Robot charging method and system

Abstract

The present invention discloses a method and system for charging a pile by a robot. The method for charging a pile includes the following steps: recording the laser point cloud and the first position when the robot is facing the charging pile, the laser point cloud being the target point cloud; calculating the coordinates and orientation at the first preset distance position directly behind the robot according to the real-time position of the robot, and obtaining the second position; using the point cloud at the second position of the robot as the input point cloud, and performing the nearest neighbor search with the target point cloud and the input point cloud; performing point cloud registration with the input point cloud and the target point cloud to obtain the third position after registration, and continuously updating the input point cloud until the absolute value of the deviation between the third position after registration and the first position is less than the second preset distance. The method for charging a pile by a robot of the present invention can realize high-precision charging of the pile, has a stronger tolerance for the environment in which the charging pile is deployed, and does not require additional hardware equipment, effectively saving hardware costs.

Description

Technical Field

[0001] The present application relates to the technical field of mobile robots, and more specifically, to a method and system for charging a charging pile by a robot. Background Art

[0002] At present, existing robots usually use infrared transmitters and infrared receivers to determine the relative position of the robot to the charging pile, and use the relative position to control the robot to charge the pile. Alternatively, existing robots use visual cameras to identify the QR code on the charging pile, and use the position of the identified QR code in the camera to find the position of the robot relative to the charging pile, and use its relative position to control the robot to charge the pile.

[0003] The above-mentioned charging methods of the robot in the prior art all have certain defects. The first solution is suitable for environments where the electromagnetic interference at the charging pile is relatively small, and there is a problem of interference with infrared signals. In addition, it is necessary to install an infrared transmitter on the charging pile and an infrared receiver on the robot, which leads to an increase in hardware costs. For outdoor robots, one more hardware device needs to be installed, which poses a risk of hardware instability, resulting in failure of robot charging due to poor charging accuracy. The second solution is suitable for indoor environments, and there will also be redundant hardware equipment that needs to be installed. At the same time, the QR code is easily contaminated and easily worn out after long-term use, which increases the probability of robot charging failure. Summary of the invention

[0004] One object of the present invention is to provide a new technical solution for a charging method of a robot, which can at least solve the problems of high cost, poor charging accuracy, and easy charging failure in the prior art.

[0005] According to a first aspect of the present invention, a method for charging a charging pile by a robot is provided, comprising the following steps:

[0006] Recording the laser point cloud and the first position of the robot when it is facing the charging pile, wherein the laser point cloud is the target point cloud;

[0007] Calculate the coordinates and orientation of a position at a first preset distance directly behind the robot according to the real-time position of the robot to obtain a second position;

[0008] Based on the point cloud at the second position of the robot as the input point cloud, the target point cloud and the input point cloud are used for nearest neighbor search;

[0009] The input point cloud and the target point cloud are used to perform point cloud registration to obtain a third position after registration, and the input point cloud is continuously updated until the absolute value of the deviation between the third position after registration and the first position is less than a second preset distance.

[0010] Optionally, the step of performing nearest neighbor search on the target point cloud and the input point cloud includes:

[0011] All points of the input point cloud are traversed, points in the input point cloud that are greater than a preset multiple of the first preset distance are eliminated, and points in the input point cloud that are less than or equal to a preset multiple of the first preset distance are retained.

[0012] Optionally, the step of continuously updating the input point cloud comprises:

[0013] The robot is controlled to move toward the charging pile according to the relative position deviation between the second position and the first position, and the input point cloud is continuously updated during the moving process.

[0014] Optionally, the laser point cloud is a laser radar point cloud, and the laser point cloud includes three-dimensional coordinates and laser reflection intensity.

[0015] Optionally, the first preset distance is 0.2m-0.8m, the preset multiple is 1-2, and the second preset distance is 3cm-8cm.

[0016] According to a second aspect of the present invention, a robot charging system is provided, which is applied to the robot charging method described in the above embodiment. The charging system comprises:

[0017] A recording module, used to record the laser point cloud and the first position when the robot is facing the charging pile, wherein the laser point cloud is a target point cloud;

[0018] A calculation module, the calculation module is connected to the recording module, and the calculation module is used to calculate the coordinates and orientation of a position at a first preset distance from the rear of the robot, and obtain a second position, wherein the point cloud at the second position is the input point cloud;

[0019] A search module, the search module is connected to the calculation module, and the search module is used to perform a nearest neighbor search on the target point cloud and the input point cloud;

[0020] A registration module, the registration module is connected to the search module, and the registration module is used to perform point cloud registration on the input point cloud and the target point cloud;

[0021] An updating module, wherein the updating module is connected to the registration module, and the updating module is used to update the input point cloud.

[0022] Optionally, the search module includes: an elimination unit and a retention unit, the elimination unit and the retention unit are respectively connected to the calculation module, the elimination unit is used to eliminate points in the input point cloud that are greater than a preset multiple of the first preset distance, and the retention unit is used to retain points in the input point cloud that are less than or equal to a preset multiple of the first preset distance.

[0023] According to a third aspect of the present invention, there is provided a robot, comprising: a mobile chassis; a machine body, the machine body being arranged on the mobile chassis, the mobile chassis driving the machine body to be movable; and a laser radar, the laser radar being arranged in the machine body.

[0024] Optionally, the robot further includes: a processor and a memory, wherein computer program instructions are stored in the memory, wherein when the computer program instructions are executed by the processor, the processor executes the steps of the robot charging pile method in the above embodiment.

[0025] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the robot charging pile method in the above embodiment.

[0026] According to the robot charging pile method of the embodiment of the present invention, the robot's own laser point cloud is used to obtain the robot's real-time position, without the need for additional hardware equipment, thus saving hardware costs. In the charging pile method, the input point cloud is used to perform point cloud registration with the target point cloud, and the input point cloud is continuously updated. Through the registration between the point clouds, a position with higher accuracy can be obtained, thereby achieving high-precision charging pile. The charging pile method has a stronger tolerance for the deployment environment of the charging pile, and can perform high-precision charging piles in different scenarios such as indoors and outdoors, avoiding the risk of charging failure.

[0027] Other features and advantages of the present application will become apparent from the following detailed description of exemplary embodiments of the present application with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with the description, serve to explain the principles of the application.

[0029] Figure 1 is a flow chart of a method for charging a pile by a robot according to an embodiment of the present invention;

[0030] Figure 2 is a schematic diagram of a robot-to-pile charging system according to an embodiment of the present invention;

[0031] Figure 3 is a diagram showing the working principle of a robot according to an embodiment of the present invention.

[0032] Reference numerals:

[0033] Recording module 10;

[0034] Calculation module 20;

[0035] Search module 30; elimination unit 31; retention unit 32;

[0036] Registration module 40;

[0037] Update module 50;

[0038] Processor 201;

[0039] Memory 202; operating system 2021; application program 2022;

[0040] Network interface 203;

[0041] Input device 204;

[0042] Hard disk 205;

[0043] Display device 206. DETAILED DESCRIPTION

[0044] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application.

[0045] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0046] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0047] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0048] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0049] The following describes in detail the method for charging a pile with a robot according to an embodiment of the present invention with reference to the accompanying drawings.

[0050] like Figure 1 As shown, the robot charging method according to an embodiment of the present invention includes the following steps:

[0051] S1, record the laser point cloud and the first position of the robot when it faces the charging pile, and the laser point cloud is the target point cloud;

[0052] S2. Calculate the coordinates and orientation of a position at a first preset distance directly behind the robot according to the real-time position of the robot to obtain a second position;

[0053] S3, using the point cloud at the second position of the robot as the input point cloud, and performing nearest neighbor search on the target point cloud and the input point cloud;

[0054] S4. Perform point cloud registration with the input point cloud and the target point cloud to obtain a third position after registration, and continuously update the input point cloud until the absolute value of the deviation between the third position after registration and the first position is less than a second preset distance.

[0055] In other words, see Figure 1 In the robot charging method of an embodiment of the present invention, first, the robot can be placed on the charging pile, and the laser point cloud and the first position of the robot when it is placed on the charging pile are recorded, and the laser point cloud is the target point cloud. The real-time position of the robot is obtained by using the laser point cloud of the robot's built-in laser radar, without the need for additional hardware equipment, thus saving hardware costs. Then, based on the real-time position of the robot, the coordinates and orientation of the position at the first preset distance directly behind the robot are calculated to obtain the second position. When the robot needs to be charged, the robot is navigated to the second position. After arriving at this position, the target point cloud and the input point cloud are used for nearest neighbor search.

[0056] Finally, the input point cloud is used to align the target point cloud to obtain the third position after alignment, and the input point cloud is continuously updated until the absolute value of the deviation between the third position after alignment and the first position is less than the second preset distance, thus completing the high-precision charging of the robot. The present invention can obtain a position with higher accuracy through the alignment between point clouds, thereby achieving high-precision charging of the charging pile. In addition, the present invention has a strong tolerance for the environment in which the charging pile is deployed, does not require an environment with low infrared interference, and does not have the loss or pollution problem of the QR code like the QR code charging pile. The success rate of long-term charging is very high.

[0057] Therefore, according to the robot charging method of the embodiment of the present invention, the robot's own laser point cloud is used to obtain the robot's real-time position, without the need for additional hardware equipment, saving hardware costs. In the charging method, the input point cloud and the target point cloud are used for point cloud registration, and the input point cloud is continuously updated. Through the registration between the point clouds, a position with higher accuracy can be obtained, thereby achieving high-precision charging. The charging method has a stronger tolerance for the deployment environment of the charging pile, and can perform high-precision charging in different scenarios such as indoors and outdoors, avoiding the risk of charging failure.

[0058] In some specific embodiments of the present invention, the step of performing nearest neighbor search on the target point cloud and the input point cloud includes: traversing all points in the input point cloud, eliminating points in the input point cloud that are greater than a preset multiple of a first preset distance, and retaining points in the input point cloud that are less than or equal to a preset multiple of the first preset distance. The step of continuously updating the input point cloud includes: controlling the robot to move toward the charging pile according to the relative position deviation between the second position and the first position, and continuously updating the input point cloud during the moving process.

[0059] Among them, the laser point cloud is a laser radar point cloud (3D point cloud), which includes three-dimensional coordinates and laser reflection intensity. 3D laser radar itself is one of the necessary hardware for outdoor robot mapping, positioning and obstacle avoidance. No additional hardware equipment is required, saving costs. The 3D laser radar point cloud is a collection of massive points of target surface characteristics. The point cloud obtained according to the laser measurement principle includes three-dimensional coordinates (XYZ) and laser reflection intensity (Intensity). Point cloud registration obtains a rotation and translation transformation matrix, which represents the position transformation relationship between the two point clouds, that is, the source point cloud can be transformed to the position of the target point cloud through RT so that the two can overlap.

[0060] According to one embodiment of the present invention, the first preset distance is 0.2m-0.8m, the preset multiple is 1-2, and the second preset distance is 3cm-8cm.

[0061] That is to say, in the robot charging method of the present invention, see Figure 1 First, place the robot on the charging pile and record the 3D point cloud of the 3D laser radar at the current moment. Record the current real-time position (first position). Then, based on the real-time position of the robot, calculate the coordinates and orientation of the first preset distance directly behind the robot to obtain the second position. For example, the first preset distance is 0.5m.

[0062] When the robot needs to be charged, it first navigates to the second position. After arriving at the position, the laser point cloud is used as the target point cloud, and the point cloud at the current moment (the point cloud at the second position) is used as the input point cloud to perform the nearest neighbor search. Traverse all points in the input point cloud. When the distance between the nearest neighbor point of a point in the target point cloud exceeds 1.5 times the first preset distance, that is, greater than 0.75m, the point can be regarded as a dynamic point and removed from the input point cloud. Points with a nearest neighbor distance less than or equal to 1.5 times the first preset distance are retained. After removing the dynamic points, the input point cloud and the target point cloud are used for point cloud registration. The relative position is obtained by point cloud registration. At this time, the third position of the radar point cloud at the current moment to the previously recorded radar point cloud can be obtained. The input point cloud is updated, and the robot is controlled to move toward the charging pile according to the relative position deviation of the robot. For example, the y-axis deviation is positive 10cm at this time. At this time, the angular velocity can be controlled to reduce the y-axis deviation. As the robot moves forward, the input point cloud continues to be updated, and then the dynamic points of the point cloud at the current moment are eliminated, and the point cloud alignment continues, and the relative position is updated rollingly until the absolute value of the position deviation is less than 5cm or until the robot is charged, completing the robot's high-precision charging of the pile.

[0063] In summary, the robot charging method according to the embodiment of the present invention uses the robot's own laser point cloud to obtain the robot's real-time position, without the need for additional hardware equipment, saving hardware costs. In the charging method, the input point cloud and the target point cloud are used for point cloud registration, and the input point cloud is continuously updated. Through the registration between the point clouds, a position with higher accuracy can be obtained, thereby achieving high-precision charging. The charging method has a stronger tolerance for the deployment environment of the charging pile, and can perform high-precision charging in different scenarios such as indoors and outdoors, avoiding the risk of charging failure.

[0064] According to a second aspect of the present application, a robot charging pile system is provided, which is applied to the robot charging pile method in the above embodiment. The charging pile system includes a recording module 10, a calculation module 20, a search module 30, an alignment module 40 and an update module 50.

[0065] Specifically, see Figure 2 The recording module 10 is used to record the laser point cloud and the first position when the robot is facing the charging pile, wherein the laser point cloud is the target point cloud. The calculation module 20 is connected to the recording module 10, and the calculation module 20 is used to calculate the coordinates and orientation at the first preset distance position directly behind the robot, and obtain the second position, wherein the point cloud at the second position is the input point cloud. The search module 30 is connected to the calculation module 20, and the search module 30 is used to perform nearest neighbor search on the target point cloud and the input point cloud. The registration module 40 is connected to the search module 30, and the registration module 40 is used to perform point cloud registration on the input point cloud and the target point cloud. The update module 50 is connected to the registration module 40, and the update module 50 is used to update the input point cloud.

[0066] Among them, the search module 30 includes a removal unit 31 and a retention unit 32, and the removal unit 31 and the retention unit 32 are respectively connected to the calculation module 20. The removal unit 31 is used to remove points in the input point cloud that are greater than a preset multiple of the first preset distance, and the retention unit 32 is used to retain points in the input point cloud that are less than or equal to a preset multiple of the first preset distance.

[0067] The robot charging system of the embodiment of the present invention uses the robot's own laser point cloud to obtain the robot's real-time position, without the need for additional hardware equipment, saving hardware costs. In the charging method, the input point cloud is used to perform point cloud registration with the target point cloud, and the input point cloud is continuously updated. Through the registration between the point clouds, a position with higher accuracy can be obtained, thereby achieving high-precision charging. The charging method has a stronger tolerance for the deployment environment of the charging pile, and can perform high-precision charging in different scenarios such as indoors and outdoors, avoiding the risk of charging failure.

[0068] According to a third aspect of the present invention, there is provided a robot comprising a mobile chassis, a machine body and a laser radar.

[0069] Specifically, the machine body is arranged on a mobile chassis, and the mobile chassis drives the machine body to move. The laser radar is arranged in the machine body. The laser radar is a 3D laser radar. The mobile chassis can obtain the real-time position of the current robot in the map and can navigate to any coordinate point in the map that is not occupied by obstacles.

[0070] The robot of the present invention has its own laser radar to obtain the real-time position of the robot, and no additional hardware equipment is required, which saves hardware costs, has high charging accuracy, and has no risk of failure. In addition, it has strong tolerance for the deployment environment of the charging pile, does not require an environment with low infrared interference, and does not have the loss or pollution problem of the QR code like the QR code charging pile, and the success rate of long-term charging is very high.

[0071] The robot of the present application further includes: a processor 201 and a memory 202, wherein computer program instructions are stored in the memory 202, wherein when the computer program instructions are executed by the processor 201, the processor 201 executes the steps of the robot charging pile method in the above embodiment.

[0072] Furthermore, if Figure 3 As shown, the robot further includes a network interface 203 , an input device 204 , a hard disk 205 , and a display device 206 .

[0073] The above-mentioned interfaces and devices can be interconnected through a bus architecture. The bus architecture can include any number of interconnected buses and bridges. Specifically, one or more central processing units 201 (CPUs) represented by processor 201 and various circuits of one or more memories 202 represented by memory 202 are connected together. The bus architecture can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits together. It can be understood that the bus architecture is used to achieve connection and communication between these components. In addition to the data bus, the bus architecture also includes a power bus, a control bus, and a status signal bus, which are all well known in the art, so they will not be described in detail herein.

[0074] The network interface 203 can be connected to a network (such as the Internet, a local area network, etc.), obtain relevant data from the network, and save it in the hard disk 205.

[0075] The input device 204 can receive various instructions input by the operator and send them to the processor 201 for execution. The input device 204 can include a keyboard or a pointing device (for example, a mouse, a trackball, a touch pad or a touch screen, etc.).

[0076] The display device 206 can display the result obtained by the processor 201 executing the instruction.

[0077] The memory 202 is used to store programs and data necessary for the operation of the operating system 2021, as well as data such as intermediate results during the calculation process of the processor 201.

[0078] It is understood that the memory 202 in the embodiment of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, 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. The memory 202 of the apparatus and method described herein is intended to include, but is not limited to, these and any other suitable types of memory 202.

[0079] In some implementations, the memory 202 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof: an operating system 2021 and application programs 2022 .

[0080] The operating system 2021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 2022 includes various application programs 2022, such as a browser, etc., which are used to implement various application services. The program for implementing the method of the embodiment of the present invention can be included in the application 2022.

[0081] The processor 201 , when calling and executing the application 2022 and data stored in the memory 202 , specifically, the program or instruction stored in the application 2022 , executes the steps of the robot charging pile method according to the above embodiment.

[0082] The method disclosed in the above embodiment of the present invention can be applied to the processor 201, or implemented by the processor 201. The processor 201 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 201 or the instruction in the form of software. The above processor 201 can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, and can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general processor can be a microprocessor or the processor 201 can also be any conventional processor 201, etc. The steps of the method disclosed in conjunction with the embodiment of the present invention can be directly embodied as a hardware decoding processor to be executed, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 202, and the processor 201 reads the information in the memory 202 and completes the steps of the above method in combination with its hardware.

[0083] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode or a combination thereof. For hardware implementation, the processing unit can 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 of the present application or a combination thereof.

[0084] For software implementation, the technology herein can be implemented by modules (e.g., procedures, functions, etc.) that perform the functions herein. The software code can be stored in the memory 202 and executed by the processor 201. The memory 202 can be implemented in the processor 201 or outside the processor 201.

[0085] Specifically, the processor 201 is also used to read the computer program and execute the following steps: predict the pile charging method and output the answer to the question asked by the user.

[0086] The third aspect of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by the processor 201, the processor 201 executes the steps of the robot charging pile method of the above embodiment.

[0087] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0088] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0089] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the sending and receiving methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0090] Although some specific embodiments of the present application have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are only for illustration, not for limiting the scope of the present application. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present application. The scope of the present application is defined by the appended claims.

Claims

1. A method for charging a pile with a robot, characterized in that: The following steps are involved: Recording the laser point cloud and the first position of the robot when it is facing the charging pile, wherein the laser point cloud is the target point cloud; Calculate the coordinates and orientation of a position at a first preset distance directly behind the robot according to the real-time position of the robot to obtain a second position; When the robot needs to be charged, navigating the robot to a second location; Based on the point cloud at the second position of the robot as the input point cloud, the target point cloud and the input point cloud are used for nearest neighbor search; Performing point cloud registration with the input point cloud and the target point cloud to obtain a third position after registration, and continuously updating the input point cloud until an absolute value of a deviation between the third position after registration and the first position is less than a second preset distance; The step of performing nearest neighbor search on the target point cloud and the input point cloud comprises: Traversing all points of the input point cloud, removing points in the input point cloud that are greater than a preset multiple of the first preset distance, and retaining points in the input point cloud that are less than or equal to a preset multiple of the first preset distance; The steps of continuously updating the input point cloud include: The robot is controlled to move toward the charging pile according to the relative position deviation between the second position and the first position, and the input point cloud is continuously updated during the moving process.

2. The robot charging method according to claim 1, characterized in that: The laser point cloud is a laser radar point cloud, and the laser point cloud includes three-dimensional coordinates and laser reflection intensity.

3. The robot charging method according to claim 2, characterized in that: The first preset distance is 0.2m-0.8m, the preset multiple is 1-2, and the second preset distance is 3cm-8cm.

4. A robot charging system, applied to the robot charging method according to any one of claims 1 to 3, characterized in that: The robot-to-pile charging system comprises: A recording module, used to record the laser point cloud and the first position when the robot is facing the charging pile, wherein the laser point cloud is a target point cloud; A calculation module, the calculation module is connected to the recording module, and the calculation module is used to calculate the coordinates and orientation of a position at a first preset distance directly behind the robot, and obtain a second position, wherein the point cloud at the second position is the input point cloud; when the robot needs to be charged, navigate the robot to the second position; A search module, the search module is connected to the calculation module, and the search module is used to perform a nearest neighbor search on the target point cloud and the input point cloud; A registration module, the registration module is connected to the search module, and the registration module is used to perform point cloud registration on the input point cloud and the target point cloud; An updating module, the updating module is connected to the registration module, and the updating module is used to update the input point cloud; The search module includes: a rejection unit and a retention unit, the rejection unit and the retention unit are respectively connected to the calculation module, the rejection unit is used to reject points in the input point cloud that are greater than a preset multiple of the first preset distance, and the retention unit is used to retain points in the input point cloud that are less than or equal to a preset multiple of the first preset distance; Continuously updating the input point cloud includes: The robot is controlled to move toward the charging pile according to the relative position deviation between the second position and the first position, and the input point cloud is continuously updated during the moving process.

5. A robot, characterized in that: The robot comprises: Mobile chassis; A machine body, the machine body is arranged on the mobile chassis, and the mobile chassis drives the machine body to move; A laser radar, wherein the laser radar is arranged in the machine body; The robot also includes: a processor and a memory, in which computer program instructions are stored, wherein when the computer program instructions are executed by the processor, the processor executes the steps of the robot charging pile method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the robot charging pile method according to any one of claims 1 to 3.

Images