensor data of the topics in the rMQ node and generates local mapping information and location information. The location information is stored as parameters in the rParamter node of the intelligent robot operating system IROS, forming a localization database. The navigation node uses the location information for planning and navigation.

[0007] When a location node fails to locate and encounters a highly similar environment, a relocation process is triggered, as follows:

[0008] The relocation service is invoked on the rService node deployed on the intelligent robot operating system IROS. The relocation service obtains the location B and time B of the most recent successful location from the rParamter node based on the current system time A.

[0009] Based on time B, obtain the sensor data from the irosBag file of the irosBag node in the Intelligent Robot Operating System IROS, including time B and subsequent time B.

[0010] The relocation service calculates a new position C relative to position B based on sensor data from time B and beyond.

[0011] The new location C is mapped onto the global map. Based on the deviation rate of the sensor data, an expanded local map is formed with the new location C as the center in the global map according to the deviation range of the sensor data.

[0012] The relocation service then uses the current sensor data to perform position matching in the expanded local map, thereby determining the robot's current position A, and saves the information of the current position A to the rParamter node.

[0013] As a preferred method, the relocation process utilizes current environmental information and recent historical information stored in the irosBag node and the location database to comprehensively determine the current location and achieve indoor relocation.

[0014] Even better, during robot operation, the irosBag node of the intelligent robot operating system IROS is started. The irosBag node subscribes to the sensor data of the topic in real time and saves it in the irosBag file.

[0015] Ideally, location information is stored as parameters in the rParameter node. The parameter name contains an integer value in seconds, which is convenient for subsequent queries by parameter name. The value corresponding to the parameter is binary data without format restrictions. By default, only the most recent hour's value is retained for location information (this value can be modified), and expired values ​​will be cleared.

[0016] Even better, the sensor data in the irosBag file is obtained through real-time subscription. When saving sensor data, in addition to the raw sensor data, a timestamp with a precision of microseconds is added to facilitate the relocation service in calculating the relative position. An irosBag file is generated every 10 minutes, and by default only the files from the most recent hour are retained (this value can be modified).

[0017] Preferably, an expanded local map is formed centered on the new location C in the global map according to the deviation range of the sensor data. This expanded local map is used as the global map during relocation. The range of this expanded local map is generally smaller than the real global map, so the accuracy of matching within it is higher and the matching speed is faster.

[0018] An indoor robot relocalization system based on IROS, comprising an intelligent robot operating system IROS and positioning and navigation nodes deployed based on the intelligent robot operating system IROS; the intelligent robot operating system IROS includes four basic nodes: rMaster node, rMQ node, rService node, and rParamter node, irosBag node, and utility nodes that can be started on demand.

[0019] The rMQ node is used to store a series of topics related to real-time sensor data from LiDAR, vision, and IMU.

[0020] The rParamter node is used to save location information in the form of parameters, forming a location database.

[0021] The irosBag node is used to subscribe to sensor data for a topic in real time and save it in the irosBag file;

[0022] The rService node is used to deploy the relocation service, which provides indoor relocation services based on the current system information.

[0023] The location node is used to subscribe to sensor data for topics in the rMQ node and generate local mapping information and location information;

[0024] Navigation nodes are used to plan and navigate using location information.

[0025] Preferably, when the positioning node fails to locate and encounters a highly similar environment, a relocation process is triggered, as follows:

[0026] (1) Call the relocation service of the rService node deployed on the intelligent robot operating system IROS. The relocation service obtains the location B and time B of the most recent successful location from the rParamter node according to the current system time A.

[0027] (2) Obtain the sensor data after time B from the irosBag file of the irosBag node of the intelligent robot operating system IROS based on time B.

[0028] (3) The relocation service calculates the new position C relative to position B based on sensor data from time B and after time B.

[0029] (4) Map the new location C onto the global map. Based on the deviation rate of the sensor data, form an expanded local map with the new location C in the global map as the center and according to the deviation range of the sensor data.

[0030] (5) The relocation service then performs position matching in the expanded local map based on the current sensor data, thereby determining the robot's current position A, and saving the information of the current position A to the rParamter node.

[0031] An electronic device includes: a memory and at least one processor;

[0032] The memory contains computer programs;

[0033] The at least one processor executes the computer program stored in the memory, causing the at least one processor to perform the IROS-based indoor robot relocation method as described above.

[0034] A computer-readable storage medium storing a computer program that can be executed by a processor to implement the IROS-based indoor robot relocation method described above.

[0035] The IROS-based indoor robot relocation method and system of the present invention have the following advantages:

[0036] (i) The present invention is applicable to the installation of the IROS intelligent robot operating system in the robot. The repositioning in the robot operation has the advantages of short repositioning time and low misjudgment rate, which can improve the smoothness of robot operation.

[0037] (ii) This invention uses the intelligent robot operating system IROS, which is similar in function to ROS, but has higher performance, reliability and security than ROS. Robots developed based on IROS have a higher level of intelligence.

[0038] (iii) The performance of the IROS of this invention is two orders of magnitude higher than that of ROS. In addition, the map matching range is small, and the robot can quickly relocate when it loses its location during operation, making the robot run more smoothly.

[0039] (iv) The relocation method involved in this invention is only applicable to relocation during runtime. It is not suitable for situations such as manual relocation after shutdown. In other cases, ordinary relocation methods are used. It can be determined whether it is a relocation during runtime based on the current time information, the position information stored in the rParameter node, and the irosBag information.

[0040] (v) The robot of the present invention is equipped with the intelligent robot operating system IROS, which has low computing power requirements and utilizes the performance advantages of IROS to achieve higher repositioning efficiency and accuracy during operation, and the robot runs more smoothly. Attached Figure Description

[0041] The invention will be further described below with reference to the accompanying drawings.

[0042] Appendix Figure 1 This is a schematic diagram of an indoor robot relocation method based on IROS. Detailed Implementation

[0043] The IROS-based indoor robot relocation method and system of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0044] Example 1:

[0045] As attached Figure 1 As shown, this embodiment provides a robot indoor relocalization method based on IROS. This method is based on the intelligent robot operating system IROS to develop and deploy positioning nodes and navigation nodes. Sensor data from LiDAR, vision, and IMU are collected in real time into a series of topics in the rMQ node of the intelligent robot operating system IROS. The positioning node subscribes to the sensor data in the topics in the rMQ node and generates local mapping information and location information. The location information is stored as parameters in the rParamter node of the intelligent robot operating system IROS to form a positioning database. The navigation node uses the location information for planning and navigation.

[0046] When a location node fails to locate and encounters a highly similar environment, a relocation process is triggered, as follows:

[0047] S1. Call the relocation service of the rService node deployed on the intelligent robot operating system IROS. The relocation service obtains the location B and time B of the most recent successful location from the rParamter node according to the current system time A.

[0048] S2. Obtain sensor data after time B from the irosBag file of the irosBag node of the intelligent robot operating system IROS based on time B.

[0049] S3. The relocation service calculates the new position C relative to position B based on sensor data from time B and beyond.

[0050] S4. Map the new location C onto the global map. Based on the deviation rate of the sensor data, form an expanded local map with the new location C as the center in the global map according to the deviation range of the sensor data.

[0051] S5. The relocation service then uses the current sensor data as a basis to perform position matching in the expanded local map, thereby determining the robot's current position A, and saving the information of the current position A to the rParamter node.

[0052] In this embodiment, the relocation process uses current environmental information and recent historical information stored in the irosBag node and the location database to comprehensively determine the current location and achieve indoor relocation.

[0053] In this embodiment, during robot operation, the irosBag node of the intelligent robot operating system IROS is activated. The irosBag node subscribes to the sensor data of the topic in real time and saves it in the irosBag file.

[0054] In this embodiment, location information is stored in the rParameter node as parameters. The parameter name contains an integer value in seconds, which is convenient for subsequent querying by parameter name. The value corresponding to the parameter is binary data without restriction on format. By default, the location information only retains the value of the most recent hour (this value can be modified), and expired values ​​will be cleared.

[0055] In this embodiment, the sensor data in the irosBag file is obtained through real-time subscription. When saving the sensor data, in addition to the original sensor data, a timestamp with a precision of microseconds is added to facilitate the relocation service in calculating the relative position. An irosBag file is generated every 10 minutes, and by default only the file from the most recent hour is retained (this value can be modified).

[0056] In this embodiment, an expanded local map is formed centered on the new location C in the global map according to the deviation range of the sensor data. This expanded local map is used as the global map during relocation. The range of this expanded local map is generally smaller than the real global map, so the accuracy of matching within it is higher and the matching speed is faster.

[0057] Example 2:

[0058] As attached Figure 1 As shown, this embodiment provides an indoor robot relocation system based on IROS. The system includes the intelligent robot operating system IROS and positioning and navigation nodes deployed based on the intelligent robot operating system IROS. The intelligent robot operating system IROS includes four basic nodes: rMaster node, rMQ node, rService node, and rParamter node, as well as irosBag node and utility nodes that can be started on demand.

[0059] The rMQ node is used to store a series of topics related to real-time sensor data from LiDAR, vision, and IMU.

[0060] The rParamter node is used to save location information in the form of parameters, forming a location database.

[0061] The irosBag node is used to subscribe to sensor data for a topic in real time and save it in the irosBag file;

[0062] The rService node is used to deploy the relocation service, which provides indoor relocation services based on the current system information.

[0063] The location node is used to subscribe to sensor data for topics in the rMQ node and generate local mapping information and location information;

[0064] Navigation nodes are used to plan and navigate using location information.

[0065] In this embodiment, when the positioning node fails to locate and encounters a highly similar environment, a relocation process is triggered, as follows:

[0066] (1) Call the relocation service of the rService node deployed on the intelligent robot operating system IROS. The relocation service obtains the location B and time B of the most recent successful location from the rParamter node according to the current system time A.

[0067] (2) Obtain the sensor data after time B from the irosBag file of the irosBag node of the intelligent robot operating system IROS based on time B.

[0068] (3) The relocation service calculates the new position C relative to position B based on sensor data from time B and after time B.

[0069] (4) Map the new location C onto the global map. Based on the deviation rate of the sensor data, form an expanded local map with the new location C in the global map as the center and according to the deviation range of the sensor data.

[0070] (5) The relocation service then performs position matching in the expanded local map based on the current sensor data, thereby determining the robot's current position A, and saving the information of the current position A to the rParamter node.

[0071] Example 3:

[0072] This embodiment also provides an electronic device, including: a memory and a processor;

[0073] The memory stores the instructions executed by the computer.

[0074] The processor executes computer execution instructions stored in the memory, causing the processor to perform the IROS-based indoor robot relocation method in any embodiment of the present invention.

[0075] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor can be a microprocessor or any conventional processor.

[0076] Memory is used to store computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory, and by accessing data stored in the memory. Memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system, at least one application program required for a function, etc.; the data storage area can store data created based on the use of the terminal, etc. In addition, memory can also include high-speed random access memory, and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart memory cards (SMC), secure digital cards (SD cards), flash memory cards, at least one disk storage device, flash memory devices, or other volatile solid-state storage devices.

[0077] Example 4:

[0078] This embodiment also provides a computer-readable storage medium storing multiple instructions, which are loaded by a processor to cause the processor to execute the IROS-based indoor robot relocalization method according to any embodiment of the present invention. Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the above embodiments is stored, and the computer (or CPU or MPU) of the system or apparatus can read and execute the program code stored in the storage medium.

[0079] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.

[0080] Storage media embodiments for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RYM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0081] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0082] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion unit connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion unit execute some and all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for IROS-based robot indoor relocalization, characterized in that, The method is based on intelligent robot operating system IROS to develop and deploy positioning nodes and navigation nodes, sensor data of a laser radar, vision and IMU is collected in real time to a series of topics of an rMQ node of the intelligent robot operating system IROS, the positioning node subscribes to the sensor data of the topic in the rMQ node and generates local mapping information and position information, the position information is saved in the rParamter node of the intelligent robot operating system IROS in the form of parameters, forming a positioning DB library; the navigation node uses the position information for planning and navigation; When the positioning node fails to position and encounters a similar environment, the repositioning process is triggered, and the specific process is as follows: Call the repositioning service of the rService node deployed in the intelligent robot operating system IROS, and the repositioning service obtains the position B and time B of the last successful positioning from the rParamter node according to the current system time A; According to the time B, the sensor data after the time B is obtained from the irosBag file of the irosBag node of the intelligent robot operating system IROS; The repositioning service calculates a new position C relative to the position B according to the time B and the sensor data after the time B; Map the new position C to the global map, and form an expanded local map according to the deviation range of the sensor data with the new position C as the center in the global map; The repositioning service performs position matching in the expanded local map based on the current sensor data, thereby determining the current position A of the robot, and saving the information of the current position A to the rParamter node.

2. The IROS-based robot indoor relocalization method of claim 1, wherein, The repositioning process uses the current environmental information and the recent historical information stored in the irosBag node and the positioning DB library to comprehensively determine the current position, thereby realizing indoor repositioning.

3. The IROS-based robot indoor relocalization method according to claim 1 or 2, characterized in that, During the operation of the robot, the irosBag node of the intelligent robot operating system IROS is started, and the irosBag node subscribes to the sensor data of the topic in real time and saves it in the irosBag file.

4. The IROS-based robot indoor relocalization method of claim 3, wherein, The position information is saved in the rParameter node in the form of parameters, and the parameter name is an integer value with seconds as the unit; the value corresponding to the parameter is binary data without format limitation; The position information is only kept for the last one hour by default, and the expired information will be cleared.

5. The IROS-based robot indoor relocalization method of claim 4, wherein, The sensor data in the irosBag file is obtained by real-time subscription, and when saving the sensor data, a timestamp with an accuracy of microseconds is added in addition to the original sensor data; the irosBag file generates a file every 10 minutes, and only the files in the last one hour are kept by default.

6. The IROS-based robot indoor relocalization method of claim 1, wherein, The new position C in the global map is taken as the center to form an expanded local map according to the deviation range of the sensor data, and the expanded local map is taken as the global map during repositioning. The range of the expanded local map is smaller than that of the real global map.

7. A robot indoor repositioning system based on IROS, characterized in that, The system comprises an intelligent robot operating system (IROS) and a positioning node and a navigation node deployed based on the intelligent robot operating system (IROS); the intelligent robot operating system (IROS) comprises four basic nodes of an rMaster node, an rMQ node, an rService node and an rParamter node, an irosBag node and tool-type nodes started on demand; The rMQ node is used for storing a series of topics of sensor data of a laser radar, vision and IMU collected in real time; The rParamter node is used for saving position information in a parameter form to form a positioning DB library; The irosBag node is used for subscribing to sensor data of topics in real time and saving in an irosBag file; The rService node is used for deploying a repositioning service, and the repositioning service realizes indoor repositioning service according to current system information; The positioning node is used for subscribing to sensor data of topics in the rMQ node and generating local mapping information and position information; The navigation node is used for planning and navigation by using the position information; When the positioning node fails to position and encounters a similar environment, a repositioning process is triggered, and the repositioning process is as follows: (1) a repositioning service of the rService node deployed in the intelligent robot operating system (IROS) is called, the repositioning service acquires a last successful positioning position B and time B from the rParamter node according to current system time A; (2) sensor data after the time B is acquired from an irosBag file of the irosBag node of the intelligent robot operating system (IROS) according to the time B; (3) the repositioning service calculates a new position C relative to the position B according to the time B and the sensor data after the time B; (4) the new position C is mapped to a global map, and an expanded local map is formed with the new position C as a center and according to a deviation range of the sensor data in the global map; (5) the repositioning service performs position matching in the expanded local map based on current sensor data, thereby determining a current position A of the robot, and saving information of the current position A to the rParamter node.

8. An electronic device, comprising: Comprise: a memory and at least one processor; wherein the memory has stored thereon a computer program; the at least one processor executes the computer program stored in the memory, so that the at least one processor executes the indoor repositioning method of the robot based on the IROS as claimed in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium has stored therein a computer program, and the computer program can be executed by a processor to implement the indoor repositioning method of the robot based on the IROS as claimed in any one of claims 1 to 6.

Images