A position adjustment method based on QR code recognition

Abstract

An embodiment of the present invention discloses a position adjustment method based on QR code recognition. In order to adapt to the use in actual industrial scenarios, a QR code detection and positioning method is used in combination. By calculating the position offset between the QR code in the actual picture and the QR code in the standard picture, the offset is converted into the offset of the robot. On the basis of laser positioning, the stability and accuracy of the robot moving to the charging pile for charging positioning are assisted. Specifically, the robot first navigates to the charging point to adjust the position, and then uses a camera to take an actual picture with a QR code, calculates the position offset between the QR code in the actual picture and the QR code in the standard picture, and converts it into the robot offset position. The robot position offset is corrected by taking multiple shots of the QR code position in the actual picture. When the QR code position error in the actual picture is less than a certain threshold or greater than the number of pictures taken, the adjustment is stopped, and the robot retreats into the charging pile.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular to a position adjustment method based on two-dimensional code recognition. Background Art

[0002] Before the robot enters the charging state, it is necessary to first use accurate positioning adjustment methods. Common methods use rear laser point cloud data, reduce the adjustment step size, and adjust the robot's angle and position offset. However, the robot's laser position is usually located at the front or back. When the robot laser is positioned at the front, the lack of rear laser data during the charging state will affect the accuracy of the robot's posture adjustment. Summary of the Invention

[0003] In order to solve the existing technical problems, an embodiment of the present invention provides a position adjustment method based on QR code recognition, which uses the relative offset between the QR code of the charging pile position and the preset position to assist computer position correction. Using the QR code image to assist robot correction can effectively improve the positioning accuracy and stability.

[0004] To achieve the above-mentioned purpose, the technical solution of the embodiment of the present invention is implemented as follows:

[0005] An embodiment of the present invention provides a position adjustment method based on QR code recognition, the method comprising:

[0006] S11: Use laser positioning navigation to navigate the robot to the adjusted position of the charging point;

[0007] S12: Controlling the robot to move left and right at the adjustment position and recording the robot's position offset, and using a camera to capture a real picture with a QR code, wherein the recorded robot's position offset is a first position offset;

[0008] S13: Calculating a position offset between the QR code in the actual image and the QR code in the standard image based on the actual image and the standard image, wherein the calculated position offset is a second position offset, wherein the standard image is a picture taken when the robot is facing the charging pile;

[0009] S14: Calculating a deviation weight ratio between the first position offset and the second position offset according to the first position offset and the second position offset;

[0010] S15: Calculate the distance that the robot needs to move laterally according to the first position offset and the deviation weight ratio, and then adjust the position of the robot to control the robot to retreat into the charging pile.

[0011] Preferably, the method of using a camera to take a real picture with a QR code includes:

[0012] Use the camera to take real-time pictures;

[0013] Determine whether the real picture contains a QR code by using a QR code detection algorithm;

[0014] If the judgment result is yes, execute step S13;

[0015] If the judgment result is no, then continue to execute step S12.

[0016] Preferably, the controlling the robot to move left and right at the adjustment position and recording the robot's offset, and using a camera to take a real picture with a QR code includes:

[0017] Control the robot to move left and right multiple times at the adjustment position, and record the first position offset of each left and right movement of the robot;

[0018] The camera is controlled to take a plurality of the real-shot pictures, wherein the number of left and right lateral movements of the robot and the number of the real-shot pictures taken are in a one-to-one correspondence.

[0019] Preferably, the calculating, based on the real picture and the standard picture, the position offset between the QR code in the real picture and the QR code in the standard picture includes:

[0020] According to the key point matching algorithm, the second position offset between the QR code in each of the real pictures and the QR code in the standard picture is calculated.

[0021] Preferably, the calculating, based on the first position offset and the second position offset, a deviation weight ratio between the two comprises:

[0022] A two-dimensional array is formed based on a plurality of first position offsets and a corresponding plurality of second position offsets, and a deviation weight ratio of the first position offset to the second position offset is calculated.

[0023] Preferably, the step of adjusting the position of the robot and controlling the robot to retreat into the charging pile includes:

[0024] After executing step S15, if the position offset between the QR code in the actual picture and the QR code in the standard picture is less than threshold A or the number of times the actual picture is taken is greater than threshold B, the robot stops adjusting, and then the robot retreats into the charging pile, otherwise, returns to step S12.

[0025] Preferably, the key point matching algorithm is a deep neural network matching method.

[0026] An embodiment of the present invention further provides a position adjustment device based on QR code recognition, comprising:

[0027] A navigation module, used to navigate the robot to the adjusted position of the charging point using a laser positioning navigation method;

[0028] Control module: used to control the robot to move left and right at the adjustment position and record the robot's offset, and use the camera to take a real picture with a QR code;

[0029] A first calculation module is used to calculate the position offset between the QR code in the real picture and the QR code in the standard picture based on the real picture and the standard picture;

[0030] A second calculation module: according to the first position offset and the second position offset, calculates the deviation weight ratio between the two;

[0031] The third calculation module calculates the distance the robot needs to move laterally according to the first position offset and the deviation weight ratio, and then adjusts the position of the robot to control the robot to retreat into the charging pile.

[0032] An embodiment of the present invention further provides a computer device, comprising: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor is configured to implement the method described in item when running the computer program.

[0033] An embodiment of the present invention further provides a computer storage medium storing an executable program, wherein when the executable program is executed by a processor, the method described above is implemented.

[0034] The above embodiment provides a position adjustment method based on QR code recognition. In order to adapt to the use in actual industrial scenarios, it uses a QR code detection and positioning method in combination. By calculating the position offset between the QR code in the actual picture and the QR code in the standard picture, it is converted into the offset of the robot. On the basis of laser positioning, it helps to improve the stability and accuracy of the robot moving to the charging pile for charging positioning. Specifically, the robot first navigates to the charging point to adjust the position, and then uses the camera to take a real picture with a QR code, calculates the position offset between the QR code in the actual picture and the QR code in the standard picture, and converts it into the robot offset position. The robot position offset is corrected by taking multiple shots of the QR code position in the actual picture. When the QR code position error in the actual picture is less than a certain threshold or greater than the number of pictures taken, the adjustment is stopped and the robot retreats into the charging pile. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic flow chart of a method provided in one embodiment of the present invention;

[0036] Figure 2 A schematic structural diagram of a device provided in one embodiment of the present invention;

[0037] Figure 3 A flowchart of a specific method provided by an embodiment of the present invention;

[0038] Figure 4 A flowchart of a specific method according to an embodiment of the present invention;

[0039] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present invention; DETAILED DESCRIPTION

[0040] The present invention will be further described in detail below with reference to the following examples. It should be understood that the specific examples described herein are only used to explain the present invention and are not intended to limit the present invention.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used herein in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0042] A position adjustment method based on QR code recognition provided in an embodiment of the present invention belongs to the field of image recognition technology, and its application scenario can be: navigating a robot to the charging position of a charging pile. It is understandable that in the prior art, before the robot enters the charging state, it is necessary to first use an accurate positioning adjustment method, which commonly uses rear-mounted laser point cloud data to reduce the adjustment step size and adjust the robot's angle and position offset. However, the common laser position of the robot is at the front or rear end. When the robot laser is positioned at the front, the lack of rear laser data in the charging backward state will affect the accuracy of the robot's posture adjustment.

[0043] Based on this, how to improve the accuracy of the robot's posture adjustment when charging and retreating has become a technical problem that needs to be solved urgently.

[0044] It should be noted that this method is performed by a computer device. It should be noted that the computer device here refers to any device with computing capabilities, including but not limited to fixed terminal devices or mobile terminal devices. Fixed terminal devices may include but are not limited to desktop computers or computer devices, and mobile terminal devices may include but are not limited to mobile phones, tablet computers, wearable devices, or laptop computers.

[0045] The technical solution of the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0046] refer to Figure 1, an embodiment of the present invention provides a position adjustment method based on two-dimensional code recognition, the method comprising:

[0047] S11: Use laser positioning navigation to navigate the robot to the adjusted position of the charging point;

[0048] S12: Controlling the robot to move left and right at the adjustment position and recording the robot's position offset, and using a camera to capture a real picture with a QR code, wherein the recorded robot's position offset is a first position offset;

[0049] S13: Calculating a position offset between the QR code in the actual image and the QR code in the standard image based on the actual image and the standard image, wherein the calculated position offset is a second position offset, wherein the standard image is a picture taken when the robot is facing the charging pile;

[0050] S14: Calculating a deviation weight ratio between the first position offset and the second position offset according to the first position offset and the second position offset;

[0051] S15: Calculate the distance that the robot needs to move laterally according to the first position offset and the deviation weight ratio, and then adjust the position of the robot to control the robot to retreat into the charging pile.

[0052] In this embodiment, in order to adapt to the use in actual industrial scenarios, a QR code detection and positioning method is used in combination. By calculating the position offset between the QR code in the actual picture and the QR code in the standard picture, it is converted into the offset of the robot. On the basis of laser positioning, it helps to improve the stability and accuracy of the robot moving to the charging pile for charging positioning. Specifically, the robot first navigates to the charging point to adjust its position, and then uses the camera to take a real picture with a QR code. The position offset between the QR code in the actual picture and the QR code in the standard picture is calculated and converted into the robot offset position. The robot position offset is corrected by taking multiple shots of the QR code position in the actual picture. When the QR code position error in the actual picture is less than a certain threshold or greater than the number of pictures taken, the adjustment is stopped and the robot retreats into the charging pile.

[0053] In some embodiments, the step of using a camera to capture a real picture with a QR code includes:

[0054] Use the camera to take real-time pictures;

[0055] Determine whether the real picture contains a QR code by using a QR code detection algorithm;

[0056] If the judgment result is yes, execute step S13;

[0057] If the judgment result is no, then continue to execute step S12.

[0058] It should be noted that after each real-shot picture is taken, a QR code detection is required to determine whether a QR code exists in the real-shot picture to avoid obtaining an invalid first position offset later.

[0059] In some embodiments, the specific process from step S12 to step S14 is as follows:

[0060] 1. Control the robot to move left and right multiple times at the adjustment position, and record the first position offset of each left and right movement of the robot;

[0061] 2. Controlling the camera to capture multiple real-shot images, wherein the number of left and right lateral movements of the robot corresponds to the number of real-shot images captured;

[0062] 3. Calculate the second position offset between the QR code in each of the actual pictures and the QR code in the standard picture according to the key point matching algorithm.

[0063] 4. Based on a two-dimensional array composed of multiple first position offsets and corresponding multiple second position offsets, calculate the deviation weight ratio of the first position offset and the second position offset, where the two-dimensional array is [(d1, d_pixel1), (d2, d_pixel2), ...], dn is the first position offset, d_pixeln is the second position offset, then the obtained deviation weight ratio scale is:

[0064]

[0065] In general, the robot position offset is corrected by taking multiple shots of the QR code position in the actual image: in each iteration, the QR code detection algorithm is used to determine whether there is a QR code in the actual image, and the affine transformation matrix is ​​calculated according to the key point matching algorithm to obtain the offset information of the QR code position in the actual image. Then, the distance the robot needs to move laterally is calculated based on the offset information and the weight ratio scale.

[0066] In some embodiments, adjusting the position of the robot and controlling the robot to retreat into the charging station includes:

[0067] After executing step S15, if the position offset between the QR code in the actual picture and the QR code in the standard picture is less than threshold A or the number of times the actual picture is taken is greater than threshold B, the robot stops adjusting, and then the robot retreats into the charging pile, otherwise, returns to step S12.

[0068] In some embodiments, the key point matching algorithm is a deep neural network matching method or a traditional SIFT / SURF algorithm.

[0069] like Figure 2 As shown, the embodiment of the present invention also provides a position adjustment device based on two-dimensional code recognition, comprising

[0070] A navigation module 21 is used to navigate the robot to the adjusted position of the charging point using a laser positioning navigation method;

[0071] Control module 22: used to control the robot to move left and right at the adjustment position and record the robot's offset, and use a camera to take a real picture with a QR code;

[0072] A first calculation module 23 is configured to calculate, based on the real-shot image and the standard image, a position offset between the QR code in the real-shot image and the QR code in the standard image;

[0073] A second calculation module 24 calculates a deviation weight ratio between the first position offset and the second position offset according to the first position offset and the second position offset;

[0074] The third calculation module 25 calculates the distance that the robot needs to move laterally according to the first position offset and the deviation weight ratio, and then adjusts the position of the robot to control the robot to retreat into the charging pile.

[0075] In some embodiments, the control module 22 is further configured to:

[0076] Use the camera to take real-time pictures;

[0077] Determine whether the real picture contains a QR code by using a QR code detection algorithm;

[0078] If the judgment result is yes, then execute step S13 of the method;

[0079] If the judgment result is no, then continue to execute step S12 of the method.

[0080] In some embodiments, the control module 22 is specifically configured to:

[0081] Control the robot to move left and right multiple times at the adjustment position, and record the first position offset of each left and right movement of the robot;

[0082] The camera is controlled to take a plurality of the real-shot pictures, wherein the number of left and right lateral movements of the robot and the number of the real-shot pictures taken are in a one-to-one correspondence.

[0083] In some embodiments, the first calculation module 23 is specifically configured to:

[0084] According to the key point matching algorithm, the second position offset between the QR code in each of the real pictures and the QR code in the standard picture is calculated.

[0085] In some embodiments, the second calculation module 24 is specifically configured to:

[0086] A two-dimensional array is formed based on a plurality of first position offsets and a corresponding plurality of second position offsets, and a deviation weight ratio of the first position offset to the second position offset is calculated.

[0087] In some embodiments, the third calculation module 25 is specifically configured to:

[0088] After executing step S15, if the position offset between the QR code in the actual picture and the QR code in the standard picture is less than threshold A or the number of times the actual picture is taken is greater than threshold B, the robot stops adjusting, and then the robot retreats into the charging pile, otherwise, returns to step S12.

[0089] It should be noted that the description of the above device items is similar to the description of the above method items, and the description of the beneficial effects of the same method is not repeated. For technical details not disclosed in the device embodiments of the present invention, please refer to the description of the method embodiments of the present invention.

[0090] The present invention also provides a specific embodiment to further understand the present invention.

[0091] Currently, traditional robots require precise positioning and adjustment before entering charging mode. This typically involves using rear-facing laser point cloud data to reduce the adjustment step size and adjust the robot's angle and position offset. However, the robot's laser is often located at the front or rear end. When the robot's laser is positioned forward, the lack of rear-facing laser data during charging and reverse operation can affect the accuracy of the robot's position adjustment. To compensate for this positioning error, a QR code representing the charging station's location is used to offset the preset position and assist the computer in position correction. Using this QR code image to assist the robot in correction effectively improves positioning accuracy and stability.

[0092] Based on this, take the following as an example, Figure 3-4 .

[0093] The present invention provides a position adjustment method based on QR code recognition, the specific process is as follows:

[0094] 1. The robot navigates to the charging point and adjusts its position: During operation, the robot uses laser positioning and navigation, which typically has a positioning error of less than ten centimeters. Therefore, when the robot reaches the charging adjustment position, it stops and enters the posture adjustment state.

[0095] 2. Preset photo capture of the QR code location: During the deployment phase, when entering the robot charging point information, rotate the robot's forward direction and the charging pile vertically, and simultaneously aim the camera at the center of the QR code image to capture a template image of the QR code location. Then, obtain the current robot posture status and parameters such as the gimbal camera angle and magnification.

[0096] 3. Calculate the positional offset between the actual QR code detection and the preset standard QR code image: When the robot returns to the charging point, read the robot's posture and the gimbal camera angle and magnification parameters. Adjust the robot's posture and capture a QR code recognition image. Use a QR code detection algorithm to determine whether a QR code exists in the image (a traditional QR code detection method). Simultaneously, calculate the affine transformation matrix based on a key point matching algorithm to obtain information such as the QR code's positional offset and rotation angle. Key point matching algorithms can use traditional SIFT / SURF or deep neural network matching methods (superglue).

[0097] 4. Based on the preset calibration values, the pixel offsets of the QR code in the image are converted to the robot's offset position: 1) Preset calibration method: In the charging position, the robot moves horizontally multiple times and records the corresponding robot position offsets and the pixel offsets of the QR code in the captured image. 2) Based on the data set [(d1, d_pixel1), (d2, d_pixel2), ...] consisting of multiple calibrated robot horizontal displacements and pixel offsets of the QR code in the captured image, the weighted ratio of the robot's position and the QR code image pixel offsets is calculated:

[0098]

[0099] 5. Correct the robot's position offset by capturing the QR code position in multiple images. In each iteration, the QR code detection algorithm determines whether the QR code exists in the image. The key point matching algorithm calculates the affine transformation matrix to obtain the offset information for the QR code position. This offset information and the weighted scale are used to calculate the distance and time required for the robot to adjust its position.

[0100] 6. When the position error of the QR code in the image is less than a certain threshold or greater than the number of times the image is taken, the robot stops adjusting and moves backwards into the charging station.

[0101] Generally speaking, accurate positioning adjustment methods are required before entering the charging state. This typically involves using rear-mounted laser point cloud data, reducing the adjustment step size, and adjusting the robot's angle and position offset. However, the robot's laser is often located at the front or rear end. When the robot's laser is positioned forward, the lack of rear-mounted laser data during charging and reverse operation can affect the accuracy of the robot's position adjustment. To compensate for this positioning error, a QR code representing the charging station's location is used to offset the preset position and assist the computer in position correction. Using this QR code image to assist the robot in correction effectively improves positioning accuracy and stability.

[0102] like Figure 5 As shown, an embodiment of the present invention further provides a computer device, including a processor 51 and a memory 52 for storing a computer program that can be run on the processor, wherein the processor is used to implement the method described above when running the computer program.

[0103] In some embodiments, the memory 52 in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 52 of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0104] The processor 51 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits or software instructions in the processor 51. The processor 51 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in memory 52. ​​The processor 51 reads the information in memory 52 and, in conjunction with its hardware, completes the steps of the above method.

[0105] In some embodiments, the embodiments described herein may be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or a combination thereof.

[0106] For software implementation, the techniques described herein can be implemented by modules (e.g., procedures, functions, etc.) that perform the functions described herein. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0107] Another embodiment of the present invention provides a computer storage medium, which stores an executable program. When the executable program is executed by the processor 51, the steps applied to the method can be implemented. For example, Figure 1 One or more of the methods shown.

[0108] In some embodiments, the computer storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., various media that can store program codes.

[0109] It should be noted that the technical solutions described in the embodiments of the present invention can be arbitrarily combined without conflict.

[0110] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A position adjustment method based on QR code recognition, characterized in that: The method comprises: S11: Use laser positioning navigation to navigate the robot to the adjusted position of the charging point; S12: Controlling the robot to move left and right at the adjustment position and recording the position offset of the robot, and using a camera to capture a real picture with a QR code, wherein the recorded position offset of the robot is a first position offset; S13: Calculating a position offset between the QR code in the actual image and the QR code in the standard image based on the actual image and the standard image, wherein the calculated position offset is a second position offset, wherein the standard image is a picture taken when the robot is facing the charging pile; S14: Calculating a deviation weight ratio between the first position offset and the second position offset according to the first position offset and the second position offset; S15: Calculate the distance that the robot needs to move laterally according to the second position offset and the deviation weight ratio, and then adjust the position of the robot to control the robot to retreat into the charging pile.

2. The method according to claim 1, characterized in that The method of using a camera to take a real picture with a QR code includes: Use the camera to take real-time pictures; Determine whether the real picture contains a QR code by using a QR code detection algorithm; If the judgment result is yes, execute step S13; If the judgment result is no, then continue to execute step S12.

3. The method according to claim 1, characterized in that The controlling robot to move left and right at the adjustment position and recording the position offset of the robot, and using a camera to take a real picture with a QR code includes: Control the robot to move left and right multiple times at the adjustment position, and record the first position offset of each left and right movement of the robot; The camera is controlled to take a plurality of the real-shot pictures, wherein the number of left and right lateral movements of the robot and the number of the real-shot pictures taken are in a one-to-one correspondence.

4. The method according to claim 3, characterized in that The calculating, based on the actual picture and the standard picture, a position offset between the QR code in the actual picture and the QR code in the standard picture includes: According to the key point matching algorithm, the second position offset between the QR code in each of the real pictures and the QR code in the standard picture is calculated.

5. The method according to claim 4, characterized in that The calculating, based on the first position offset and the second position offset, a deviation weight ratio between the two, includes: A two-dimensional array is formed based on a plurality of first position offsets and a corresponding plurality of second position offsets, and a deviation weight ratio of the first position offset to the second position offset is calculated.

6. The method according to claim 1, characterized in that The method of adjusting the position of the robot and controlling the robot to retreat into the charging station includes: After executing step S15, if the position offset between the QR code in the actual picture and the QR code in the standard picture is less than threshold A or the number of times the actual picture is taken is greater than threshold B, the robot stops adjusting, and then the robot retreats into the charging pile, otherwise, returns to step S12.

7. The method according to claim 4, characterized in that: The key point matching algorithm is a deep neural network matching method.

8. A position adjustment device based on QR code recognition, characterized in that: include: A navigation module, used to navigate the robot to the adjusted position of the charging point using a laser positioning navigation method; a control module, configured to control the robot to move left and right at the adjustment position and record a position offset of the robot, and use a camera to capture a real picture with a QR code, wherein the recorded position offset of the robot is a first position offset; a first calculation module, configured to calculate, based on the actual image and the standard image, a position offset between the QR code in the actual image and the QR code in the standard image, wherein the calculated position offset is a second position offset, wherein the standard image is a picture taken when the robot is facing the charging pile; A second calculation module is configured to calculate a deviation weight ratio between the first position offset and the second position offset according to the first position offset and the second position offset; The third calculation module calculates the distance that the robot needs to move laterally according to the second position offset and the deviation weight ratio, and then adjusts the position of the robot to control the robot to retreat into the charging pile.

9. A computer device, characterized in that: include: A processor and a memory for storing a computer program that can be run on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when running the computer program.

10. A computer storage medium, characterized in that An executable program is stored, and when the executable program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images