A method and system for automatic recharging of a robot

Abstract

The present application discloses a method and system for automatic recharging of a robot, and relates to the field of robot technology. The method includes: S1, when the robot reaches a preset recharging point, the current posture of the robot is obtained, and the first score of the current posture of the robot is calculated; S2, whether the first score of the robot exceeds the first threshold is determined, and when the first score exceeds the first threshold, step S3 is executed; S3, based on the geometric shape of the charging pile, the charging pile is identified, and the posture of the identified charging pile is compared with the pre-marked charging pile posture. If the posture of the identified charging pile and the pre-marked charging pile posture meet the first condition, the identified charging pile is used as the target charging pile, and step S4 is executed; S4, the robot recharges and docks with the target charging pile, and during the recharge docking process, the robot continuously updates the posture of the target charging pile used for recharge docking. The method and system for automatic recharging of the robot of the present application are suitable for automatic recharging of the robot.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a method and system for automatic recharging of a robot. Background Art

[0002] The current automatic recharging of indoor service robots is easily caused by misidentification of charging piles, which leads to failure of automatic recharging due to the limitation of the recognition method of charging piles. In addition, when the service robots on the market are arranged on site, they require that the charging piles must be arranged at a greater than certain interval (for example, 1.5 meters). This will waste a lot of space when arranging on-site service robots, and more robots cannot be arranged in a relatively small site. Summary of the invention

[0003] The technical problem to be solved by this application is: when multiple charging piles are densely arranged on the site, how can the robot accurately identify the designated charging pile and complete automatic recharging.

[0004] The technical solution adopted by this application to solve its technical problem is:

[0005] In a first aspect, the present application provides a method for automatic recharging of a robot, the method comprising the following steps:

[0006] S1, when the robot reaches the preset recharging point, obtain the current posture of the robot and calculate the first score of the current posture of the robot;

[0007] S2, determining whether the first score of the current posture of the robot exceeds a first threshold, and when the first score exceeds the first threshold, executing step S3;

[0008] S3, based on the geometric shape of the charging pile, identify the charging pile, compare the posture of the identified charging pile with the posture of the charging pile marked in advance, if the posture of the identified charging pile and the posture of the charging pile marked in advance meet the first condition, then the identified charging pile is used as the target charging pile, and step S4 is executed;

[0009] S4, the robot performs recharging docking with the target charging pile. During the recharging docking process, the robot continuously updates the position and posture of the target charging pile used for recharging docking.

[0010] Based on the first aspect, further, the above-mentioned determining whether the first score of the current posture of the robot exceeds the first threshold value also includes:

[0011] When the first score does not exceed the first threshold, repositioning the robot is performed.

[0012] Based on the first aspect, further, the above-mentioned repositioning of the robot includes the following steps:

[0013] Based on the current posture of the robot, within a first preset range of the robot, the posture of the robot is searched by a first distance search accuracy and a first angle search accuracy to obtain a plurality of candidate postures of the robot;

[0014] Calculate the third scores of all candidate postures of the robot, obtain the posture with the highest third score among all candidate postures of the robot, and use the third score of the posture as the second score;

[0015] Determine whether the second score exceeds a second threshold. When the second score exceeds the second threshold, correct the current posture of the robot to the posture with the third highest score among all candidate postures, and execute step S3.

[0016] Based on the first aspect, further, the specific formula for calculating the first score of the current posture of the robot is:

[0017] ;

[0018] in, is the first score of the robot’s current position, It is the number of laser points contained in the laser point cloud of the laser radar ranging information corresponding to the current posture of the robot; It is the first point cloud in the laser radar ranging information corresponding to the robot's current posture. The score of laser points; Obtained by the following formula:

[0019] ;

[0020] in, is the noise level parameter of the lidar sensor; It is the first point cloud in the laser radar ranging information corresponding to the robot's current posture. The distance between a laser point and the nearest obstacle in the global map, is a natural constant.

[0021] Based on the first aspect, further, the above-mentioned first condition is: the Euclidean distance between the identified posture of the charging pile and the pre-marked posture of the charging pile is less than the first Euclidean distance and the angle difference between the identified posture of the charging pile and the pre-marked posture of the charging pile is less than the first angle difference.

[0022] Based on the first aspect, further, the specific method for identifying the charging pile based on the geometric shape of the charging pile includes:

[0023] S31, fitting multiple line segments by using the laser point cloud and the least square method, and determining whether there are two or more line segments with a first length among the multiple fitted line segments, and if so, executing step S32;

[0024] S32, determining whether there are two line segments whose included angles are the first angle among the two or more fitted line segments whose lengths are the first length, if so, it is considered that the charging pile is successfully identified; otherwise, it is considered that the identification of the charging pile fails, and the search for the charging pile continues.

[0025] Based on the first aspect, further, before comparing the identified posture of the charging pile with the pre-marked posture of the charging pile, the method further includes a step of performing a coordinate system transformation on the identified posture of the charging pile; the specific method of performing the coordinate system transformation is as follows:

[0026] ;

[0027] in, is the recognized position and posture of the charging pile in the robot coordinate system; is the robot’s position in the world coordinate system; It is the recognized position and posture of the charging pile in the world coordinate system.

[0028] Based on the first aspect, further, in the above step S4, the specific method for the robot to continuously update the position and posture of the target charging pile for recharging and docking is:

[0029] At every first time interval, the robot obtains the position and posture of the target charging pile; compares the position and posture of the target charging pile currently obtained with the position and posture of the target charging pile obtained last time; if the position and posture of the target charging pile currently obtained and the position and posture of the target charging pile obtained last time meet the second condition, the position and posture of the target charging pile used for recharging and docking are updated to the position and posture of the target charging pile currently obtained; otherwise, the position and posture of the target charging pile used for recharging and docking are not updated.

[0030] Based on the first aspect, further, in the above step S4, the specific method for the robot to continuously update the position and posture of the target charging pile for recharging and docking is:

[0031] At every second time interval, the robot obtains the position and posture of the target charging pile; compares the position and posture of the target charging pile currently obtained with the position and posture of the target charging pile used for recharging and docking; if the position and posture of the target charging pile currently obtained and the position and posture of the target charging pile used for recharging and docking meet the third condition, the position and posture of the target charging pile used for recharging and docking are updated to the position and posture of the target charging pile currently obtained; otherwise, the position and posture of the target charging pile used for recharging and docking are not updated.

[0032] In a second aspect, the present application also provides a robot automatic recharging system, the system comprising: a score calculation module, a score judgment module, a posture comparison module and a posture update module, wherein:

[0033] A score calculation module is used to obtain the current posture of the robot and calculate the first score of the current posture of the robot when the robot reaches the preset recharging point;

[0034] A score judgment module, used to judge whether a first score of the current posture of the robot exceeds a first threshold, and when the first score exceeds the first threshold, execute the posture comparison module;

[0035] A posture comparison module is used to identify the charging pile based on the geometric shape of the charging pile, and compare the posture of the identified charging pile with the posture of the pre-marked charging pile. If the posture of the identified charging pile and the posture of the pre-marked charging pile meet the first condition, the identified charging pile is used as the target charging pile, and the posture update module is executed;

[0036] The posture update module is used for the robot to recharge and dock with the target charging pile. During the recharge and docking process, the robot continuously updates the posture of the target charging pile used for recharge and docking.

[0037] In a third aspect, the present application also provides an electronic device, comprising a memory and a processor; the memory is used to store one or more programs; when one or more programs are executed by the processor, a method as described in any one of the first aspects above is implemented.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method according to any one of the above-mentioned first aspects is implemented.

[0039] The beneficial effects of this application are:

[0040] When multiple charging piles are densely arranged on site, the robot can accurately identify the designated charging pile and complete automatic recharging. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flowchart of a method for automatic recharging of a robot provided in an embodiment of the present application.

[0042] Figure 2 A functional block diagram of the robot automatic recharging system provided in an embodiment of the present application.

[0043] Figure 3 A schematic diagram of the geometric shape of the charging pile provided in an embodiment of the present application.

[0044] Figure 4A structural block diagram of an electronic device provided in an embodiment of the present application.

[0045] The reference numerals are: 100, score calculation module; 200, score judgment module; 300, posture comparison module; 400, posture update module; 101, memory; 102, processor; 103, communication interface. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0047] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0048] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0049] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0050] In the description of the embodiments of the present application, "plurality" means at least 2.

[0051] In the case where multiple charging piles are densely arranged on the site, the robot is prone to misidentifying the target charging pile. For example: the robot's target charging pile is A, but because the site is densely arranged with multiple charging piles, the interval between one charging pile and another is relatively narrow, so the robot will identify charging pile B as the target charging pile to perform the recharging task, resulting in the robot with charging pile B as the target charging pile being unable to recharge and dock, causing chaos in the robot's recharging order. To this end, the present application provides a method and system that can accurately identify the target charging pile and complete automatic recharging in the scenario where multiple charging piles are densely arranged, which can effectively ensure that each robot accurately identifies its respective target charging pile and completes automatic recharging.

[0052] First, as Figure 1 As shown, an embodiment of the present application provides a method for automatic recharging of a robot, the method comprising the following steps:

[0053] S1, when the robot reaches the preset recharging point, obtain the current posture of the robot and calculate the first score of the current posture of the robot;

[0054] S2, determining whether the first score of the current posture of the robot exceeds a first threshold, and when the first score exceeds the first threshold, executing step S3;

[0055] S3, based on the geometric shape of the charging pile, identify the charging pile, compare the posture of the identified charging pile with the posture of the charging pile marked in advance, if the posture of the identified charging pile and the posture of the charging pile marked in advance meet the first condition, then the identified charging pile is used as the target charging pile, and step S4 is executed;

[0056] S4, the robot performs recharging docking with the target charging pile. During the recharging docking process, the robot continuously updates the position and posture of the target charging pile used for recharging docking.

[0057] Indoor service robots use 2D lidar to obtain 360° ranging information.

[0058] In one embodiment of the present application, determining whether the first score of the current posture of the robot exceeds the first threshold value further includes:

[0059] When the first score does not exceed the first threshold, repositioning the robot is performed.

[0060] In one embodiment of the present application, performing repositioning on the robot comprises the following steps:

[0061] Based on the current posture of the robot, within a first preset range of the robot, the posture of the robot is searched by a first distance search accuracy and a first angle search accuracy to obtain a plurality of candidate postures of the robot;

[0062] Calculating the third scores of all candidate postures of the robot, obtaining the posture with the highest third score among all candidate postures of the robot, and using the third score of the posture as the second score;

[0063] Determine whether the second score exceeds a second threshold. When the second score exceeds the second threshold, correct the current posture of the robot to the posture with the third highest score among all candidate postures, and execute step S3.

[0064] The first preset range is 4 meters around the robot.

[0065] The first distance search accuracy is 0.05 meters.

[0066] The first angle search accuracy is 10°.

[0067] The value of the first threshold may be the same as the value of the second threshold.

[0068] When re-positioning, according to the current position of the robot, with a distance search accuracy of 0.05 meters, 80 80 grids, and then rotate the robot according to the 10° angle search accuracy, so there will be a total of 80 80 36 candidate postures of the robot; calculate the third score of each candidate posture, find the posture with the highest third score, then it is considered that the laser data of this posture has the highest overlap with the map, and the third score of this candidate posture is used as the second score; if the second score exceeds the set second threshold, the current posture of the robot is corrected to the posture with the highest third score among all candidate postures, the robot is repositioned successfully, and step S3 is executed.

[0069] In one embodiment of the present application, the specific formula for calculating the third score of each candidate posture of the robot is:

[0070] ;

[0071] in, is the third score of a candidate pose of the robot, is the number of laser points contained in the laser point cloud in the ranging information of the laser radar corresponding to the candidate pose; is the first laser point cloud contained in the laser radar ranging information corresponding to the candidate pose The score of laser points; Obtained by the following formula:

[0072] ;

[0073] in, is the noise level parameter of the lidar sensor; is the first laser point cloud contained in the laser radar ranging information corresponding to the candidate pose The distance between a laser point and the nearest obstacle in the global map, is a natural constant.

[0074] In one embodiment of the present application, determining whether the second score exceeds the second threshold further includes:

[0075] When the second score does not exceed the second threshold, it is determined that the robot repositioning has failed, the robot positioning is confirmed to be lost, and the recharging task is terminated.

[0076] In one embodiment of the present application, the specific formula for calculating the first score of the current posture of the robot is:

[0077] ;

[0078] in, is the first score of the robot’s current position, It is the number of laser points contained in the laser point cloud of the laser radar ranging information corresponding to the current posture of the robot; It is the first point cloud in the laser radar ranging information corresponding to the robot's current posture. The score of laser points; Obtained by the following formula:

[0079] ;

[0080] in, is the noise level parameter of the lidar sensor; It is the first point cloud in the laser radar ranging information corresponding to the robot's current posture. The distance between a laser point and the nearest obstacle in the global map, is a natural constant.

[0081] In one embodiment of the present application, the first condition is that the Euclidean distance between the identified posture of the charging pile and the pre-marked posture of the charging pile is less than the first Euclidean distance and the angular difference between the identified posture of the charging pile and the pre-marked posture of the charging pile is less than the first angular difference.

[0082] The first Euclidean distance is 0.05 meters. The first angular difference is 6 degrees.

[0083] In one embodiment of the present application, comparing the identified posture of the charging pile with the pre-marked posture of the charging pile further includes:

[0084] If the position and posture of the identified charging pile and the position and posture of the pre-marked charging pile do not satisfy the first condition, it is determined that the search for the pre-marked charging pile has failed, and the search for the pre-marked charging pile continues.

[0085] like Figure 3 As shown, in one embodiment of the present application, the geometric shape of the charging pile is an inner triangle. Based on the geometric shape of the charging pile, the specific method for identifying the charging pile includes:

[0086] S31, fitting multiple line segments by using the laser point cloud and the least square method, and determining whether there are two or more line segments with a first length among the multiple fitted line segments, and if so, executing step S32;

[0087] S32, determining whether there are two line segments whose included angles are the first angle among the two or more fitted line segments whose lengths are the first length, if so, it is considered that the charging pile is successfully identified; otherwise, it is considered that the identification of the charging pile fails, and the search for the charging pile continues.

[0088] In the description of the present application, "two or more" means at least two.

[0089] The first length is 0.25 meters.

[0090] The first angle is 120°.

[0091] In one embodiment of the present application, the pre-marked charging pile posture is the posture in the world coordinate system, and the recognized charging pile posture is the posture in the robot coordinate system. In this case, before comparing the recognized charging pile posture with the pre-marked charging pile posture, a step of performing a coordinate system transformation on the recognized charging pile posture is also included; the specific method of performing the coordinate system transformation is as follows:

[0092] ;

[0093] in, is the recognized position and posture of the charging pile in the robot coordinate system; is the robot’s position in the world coordinate system; It is the recognized position and posture of the charging pile in the world coordinate system.

[0094] In this embodiment, comparing the recognized posture of the charging pile with the pre-marked posture of the charging pile refers to comparing the recognized posture of the charging pile in the world coordinate system with the pre-marked posture of the charging pile in the world coordinate system.

[0095] In one embodiment of the present application, the specific method for the robot to continuously update the posture of the target charging pile for recharging and docking in step S4 is: at every first time interval, the robot obtains the posture of the target charging pile; compares the posture of the currently obtained target charging pile with the posture of the target charging pile obtained last time, and if the posture of the currently obtained target charging pile and the posture of the target charging pile obtained last time meet the second condition, then the posture of the target charging pile for recharging and docking is updated to the posture of the currently obtained target charging pile, otherwise the posture of the target charging pile for recharging and docking is not updated.

[0096] In another embodiment of the present application, the specific method for the robot to continuously update the posture of the target charging pile for recharging and docking in step S4 is: at every second time interval, the robot obtains the posture of the target charging pile; compares the posture of the currently obtained target charging pile with the posture of the target charging pile for recharging and docking, if the posture of the currently obtained target charging pile and the posture of the target charging pile for recharging and docking meet the third condition, then the posture of the target charging pile for recharging and docking is updated to the posture of the currently obtained target charging pile, otherwise the posture of the target charging pile for recharging and docking is not updated.

[0097] The first time length is 1 second.

[0098] The second condition is that the Euclidean distance between the current target charging pile's posture and the last target charging pile's posture is less than the second Euclidean distance and the angle difference between the current target charging pile's posture and the last target charging pile's posture is less than the second angle difference.

[0099] The second Euclidean distance is 0.05 meters.

[0100] The second angular difference is 3°.

[0101] The second time length is 1 second.

[0102] The third condition is that the Euclidean distance between the currently obtained position of the target charging pile and the position of the target charging pile for recharging and docking is less than the third Euclidean distance and the angular difference between the currently obtained position of the target charging pile and the position of the target charging pile for recharging and docking is less than the third angular difference.

[0103] The third Euclidean distance is 0.05 meters.

[0104] The third angular difference is 3°.

[0105] In one embodiment of the present application, if there is a special situation where the laser radar cannot see the charging pile, the relative position and posture of the robot with respect to the target charging pile can be calculated with the help of the odometer coordinate system.

[0106] Second, as Figure 2 As shown, the embodiment of the present application also provides a system for automatic recharging of a robot, the system comprising: a score calculation module 100, a score judgment module 200, a posture comparison module 300 and a posture update module 400, wherein:

[0107] The score calculation module 100 is used to obtain the current posture of the robot and calculate the first score of the current posture of the robot when the robot reaches the preset recharging point;

[0108] The score judgment module 200 is used to judge whether the first score of the current posture of the robot exceeds the first threshold, and when the first score exceeds the first threshold, the posture comparison module 300 is executed;

[0109] A posture comparison module 300 is used to identify the charging pile based on the geometric shape of the charging pile, and compare the posture of the identified charging pile with the posture of the charging pile marked in advance. If the posture of the identified charging pile and the posture of the charging pile marked in advance meet the first condition, the identified charging pile is used as the target charging pile, and the posture update module 400 is executed;

[0110] The posture update module 400 is used for the robot to perform recharging docking with a target charging pile. During the recharging docking process, the robot continuously updates the posture of the target charging pile used for recharging docking.

[0111] Thirdly, Figure 4 As shown, an embodiment of the present application also provides an electronic device, which includes a memory 101 and a processor 102; the memory 101 is used to store one or more programs; when one or more programs are executed by the processor 102, a method as described in any one of the first aspects above is implemented.

[0112] A communication interface 103 may also be included. The memory 101, the processor 102 and the communication interface 103 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these elements can be electrically connected to each other through one or more communication buses or signal lines. The memory 101 can be used to store software programs and modules, and the processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101. The communication interface 103 can be used to communicate signaling or data with other node devices.

[0113] Among them, the memory 101 can be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc.

[0114] The processor 102 may be an integrated circuit chip with signal processing capability. The processor 102 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0115] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by the processor 102, a method as described in any one of the first aspects above is implemented. If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or part of the technical solution that contributes to the prior art or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk.

[0116] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0117] It will be apparent to those skilled in the art that the present application is not limited to the details of the exemplary embodiments described above, and that the present application can be implemented in other specific forms without departing from the spirit or essential features of the present application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims be included in the present application. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for automatic recharging of a robot, characterized in that: The following steps are involved: S1, when the robot reaches the preset recharging point, obtain the current posture of the robot and calculate the first score of the current posture of the robot; S2, determining whether the first score of the current posture of the robot exceeds a first threshold, and when the first score exceeds the first threshold, executing step S3; S3, based on the geometric shape of the charging pile, identify the charging pile, compare the posture of the identified charging pile with the posture of the charging pile marked in advance, if the posture of the identified charging pile and the posture of the charging pile marked in advance meet the first condition, then the identified charging pile is used as the target charging pile, and step S4 is executed; S4, the robot performs recharging docking with the target charging pile. During the recharging docking process, the robot continuously updates the position and posture of the target charging pile for recharging docking; The specific formula for calculating the first score of the current posture of the robot is: ； in, is the first score of the robot’s current position, It is the number of laser points contained in the laser point cloud of the laser radar ranging information corresponding to the current posture of the robot; It is the first point cloud in the laser radar ranging information corresponding to the robot's current posture. The score of laser points; It is obtained by the following formula: ； in, is the noise level parameter of the lidar sensor; It is the first point cloud in the laser radar ranging information corresponding to the robot's current posture. The distance between a laser point and the nearest obstacle in the global map, is a natural constant; The specific method for identifying the charging pile based on the geometric shape of the charging pile includes: S31, fitting multiple line segments by using the laser point cloud and the least square method, and determining whether there are two or more line segments with a first length among the multiple fitted line segments, and if so, executing step S32; S32, determining whether there are two line segments whose included angles are the first angle among the two or more fitted line segments whose lengths are the first length, if so, it is considered that the charging pile is successfully identified; otherwise, it is considered that the charging pile is failed to be identified, and the search for the charging pile continues; The first condition is that the Euclidean distance between the recognized posture of the charging pile and the pre-marked posture of the charging pile is less than the first Euclidean distance and the angular difference between the recognized posture of the charging pile and the pre-marked posture of the charging pile is less than the first angular difference.

2. The method for automatic robot recharging according to claim 1, characterized in that: The step of determining whether the first score of the current posture of the robot exceeds a first threshold value further includes: When the first score does not exceed the first threshold, repositioning the robot is performed.

3. The method for automatic robot recharging according to claim 2, characterized in that: The repositioning of the robot comprises the following steps: Based on the current posture of the robot, within a first preset range of the robot, the posture of the robot is searched by a first distance search accuracy and a first angle search accuracy to obtain a plurality of candidate postures of the robot; Calculate the third scores of all candidate postures of the robot, obtain the posture with the highest third score among all candidate postures of the robot, and use the third score of the posture as the second score; Determine whether the second score exceeds a second threshold. When the second score exceeds the second threshold, correct the current posture of the robot to the posture with the third highest score among all candidate postures, and execute step S3.

4. The method for automatic robot recharging according to claim 1, characterized in that: Before comparing the identified posture of the charging pile with the pre-marked posture of the charging pile, the method further includes a step of performing a coordinate system transformation on the identified posture of the charging pile; the specific method of performing the coordinate system transformation is as follows: ； in, is the recognized position and posture of the charging pile in the robot coordinate system; is the robot’s position in the world coordinate system; It is the recognized position and posture of the charging pile in the world coordinate system.

5. The method for automatic robot recharging according to claim 1, characterized in that: The specific method for the robot to continuously update the position and posture of the target charging pile for recharging and docking in step S4 is: At every first time interval, the robot obtains the position and posture of the target charging pile; compares the position and posture of the target charging pile currently obtained with the position and posture of the target charging pile obtained last time; if the position and posture of the target charging pile currently obtained and the position and posture of the target charging pile obtained last time meet the second condition, the position and posture of the target charging pile used for recharging and docking are updated to the position and posture of the target charging pile currently obtained; otherwise, the position and posture of the target charging pile used for recharging and docking are not updated.

6. The method for automatic robot recharging according to claim 1, characterized in that: The specific method for the robot to continuously update the position and posture of the target charging pile for recharging and docking in step S4 is: At every second time interval, the robot obtains the position and posture of the target charging pile; compares the position and posture of the target charging pile currently obtained with the position and posture of the target charging pile used for recharging and docking; if the position and posture of the target charging pile currently obtained and the position and posture of the target charging pile used for recharging and docking meet the third condition, the position and posture of the target charging pile used for recharging and docking are updated to the position and posture of the target charging pile currently obtained; otherwise, the position and posture of the target charging pile used for recharging and docking are not updated.

7. A robot automatic recharging system, characterized in that: include: Score calculation module, score judgment module, posture comparison module and posture update module, among which: A score calculation module is used to obtain the current posture of the robot and calculate the first score of the current posture of the robot when the robot reaches the preset recharging point; A score judgment module, used to judge whether a first score of the current posture of the robot exceeds a first threshold, and when the first score exceeds the first threshold, execute the posture comparison module; A posture comparison module is used to identify the charging pile based on the geometric shape of the charging pile, and compare the posture of the identified charging pile with the posture of the pre-marked charging pile. If the posture of the identified charging pile and the posture of the pre-marked charging pile meet the first condition, the identified charging pile is used as the target charging pile, and the posture update module is executed; The posture update module is used for the robot to recharge and dock with the target charging pile. During the recharge and docking process, the robot continuously updates the posture of the target charging pile for recharge and docking; The specific formula for calculating the first score of the current posture of the robot is: ； in, is the first score of the robot’s current position, It is the number of laser points contained in the laser point cloud of the laser radar ranging information corresponding to the current posture of the robot; It is the first point cloud in the laser radar ranging information corresponding to the robot's current posture. The score of laser points; It is obtained by the following formula: ； in, is the noise level parameter of the lidar sensor; It is the first point cloud in the laser radar ranging information corresponding to the robot's current posture. The distance between a laser point and the nearest obstacle in the global map, is a natural constant; The identifying of the charging pile based on the geometric shape of the charging pile specifically includes: S31, fitting multiple line segments by using the laser point cloud and the least square method, and determining whether there are two or more line segments with a first length among the multiple fitted line segments, and if so, executing step S32; S32, determining whether there are two line segments whose included angles are the first angle among the two or more fitted line segments whose lengths are the first length, if so, it is considered that the charging pile is successfully identified; otherwise, it is considered that the charging pile is failed to be identified, and the search for the charging pile continues; The first condition is that the Euclidean distance between the recognized posture of the charging pile and the pre-marked posture of the charging pile is less than the first Euclidean distance and the angular difference between the recognized posture of the charging pile and the pre-marked posture of the charging pile is less than the first angular difference.

Images