A positioning method, system, and storage medium for long shelf inspection robots

Abstract

This invention discloses a positioning method, system, and storage medium for inspection robots operating in long aisle corridors. It constructs a grid map of the long aisle, records the 2D laser scan profiles of the inspection robot at the beginning and end of the aisle, and the robot's current pose. Based on the robot's laser positioning system and 2D laser scanning device, it acquires the robot's real-time pose and real-time 2D laser scan frames. The difference between the robot's real-time pose and the recorded pose at the beginning of the aisle is calculated. Registration is then performed using the real-time received 2D laser scan frames and 2D laser scan profiles to determine the robot's current position. This invention solves the positioning problem of inspection robots in long aisle scenarios without increasing the robot's cost, demonstrating good adaptability to various scenarios.

Description

Technical Field

[0001] This application relates to the field of autonomous mobile inspection robot positioning, and more specifically, to a positioning method, system, and storage medium for a robot inspecting long shelves. Background Technology

[0002] Indoor inspection robots perform autonomous inspections within a work environment, requiring the pre-construction of a 2D grid map of the work environment using laser SLAM (Simultaneous Localization and Mapping) technology. The robot's localization is achieved through real-time registration between the 2D laser scan outline and the pre-built grid map. However, in scenarios with very long shelving aisles, similar to corridors, the laser scan outline remains essentially unchanged even as the robot moves forward. This can lead to the robot easily losing its localization during inspections within long shelving areas.

[0003] Therefore, existing technologies have shortcomings and urgently need improvement. Summary of the Invention

[0004] In view of the above problems, the purpose of this invention is to provide a positioning method, system and storage medium for inspection robots facing long shelves, which can more conveniently solve the positioning problem of inspection robots in long corridor scenarios.

[0005] The first aspect of this invention provides a positioning method for a long shelf inspection robot, comprising:

[0006] Based on the grid map Map of the pre-set long shelf aisle, obtain the 2D laser scan profile of the inspection robot at the beginning and end of each long shelf aisle and the current pose of the inspection robot;

[0007] Based on the laser positioning system of the inspection robot, the position and pose information of the inspection robot can be obtained in real time.

[0008] Determine whether the difference between the pose of the inspection robot and the pose of the inspection robot at the beginning of each long shelf aisle is less than a preset first difference. If yes, trigger the switch of the 2D laser scanning device; otherwise, set the pose of the inspection robot as the current position of the inspection robot.

[0009] Acquire 2D laser scan frame information;

[0010] Based on a preset algorithm, the 2D laser scan frame and the 2D laser scan contour are registered to obtain a registration score;

[0011] Determine whether the registration score is greater than a preset first registration value. If yes, set the pose of the 2D laser scan contour position as the current position of the inspection robot; otherwise, continue to acquire 2D laser scan frame information.

[0012] In this solution, the method for constructing the grid map of the preset long shelving aisle specifically includes:

[0013] The inspection robot is manually controlled to move and a map of its walking route in a long shelf aisle is obtained.

[0014] The walking route map of the long shelving aisle is rasterized according to the long shelving to obtain a raster map of the long shelving aisle.

[0015] The long rack aisles are numbered in ascending order according to a preset sequence to obtain the long rack aisle numbering information;

[0016] Send the long rack aisle numbers to the long rack aisle grid map for storage.

[0017] In this solution, the method for obtaining the 2D laser scan profiles of the inspection robot at the beginning and end of each long shelf aisle and the current pose of the inspection robot is as follows:

[0018] Move the inspection robot to point B at the end of the long aisle, and control it to face the aisle and be positioned in the middle of the aisle. Record the 2D laser scan profile and the robot's current pose at the current location, denoted as follows: and ;

[0019] Move the inspection robot to point A at the beginning of the long aisle, and control the robot so that its back faces the aisle and it is in the middle of the aisle. Record the 2D laser scan profile and the robot's current pose at the current position, denoted as follows: and ;

[0020] in This indicates the number of the long shelving aisle.

[0021] In this solution, the step of triggering the switch of the 2D laser scanning device further includes;

[0022] Obtain the direction information of the inspection robot's movement;

[0023] Based on the direction information of the inspection robot's movement, we can determine whether the inspection robot is facing the corridor or its back is facing the corridor.

[0024] When the difference between the pose of the inspection robot and the pose of the inspection robot at the beginning of each long shelf aisle is less than the preset first difference, and the inspection robot is facing the aisle, turn on the 2D laser scanning device.

[0025] When the inspection robot moves beyond the starting position to the end position, and the back of the inspection robot faces the corridor, turn off the 2D laser scanning device.

[0026] This plan also includes;

[0027] Obtain the route information of the inspection robot in the grid map Map of the preset long shelf aisle;

[0028] Determine whether the inspection robot's movement route and direction are consistent in the grid map Map of the preset long shelf aisle. If not, trigger an alert; if so, do not trigger an alert.

[0029] In this scheme, the step of registering the 2D laser scanning frame and the 2D laser scanning contour based on a preset algorithm to obtain a registration score specifically includes:

[0030] 2D laser scanning contour Set the source point cloud as the source point cloud, and set the 2D laser scan frame Scan as the target point cloud;

[0031] Based on a preset algorithm, the target point cloud is registered to the source point cloud, with the initial value set to 0, to obtain the registration score, which is calculated using the following formula:

[0032] ;

[0033] Where n represents the number of nearest neighbor pairs, For a point in the target point cloud Scan, Source Point Cloud Zhongyu The corresponding nearest point, where when hour, Indicates the corridor number is 2D laser scan profile at the end position; when hour, Indicates the corridor number is 2D laser scan profile at the beginning position.

[0034] A second aspect of the present invention provides a positioning system for a long shelf inspection robot, comprising a memory and a processor. The memory stores a positioning method program for the long shelf inspection robot, and when the processor executes the positioning method program for the long shelf inspection robot, it performs the following steps:

[0035] Based on the grid map Map of the pre-set long shelf aisle, obtain the 2D laser scan profile of the inspection robot at the beginning and end of each long shelf aisle and the current pose of the inspection robot;

[0036] Based on the laser positioning system of the inspection robot, the position and pose information of the inspection robot can be obtained in real time.

[0037] Determine whether the difference between the pose of the inspection robot and the pose of the inspection robot at the beginning of each long shelf aisle is less than a preset first difference. If yes, trigger the switch of the 2D laser scanning device; otherwise, set the pose of the inspection robot as the current position of the inspection robot.

[0038] Acquire 2D laser scan frame information;

[0039] Based on a preset algorithm, the 2D laser scan frame and the 2D laser scan contour are registered to obtain a registration score;

[0040] Determine whether the registration score is greater than a preset first registration value. If yes, set the pose of the 2D laser scan contour position as the current position of the inspection robot; otherwise, continue to acquire 2D laser scan frame information.

[0041] In this solution, the method for constructing the grid map of the preset long shelving aisle specifically includes:

[0042] The inspection robot is manually controlled to move and a map of its walking route in a long shelf aisle is obtained.

[0043] The walking route map of the long shelving aisle is rasterized according to the long shelving to obtain a raster map of the long shelving aisle.

[0044] The long rack aisles are numbered in ascending order according to a preset sequence to obtain the long rack aisle numbering information;

[0045] Send the long rack aisle numbers to the long rack aisle grid map for storage.

[0046] In this solution, the method for obtaining the 2D laser scan profiles of the inspection robot at the beginning and end of each long shelf aisle and the current pose of the inspection robot is as follows:

[0047] Move the inspection robot to point B at the end of the long aisle, and control it to face the aisle and be positioned in the middle of the aisle. Record the 2D laser scan profile and the robot's current pose at the current location, denoted as follows: and ;

[0048] Move the inspection robot to point A at the beginning of the long aisle, and control the robot so that its back faces the aisle and it is in the middle of the aisle. Record the 2D laser scan profile and the robot's current pose at the current position, denoted as follows: and ;

[0049] in This indicates the number of the long shelving aisle.

[0050] In this solution, the step of triggering the switch of the 2D laser scanning device further includes;

[0051] Obtain the direction information of the inspection robot's movement;

[0052] Based on the direction information of the inspection robot's movement, we can determine whether the inspection robot is facing the corridor or its back is facing the corridor.

[0053] When the difference between the pose of the inspection robot and the pose of the inspection robot at the beginning of each long shelf aisle is less than the preset first difference, and the inspection robot is facing the aisle, turn on the 2D laser scanning device.

[0054] When the inspection robot moves beyond the starting position to the end position, and the back of the inspection robot faces the corridor, turn off the 2D laser scanning device.

[0055] This plan also includes;

[0056] Obtain the route information of the inspection robot in the grid map Map of the preset long shelf aisle;

[0057] Determine whether the inspection robot's movement route and direction are consistent in the grid map Map of the preset long shelf aisle. If not, trigger an alert; if so, do not trigger an alert.

[0058] In this scheme, the step of registering the 2D laser scanning frame and the 2D laser scanning contour based on a preset algorithm to obtain a registration score specifically includes:

[0059] 2D laser scanning contour Set the source point cloud as the source point cloud, and set the 2D laser scan frame Scan as the target point cloud;

[0060] Based on a preset algorithm, the target point cloud is registered to the source point cloud, with the initial value set to 0, to obtain the registration score, which is calculated using the following formula:

[0061] ;

[0062] Where n represents the number of nearest neighbor pairs, For a point in the target point cloud Scan, Source Point Cloud Zhongyu The corresponding nearest point, where when hour, Indicates the corridor number is 2D laser scan profile at the end position; when hour, Indicates the corridor number is 2D laser scan profile at the beginning position.

[0063] A third aspect of the present invention provides a computer storage medium storing a positioning method program for a long shelf inspection robot, wherein when the positioning method program for a long shelf inspection robot is executed by a processor, the steps of the positioning method for a long shelf inspection robot as described in any of the preceding claims are implemented.

[0064] This invention discloses a positioning method, system, and storage medium for inspection robots facing long shelves. It solves the positioning problem of inspection robots in long corridor scenarios without increasing the cost of the inspection robots, and has good adaptability to the scenario. Attached Figure Description

[0065] Figure 1 A flowchart of a positioning method for a long shelf inspection robot according to the present invention is shown;

[0066] Figure 2-1 and Figure 2-2 The map shows a grid map of the long shelving aisle and the movement routes of two inspection robots.

[0067] Figure 3 A block diagram of a positioning system for a long shelf inspection robot according to the present invention is shown. Detailed Implementation

[0068] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0069] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0070] Figure 1 A flowchart of a positioning method for a long shelf inspection robot according to the present invention is shown.

[0071] like Figure 1 As shown, this invention discloses a positioning method for a robot inspecting long shelves, comprising:

[0072] S102, based on the grid map Map of the preset long shelf corridor, obtain the 2D laser scan profile of the inspection robot at the beginning and end of each long shelf corridor and the current pose of the inspection robot;

[0073] S104, based on the inspection robot laser positioning system, acquires the position and pose information of the inspection robot in real time;

[0074] S106, determine whether the difference between the pose of the inspection robot and the pose of the inspection robot at the beginning of each long shelf aisle is less than a preset first difference. If yes, trigger the switch of the 2D laser scanning device; if no, set the pose of the inspection robot as the current position of the inspection robot.

[0075] S108, acquire 2D laser scan frame information;

[0076] S110, based on a preset algorithm, registers the 2D laser scanning frame and the 2D laser scanning contour to obtain a registration score;

[0077] S112, determine whether the registration score is greater than the preset first registration value. If yes, set the pose of the 2D laser scan contour position as the current position of the inspection robot; otherwise, continue to acquire 2D laser scan frame information.

[0078] It should be noted that, after starting the inspection robot and manually controlling its movement, a grid map of the long shelf aisle is constructed. Then, the 2D laser scan contours and the current pose of the inspection robot at the beginning and end of each long shelf aisle are marked. The beginning of the long shelf aisle is where the inspection robot enters, and the end of the long shelf aisle is at the other end of the corresponding long shelf aisle. Through the inspection robot's laser positioning function, the pose output by the inspection robot is received in real time. If the preset first difference value is 0.1, then when the difference between the inspection robot's pose and the training pose of the inspection robot at the beginning of each long shelf aisle is less than 0.1, real-time reception of 2D laser scan frames begins, and the laser positioning system continues. Laser positioning ensures that the inspection robot does not deviate left or right or its angular direction while moving through the long shelf aisle. If the preset first registration value is set to 0.1, when the registration score between the 2D laser scan frame and the 2D laser scan profile is greater than 0.1, it is considered that the current position of the inspection robot is at the position corresponding to the 2D laser scan profile. For example, if the 2D laser scan profile is the 2D laser scan profile of the inspection robot at the end of the long shelf aisle numbered j, then the inspection robot has arrived at the end of the long shelf aisle numbered j.

[0079] Figure 2-1 and Figure 2-2 The map shows a grid map of the long shelving aisle and the movement routes of two inspection robots.

[0080] like Figure 2-1 and Figure 2-2As shown in the embodiment of the present invention, the method for constructing the grid map of the preset long shelving aisle specifically includes:

[0081] The inspection robot is manually controlled to move and a map of its walking route in a long shelf aisle is obtained.

[0082] The walking route map of the long shelving aisle is rasterized according to the long shelving to obtain a raster map of the long shelving aisle.

[0083] The long rack aisles are numbered in ascending order according to a preset sequence to obtain the long rack aisle numbering information;

[0084] Send the long rack aisle numbers to the long rack aisle grid map for storage.

[0085] It should be noted that when the preset order is from left to right, the leftmost long aisle is numbered 1, and then numbered sequentially from smallest to largest. The end of the long aisle where the inspection robot enters is designated as the starting position, and the opposite side as the ending position. For example... Figure 2-1 The inspection robot follows a reversal route, moving from point A at the beginning to point B at the end, then returning from point B to point A at the beginning of the corresponding long corridor, before continuing its inspection of the next long shelving corridor; for example... Figure 2-2 The inspection robot travels in a zigzag pattern, moving from point A at the beginning to point B at the end, and then turning into the next long shelf aisle on the same side to perform inspection.

[0086] According to an embodiment of the present invention, the method for obtaining the 2D laser scan profiles of the inspection robot at the beginning and end of each long shelf aisle and the current pose of the inspection robot specifically includes:

[0087] Move the inspection robot to point B at the end of the long aisle, and control it to face the aisle and be positioned in the middle of the aisle. Record the 2D laser scan profile and the robot's current pose at the current location, denoted as follows: and ;

[0088] Move the inspection robot to point A at the beginning of the long aisle, and control the robot so that its back faces the aisle and it is in the middle of the aisle. Record the 2D laser scan profile and the robot's current pose at the current position, denoted as follows: and ;

[0089] in This indicates the number of the long shelving aisle.

[0090] It should be noted that in the embodiment of the invention, the preset distance is set to 8 meters, meaning the inspection robot is controlled to be 8 meters away from the end of the long shelf aisle B. When At that time, the beginning position of the corresponding long shelving aisle is set as The end position is set as .

[0091] According to an embodiment of the present invention, the step of triggering the switch of the 2D laser scanning device further includes;

[0092] Obtain the direction information of the inspection robot's movement;

[0093] Based on the direction information of the inspection robot's movement, we can determine whether the inspection robot is facing the corridor or its back is facing the corridor.

[0094] When the difference between the pose of the inspection robot and the pose of the inspection robot at the beginning of each long shelf aisle is less than the preset first difference, and the inspection robot is facing the aisle, turn on the 2D laser scanning device.

[0095] When the inspection robot moves beyond the starting position to the end position, and the back of the inspection robot faces the corridor, turn off the 2D laser scanning device.

[0096] It should be noted that the direction of the long shelving aisle refers to the direction from the beginning to the end of the long shelving aisle. When the inspection robot moves between the beginning and the end of the aisle, if the front of the inspection robot faces the same direction as the long shelving aisle, it is considered that the inspection robot is facing the long shelving aisle; otherwise, it is considered that the robot is facing away from the long shelving aisle. When the inspection robot moves outside the area between the beginning and the end of the aisle, moving away from the beginning or the end of the aisle is considered that the robot is facing away from the long shelving aisle, and moving closer to the beginning or the end of the aisle is considered that the robot is facing the long shelving aisle. When the inspection robot moves facing the long shelving aisle, it is considered to be entering the corresponding long shelving aisle; otherwise, it is considered to be moving away from the long shelving aisle. The inspection robot activates the 2D laser scanning device when it enters the beginning of the aisle and deactivates the 2D laser scanning device when it leaves the area between the beginning and the end of the long shelving aisle.

[0097] According to embodiments of the present invention, it further includes;

[0098] Obtain the route information of the inspection robot in the grid map Map of the preset long shelf aisle;

[0099] Determine whether the inspection robot's movement route and direction are consistent in the grid map Map of the preset long shelf aisle. If not, trigger an alert; if so, do not trigger an alert.

[0100] It should be noted that the robot's movement is manually controlled, and a pre-set route map for the inspection robot in the long shelf aisle area is created and marked on the corresponding grid map. The direction of the inspection robot's movement is consistent with the direction from the beginning to the end of the long shelf aisle.

[0101] According to an embodiment of the present invention, the step of registering the 2D laser scanning frame and the 2D laser scanning contour based on a preset algorithm to obtain a registration score specifically includes:

[0102] 2D laser scanning contour Set the source point cloud as the source point cloud, and set the 2D laser scan frame Scan as the target point cloud;

[0103] Based on a preset algorithm, the target point cloud is registered to the source point cloud, with the initial value set to 0, to obtain the registration score, which is calculated using the following formula:

[0104] ;

[0105] Where n represents the number of nearest neighbor pairs, For a point in the target point cloud Scan, Source Point Cloud Zhongyu The corresponding nearest point, where when hour, Indicates the corridor number is 2D laser scan profile at the end position; when hour, Indicates the corridor number is 2D laser scan profile at the beginning position.

[0106] It should be noted that the preset algorithm is the Iterativa Closest Point (ICP) algorithm. The ICP algorithm is used to calculate the registration score of the 2D laser scan frame received by the inspection robot in real time and the 2D laser scan profile at the beginning or end of the long shelf aisle.

[0107] According to an embodiment of the present invention, it further includes:

[0108] Obtain information on the distance traveled by the inspection robot;

[0109] Based on the distance traveled by the inspection robot, the direction of travel, and the beginning or end of the long shelf aisle traversed by the inspection robot, the distance between the inspection robot and the beginning or end of the long shelf aisle can be obtained.

[0110] The distance between the inspection robot and the beginning or end of the long shelving aisle is set as the current position of the inspection robot.

[0111] It should be noted that when the inspection robot's 2D laser scanning device is activated, the odometer is also activated simultaneously. The odometer records the distance the inspection robot travels from the beginning or end of the long aisle. For example, when the inspection robot enters aisle number 2, it reaches... When the time is set, the 2D laser scanning device is activated, and the odometer is also activated. When the recorded distance traveled by the inspection robot is 20 meters, the distance of the inspection robot in the No. 2 long shelf aisle is displayed. At a point 20 meters away, the direction is facing the long shelving aisle.

[0112] According to an embodiment of the present invention, it further includes:

[0113] Determine whether the distance traveled by the inspection robot exceeds a preset first distance threshold. If so, trigger a prompt; otherwise, display "normal".

[0114] It should be noted that the preset odometer for the inspection robot resets its mileage count upon contacting point A or point B, and counts only within long aisle shelves. When the robot's 2D laser scanning device is turned off, the odometer also shuts down to reduce energy consumption. For example, if the inspection robot follows a zigzag route, entering a long aisle from point A and exiting from point B, the odometer will activate at point A and deactivate at point B, recording the distance from A to B. If the mileage count exceeds a first distance threshold, it indicates a significant displacement deviation or mileage counting error during the robot's movement. This first distance threshold is slightly greater than the straight-line distance from A to B.

[0115] Figure 3 A block diagram of a positioning system for a long shelf inspection robot according to the present invention is shown.

[0116] like Figure 3 As shown, a second aspect of the present invention provides a positioning system 3 for a long shelf inspection robot, including a memory 31 and a processor 32. The memory stores a positioning method program for the long shelf inspection robot. When the processor executes the positioning method program for the long shelf inspection robot, it performs the following steps:

[0117] Based on the grid map Map of the pre-set long shelf aisle, obtain the 2D laser scan profile of the inspection robot at the beginning and end of each long shelf aisle and the current pose of the inspection robot;

[0118] Based on the laser positioning system of the inspection robot, the position and pose information of the inspection robot can be obtained in real time.

[0119] Determine whether the difference between the pose of the inspection robot and the pose of the inspection robot at the beginning of each long shelf aisle is less than a preset first difference. If yes, trigger the switch of the 2D laser scanning device; otherwise, set the pose of the inspection robot as the current position of the inspection robot.

[0120] Acquire 2D laser scan frame information;

[0121] Based on a preset algorithm, the 2D laser scan frame and the 2D laser scan contour are registered to obtain a registration score;

[0122] Determine whether the registration score is greater than a preset first registration value. If yes, set the pose of the 2D laser scan contour position as the current position of the inspection robot; otherwise, continue to acquire 2D laser scan frame information.

[0123] It should be noted that, after starting the inspection robot and manually controlling its movement, a grid map of the long shelf aisle is constructed. Then, the 2D laser scan contours and the current pose of the inspection robot at the beginning and end of each long shelf aisle are marked. The beginning of the long shelf aisle is where the inspection robot enters, and the end of the long shelf aisle is at the other end of the corresponding long shelf aisle. Through the inspection robot's laser positioning function, the pose output by the inspection robot is received in real time. If the preset first difference value is 0.1, then when the difference between the inspection robot's pose and the training pose of the inspection robot at the beginning of each long shelf aisle is less than 0.1, real-time reception of 2D laser scan frames begins, and the laser positioning system continues. Laser positioning ensures that the inspection robot does not deviate left or right or its angular direction while moving through the long shelf aisle. If the preset first registration value is set to 0.1, when the registration score between the 2D laser scan frame and the 2D laser scan profile is greater than 0.1, it is considered that the current position of the inspection robot is at the position corresponding to the 2D laser scan profile. For example, if the 2D laser scan profile is the 2D laser scan profile of the inspection robot at the end of the long shelf aisle numbered j, then the inspection robot has arrived at the end of the long shelf aisle numbered j.

[0124] According to an embodiment of the present invention, the method for constructing the grid map of the preset long shelving aisle specifically includes:

[0125] The inspection robot is manually controlled to move and a map of its walking route in a long shelf aisle is obtained.

[0126] The walking route map of the long shelving aisle is rasterized according to the long shelving to obtain a raster map of the long shelving aisle.

[0127] The long rack aisles are numbered in ascending order according to a preset sequence to obtain the long rack aisle numbering information;

[0128] Send the long rack aisle numbers to the long rack aisle grid map for storage.

[0129] It should be noted that when the preset order is from left to right, the leftmost long aisle is numbered 1, and then numbered sequentially from smallest to largest. The end of the long aisle where the inspection robot enters is designated as the starting position, and the opposite side as the ending position. For example... Figure 2-1 The inspection robot follows a reversal route, moving from point A at the beginning to point B at the end, then returning from point B to point A at the beginning of the corresponding long corridor, before continuing its inspection of the next long shelving corridor; for example... Figure 2-2 The inspection robot travels in a zigzag pattern, moving from point A at the beginning to point B at the end, and then turning into the next long shelf aisle on the same side to perform inspection.

[0130] According to an embodiment of the present invention, the method for obtaining the 2D laser scan profiles of the inspection robot at the beginning and end of each long shelf aisle and the current pose of the inspection robot specifically includes:

[0131] Move the inspection robot to point B at the end of the long aisle, and control it to face the aisle and be positioned in the middle of the aisle. Record the 2D laser scan profile and the robot's current pose at the current location, denoted as follows: and ;

[0132] Move the inspection robot to point A at the beginning of the long aisle, and control the robot so that its back faces the aisle and it is in the middle of the aisle. Record the 2D laser scan profile and the robot's current pose at the current position, denoted as follows: and ;

[0133] in This indicates the number of the long shelving aisle.

[0134] It should be noted that in the embodiment of the invention, the preset distance is set to 8 meters, meaning the inspection robot is controlled to be 8 meters away from the end of the long shelf aisle B. When At that time, the beginning position of the corresponding long shelving aisle is set as The end position is set as .

[0135] According to an embodiment of the present invention, the step of triggering the switch of the 2D laser scanning device further includes;

[0136] Obtain the direction information of the inspection robot's movement;

[0137] Based on the direction information of the inspection robot's movement, we can determine whether the inspection robot is facing the corridor or its back is facing the corridor.

[0138] When the difference between the pose of the inspection robot and the pose of the inspection robot at the beginning of each long shelf aisle is less than the preset first difference, and the inspection robot is facing the aisle, turn on the 2D laser scanning device.

[0139] When the inspection robot moves beyond the starting position to the end position, and the back of the inspection robot faces the corridor, turn off the 2D laser scanning device.

[0140] It should be noted that the direction of the long shelving aisle refers to the direction from the beginning to the end of the long shelving aisle. When the inspection robot moves between the beginning and the end of the aisle, if the front of the inspection robot faces the same direction as the long shelving aisle, it is considered that the inspection robot is facing the long shelving aisle; otherwise, it is considered that the robot is facing away from the long shelving aisle. When the inspection robot moves outside the area between the beginning and the end of the aisle, moving away from the beginning or the end of the aisle is considered that the robot is facing away from the long shelving aisle, and moving closer to the beginning or the end of the aisle is considered that the robot is facing the long shelving aisle. When the inspection robot moves facing the long shelving aisle, it is considered to be entering the corresponding long shelving aisle; otherwise, it is considered to be moving away from the long shelving aisle. The inspection robot activates the 2D laser scanning device when it enters the beginning of the aisle and deactivates the 2D laser scanning device when it leaves the area between the beginning and the end of the long shelving aisle.

[0141] According to embodiments of the present invention, it further includes;

[0142] Obtain the route information of the inspection robot in the grid map Map of the preset long shelf aisle;

[0143] Determine whether the inspection robot's movement route and direction are consistent in the grid map Map of the preset long shelf aisle. If not, trigger an alert; if so, do not trigger an alert.

[0144] It should be noted that the robot's movement is manually controlled, and a pre-set route map for the inspection robot in the long shelf aisle area is created and marked on the corresponding grid map. The direction of the inspection robot's movement is consistent with the direction from the beginning to the end of the long shelf aisle.

[0145] According to an embodiment of the present invention, the step of registering the 2D laser scanning frame and the 2D laser scanning contour based on a preset algorithm to obtain a registration score specifically includes:

[0146] 2D laser scanning contour Set the source point cloud as the source point cloud, and set the 2D laser scan frame Scan as the target point cloud;

[0147] Based on a preset algorithm, the target point cloud is registered to the source point cloud, with the initial value set to 0, to obtain the registration score, which is calculated using the following formula:

[0148] ;

[0149] Where n represents the number of nearest neighbor pairs, For a point in the target point cloud Scan, Source Point Cloud Zhongyu The corresponding nearest point, where when hour, Indicates the corridor number is 2D laser scan profile at the end position; when hour, Indicates the corridor number is 2D laser scan profile at the beginning position.

[0150] It should be noted that the preset algorithm is the Iterativa Closest Point (ICP) algorithm. The ICP algorithm is used to calculate the registration score of the 2D laser scan frame received by the inspection robot in real time and the 2D laser scan profile at the beginning or end of the long shelf aisle.

[0151] According to an embodiment of the present invention, it further includes:

[0152] Obtain information on the distance traveled by the inspection robot;

[0153] Based on the distance traveled by the inspection robot, the direction of travel, and the beginning or end of the long shelf aisle traversed by the inspection robot, the distance between the inspection robot and the beginning or end of the long shelf aisle can be obtained.

[0154] The distance between the inspection robot and the beginning or end of the long shelving aisle is set as the current position of the inspection robot.

[0155] It should be noted that when the inspection robot's 2D laser scanning device is activated, the odometer is also activated simultaneously. The odometer records the distance the inspection robot travels from the beginning or end of the long aisle. For example, when the inspection robot enters aisle number 2, it reaches... When the time is set, the 2D laser scanning device is activated, and the odometer is also activated. When the recorded distance traveled by the inspection robot is 20 meters, the distance of the inspection robot in the No. 2 long shelf aisle is displayed. At a point 20 meters away, the direction is facing the long shelving aisle.

[0156] According to an embodiment of the present invention, it further includes:

[0157] Determine whether the distance traveled by the inspection robot exceeds a preset first distance threshold. If so, trigger a prompt; otherwise, display "normal".

[0158] It should be noted that the preset odometer for the inspection robot resets its mileage count upon contacting point A or point B, and counts only within long aisle shelves. When the robot's 2D laser scanning device is turned off, the odometer also shuts down to reduce energy consumption. For example, if the inspection robot follows a zigzag route, entering a long aisle from point A and exiting from point B, the odometer will activate at point A and deactivate at point B, recording the distance from A to B. If the mileage count exceeds a first distance threshold, it indicates a significant displacement deviation or mileage counting error during the robot's movement. This first distance threshold is slightly greater than the straight-line distance from A to B.

[0159] A third aspect of the present invention provides a computer storage medium storing a positioning method program for a long shelf inspection robot, wherein when the positioning method program for a long shelf inspection robot is executed by a processor, the steps of the positioning method for a long shelf inspection robot as described in any of the preceding claims are implemented.

[0160] This invention discloses a positioning method, system, and storage medium for inspection robots operating in long aisle corridors. It constructs a grid map of the long aisle, records the 2D laser scan profiles of the inspection robot at the beginning and end of the aisle, and the robot's current pose. Based on the robot's laser positioning system and 2D laser scanning device, it acquires the robot's real-time pose and real-time 2D laser scan frames. The difference between the robot's real-time pose and the recorded pose at the beginning of the aisle is calculated. Registration is then performed using the real-time received 2D laser scan frames and 2D laser scan profiles to determine the robot's current position. This invention solves the positioning problem of inspection robots in long aisle scenarios without increasing the robot's cost, demonstrating good adaptability to various scenarios.

[0161] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0162] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0163] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0164] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0165] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A method of positioning a long-shelf-patrol robot, characterized by, include: Based on the grid map Map of the pre-set long shelf aisle, obtain the 2D laser scan profile of the inspection robot at the beginning and end of each long shelf aisle and the current pose of the inspection robot; Based on the laser positioning system of the inspection robot, the position and pose information of the inspection robot can be obtained in real time. Determine whether the difference between the pose of the inspection robot and the pose of the inspection robot at the beginning of each long shelf aisle is less than a preset first difference. If yes, trigger the switch of the 2D laser scanning device; otherwise, set the pose of the inspection robot as the current position of the inspection robot. Acquire 2D laser scan frame information; Based on a preset algorithm, the 2D laser scan frame and the 2D laser scan contour are registered to obtain a registration score; Determine whether the registration score is greater than a preset first registration value. If yes, set the pose of the 2D laser scan contour position as the current position of the inspection robot; otherwise, continue to acquire 2D laser scan frame information.

2. The positioning method for a long-shelf facing inspection robot according to claim 1, characterized in that, The method for constructing the grid map of the preset long shelving aisle specifically includes: The inspection robot is manually controlled to move and a map of its walking route in a long shelf aisle is obtained. The walking route map of the long shelving aisle is rasterized according to the long shelving to obtain a raster map of the long shelving aisle. The long rack aisles are numbered in ascending order according to a preset sequence to obtain the long rack aisle numbering information; Send the long rack aisle numbers to the long rack aisle grid map for storage.

3. The method of claim 1, wherein, The method for obtaining the 2D laser scan profiles of the inspection robot at the beginning and end of each long shelf aisle and the current pose of the inspection robot is as follows: The inspection robot is run to the end B of the long shelf corridor, and the inspection robot is controlled to face the corridor, the inspection robot is in the middle of the corridor, the 2D laser scanning profile under the current position and the current pose of the inspection robot are recorded, and are recorded as and , respectively. The inspection robot is run to the beginning of the long-shelf corridor at A, and the back of the inspection robot is controlled to face the corridor, the inspection robot is in the middle of the corridor, the 2D laser scanning profile under the current position and the current pose of the inspection robot are recorded, and are recorded as and , respectively. wherein denotes the number of long shelf corridors.

4. The method of claim 1, wherein, The step of triggering the switch of the 2D laser scanning device further includes; Obtain the direction information of the inspection robot's movement; Based on the direction information of the inspection robot's movement, we can determine whether the inspection robot is facing the corridor or its back is facing the corridor. When the difference between the pose of the inspection robot and the pose of the inspection robot at the beginning of each long shelf aisle is less than the preset first difference, and the inspection robot is facing the aisle, turn on the 2D laser scanning device. When the inspection robot moves outside the starting position to the end position and its back is facing the corridor, turn off the 2D laser scanning device.

5. The method of claim 4, wherein, Also includes; Obtain the route information of the inspection robot in the grid map Map of the preset long shelf aisle; Determine whether the inspection robot's movement route and direction are consistent in the grid map Map of the preset long shelf aisle. If not, trigger an alert; if so, do not trigger an alert.

6. The method of claim 1, wherein, The step of registering the 2D laser scan frame and the 2D laser scan contour based on a preset algorithm to obtain a registration score specifically includes: 2D laser scanning contour Set the source point cloud as the source point cloud, and set the 2D laser scan frame Scan as the target point cloud; Based on a preset algorithm, the target point cloud is registered to the source point cloud, with the initial value set to 0, to obtain the registration score, which is calculated using the following formula: ； Where n represents the number of nearest neighbor pairs, For a point in the target point cloud Scan, Source Point Cloud Zhongyu The corresponding nearest point, where when hour, Indicates the corridor number is 2D laser scan profile at the end position; when hour, Indicates the corridor number is 2D laser scan profile at the beginning position.

7. A positioning system for a long shelf inspection robot, characterized in that, The system includes a memory and a processor. The memory stores a positioning method program for a long shelf inspection robot. When the processor executes the positioning method program for the long shelf inspection robot, it performs the following steps: Based on the grid map Map of the pre-set long shelf aisle, obtain the 2D laser scan profile of the inspection robot at the beginning and end of each long shelf aisle and the current pose of the inspection robot; Based on the laser positioning system of the inspection robot, the position and pose information of the inspection robot can be obtained in real time. Determine whether the difference between the pose of the inspection robot and the pose of the inspection robot at the beginning of each long shelf aisle is less than a preset first difference. If yes, trigger the switch of the 2D laser scanning device; otherwise, set the pose of the inspection robot as the current position of the inspection robot. Acquire 2D laser scan frame information; Based on a preset algorithm, the 2D laser scan frame and the 2D laser scan contour are registered to obtain a registration score; Determine whether the registration score is greater than a preset first registration value. If yes, set the pose of the 2D laser scan contour position as the current position of the inspection robot; otherwise, continue to acquire 2D laser scan frame information.

8. A positioning system for a long shelf inspection robot according to claim 7, characterized in that, The method for constructing the grid map of the preset long shelving aisle specifically includes: The inspection robot is manually controlled to move and a map of its walking route in a long shelf aisle is obtained. The walking route map of the long shelving aisle is rasterized according to the long shelving to obtain a raster map of the long shelving aisle. The long rack aisles are numbered in ascending order according to a preset sequence to obtain the long rack aisle numbering information; Send the long rack aisle numbers to the long rack aisle grid map for storage.

9. A positioning system for a long shelf inspection robot according to claim 7, characterized in that, The method for obtaining the 2D laser scan profiles of the inspection robot at the beginning and end of each long shelf aisle and the current pose of the inspection robot is as follows: Move the inspection robot to point B at the end of the long aisle, and control it to face the aisle. Position the robot in the middle of the aisle and record the 2D laser scan profile and the robot's current pose at the current location, denoted as follows: and ; Move the inspection robot to point A at the beginning of the long aisle, and control the robot so that its back faces the aisle and it is in the middle of the aisle. Record the 2D laser scan profile and the robot's current pose at the current position, denoted as follows: and ; in This indicates the number of the long shelving aisle.

10. A computer storage medium, characterized in that, The computer storage medium stores a positioning method program for a long shelf inspection robot. When the positioning method program for a long shelf inspection robot is executed by the processor, it implements the steps of the positioning method for a long shelf inspection robot as described in any one of claims 1 to 6.

Images