CN112198871A - Method and apparatus for autonomous charging of mobile robot - Google Patents

Method and apparatus for autonomous charging of mobile robot Download PDF

Info

Publication number
CN112198871A
CN112198871A CN202010907714.6A CN202010907714A CN112198871A CN 112198871 A CN112198871 A CN 112198871A CN 202010907714 A CN202010907714 A CN 202010907714A CN 112198871 A CN112198871 A CN 112198871A
Authority
CN
China
Prior art keywords
point cloud
point
charging
charging pile
mobile robot
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010907714.6A
Other languages
Chinese (zh)
Inventor
王宇辰
吕峰
阎鹤凌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jiexiang Lingyue Technology Co.,Ltd.
Original Assignee
Sinovation Ventures Beijing Enterprise Management Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sinovation Ventures Beijing Enterprise Management Co ltd filed Critical Sinovation Ventures Beijing Enterprise Management Co ltd
Priority to CN202010907714.6A priority Critical patent/CN112198871A/en
Publication of CN112198871A publication Critical patent/CN112198871A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0234—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons
    • G05D1/0236—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons in combination with a laser
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0225—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving docking at a fixed facility, e.g. base station or loading bay
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
    • G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M10/00—Secondary cells; Manufacture thereof
    • H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
    • H01M10/44—Methods for charging or discharging
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/10—Energy storage using batteries

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Optics & Photonics (AREA)
  • Electromagnetism (AREA)
  • General Chemical & Material Sciences (AREA)
  • Electrochemistry (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Chemical & Material Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The application provides a method and apparatus for autonomous charging of a mobile robot, the method comprising: acquiring point cloud data scanned by a radar on one side, facing a charging pile, of the mobile robot at a detection position, and dividing the point cloud data into a plurality of point cloud subsets, wherein the charging pile comprises a specific-shape structure; matching each point cloud subset in the plurality of point cloud subsets with a point cloud template corresponding to the specific shape structure, and determining the position and direction information of the charging pile according to the matching result; and finishing the butt joint with the charging pile according to the position and direction information, and starting charging. According to the scheme of the application, the method and the device have the advantages of wide applicable scenes, low cost, high detection result precision, capability of realizing safe butt joint, stability and reliability.

Description

Method and apparatus for autonomous charging of mobile robot
Technical Field
The present application relates to the field of mobile robots, and more particularly, to a method and apparatus for autonomous charging of a mobile robot.
Background
With the continuous progress of the related technology of artificial intelligence, the application range of the mobile robot is more and more extensive, for example, the mobile robot can be widely applied to the fields of industry, agriculture, medical treatment, city safety, national defense, space detection and the like, and the mobile robot technology has many hot problems, and one of the hot problems is how to complete the autonomous charging of the mobile robot. Use the industrial field as an example, in recent years, mobile robot technique has played more and more important effect in modern industry, compare with traditional industry production line that relies on manpower transportation, the line of production that relies on mobile robot to carry out automated transportation has higher accuracy and security, production efficiency also can improve greatly, however, the magnetic track is laid on ground to the present technique of charging most dependence, arrange artifical sign such as two-dimensional code in the charging environment, guidance methods such as installation infrared ray interfacing apparatus, make mobile robot move according to setting for or half settlement route and dock the electric pile of filling, wherein lay the magnetic track and arrange the mode of two-dimensional code and need daily maintenance, and need the secondary transformation when the factory environment changes, installation infrared ray interfacing apparatus cost is higher, and break down easily.
Disclosure of Invention
The purpose of this application is to provide an environmental improvement little, low cost, again accurate stable technical scheme who is used for the autonomic charging of mobile robot.
According to an embodiment of the present application, there is provided a method for autonomous charging of a mobile robot, wherein the method includes:
acquiring point cloud data scanned by a radar on one side, facing a charging pile, of the mobile robot at a detection position, and dividing the point cloud data into a plurality of point cloud subsets, wherein the charging pile comprises a specific-shape structure;
matching each point cloud subset in the plurality of point cloud subsets with a point cloud template corresponding to the specific shape structure, and determining the position and direction information of the charging pile according to the matching result;
and finishing the butt joint with the charging pile according to the position and direction information, and starting charging.
There is also provided, according to another embodiment of the present application, an apparatus for automatic charging in a mobile robot, wherein the apparatus includes:
the device comprises a device for acquiring point cloud data scanned by a radar of one side, facing a charging pile, of the mobile robot at a detection position and dividing the point cloud data into a plurality of point cloud subsets, wherein the charging pile comprises a specific shape structure;
the device is used for matching each point cloud subset in the plurality of point cloud subsets with the point cloud template corresponding to the specific shape structure, and determining the position and direction information of the charging pile according to the matching result;
and the device is used for completing the butt joint with the charging pile according to the position and direction information and starting charging.
Compared with the prior art, the method has the following advantages: the point cloud subsets obtained by dividing the real-time point cloud data can be matched with the point cloud templates corresponding to the specific shape structures of the charging piles, so that the accurate positions and directions of the charging piles are obtained, and safe and efficient butt joint between the mobile robot and the charging piles and automatic charging of the mobile robot are realized; the charging pile has wide applicable scenes, does not need to modify the environment, can be arranged by placing the charging pile at any position, is simple and convenient, and is not limited in use scenes; the method has the advantages that the cost is low, the laser radar of the robot is reused, no auxiliary mark is required to be added in a scene, and no new sensor is required to be added on the mobile robot and the charging pile, so that the manufacturing cost and the later maintenance cost of the mobile robot are greatly reduced, the point cloud template can be quickly generated aiming at different specific shape structures, the method can adapt to the design of the charging piles in various shapes, and the shape detection algorithm based on template matching has high robustness; the detection result has high precision, the shape detection algorithm based on template matching can maximally utilize input data, the detection resolution can reach millimeter-level precision, and the result is more accurate compared with other detection algorithms; because the radar sensing system of the mobile robot is used, the surrounding environment can be sensed in real time in the autonomous charging process. When pedestrians or obstacles appear around the robot, the robot can effectively and automatically avoid the obstacles, so that the damage to the people or the environment is avoided; in addition, for the detection failure and few unexpected cases which may occur, effective trial can be performed again when the charging fails, so that the probability of the charging failure can be greatly reduced.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
fig. 1 shows a front view of a charging pole according to an example of the present application;
FIG. 2 shows a side view of the charging post of FIG. 1;
FIG. 3 illustrates a rear view of a mobile robot of one example of the present application;
FIG. 4 illustrates a side view of the mobile robot of FIG. 3;
FIG. 5 illustrates a flow diagram of a method for autonomous charging of a mobile robot, in accordance with an embodiment of the present application;
FIG. 6a is a diagram illustrating coarse matching results for an example of the present application;
FIG. 6b is a schematic diagram illustrating the fine matching result of an example of the present application;
FIG. 7 illustrates an autonomous charging flow diagram of an example of the present application;
fig. 8 is a schematic structural diagram illustrating an apparatus for autonomous charging in a mobile robot according to an embodiment of the present application.
The same or similar reference numbers in the drawings identify the same or similar elements.
Detailed Description
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel, concurrently, or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
The methodologies discussed hereinafter, some of which are illustrated by flow diagrams, may be implemented by hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. When implemented in software, firmware, middleware or microcode, the program code or code segments to perform the necessary tasks may be stored in a machine or computer readable medium such as a storage medium. The processor(s) may perform the necessary tasks.
Specific structural and functional details disclosed herein are merely representative and are provided for purposes of describing example embodiments of the present application. This application may, however, be embodied in many alternate forms and should not be construed as limited to only the embodiments set forth herein.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element may be termed a second element, and, similarly, a second element may be termed a first element, without departing from the scope of example embodiments. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be noted that, in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
The present application is described in further detail below with reference to the attached figures.
Before describing the technical solution for autonomous charging of a mobile robot in detail, a charging pile and a mobile robot according to the present application will be described as an example.
It should be noted that, in the present embodiment, the charging pile for autonomous charging of the mobile robot includes a specific shape structure, and the height of the specific shape structure is located on the radar scanning plane of the mobile robot. The specific structure of the specific shape structure included in the charging pile is not limited in the present application, for example, the specific shape structure is a combination of a V-shape with a specific included angle and a straight line, and for example, the specific shape structure is a combination of an arc and a straight line. It should be further noted that, in addition to the specific shape structure, the charging pile further includes a charging post for being abutted against a charging sheet of the mobile robot, and other structures, such as a protective housing for protecting the charging post, a base for supporting, and the like.
As an example, the charging pile comprises a linear structure, a V-shaped structure embedded into the linear structure and having a specific included angle, a charging post and a charging post protective shell, wherein the height of the V-shaped structure is located on a radar scanning plane of the mobile robot, and the charging post is used for abutting against a charging post sheet located on a body of the mobile robot. The combination of the straight line structure and the V-shaped structure forms a specific shape structure, that is, the charging pile comprises a specific shape formed by combining a V-shape with a specific included angle and a straight line (hereinafter, the specific shape is also referred to as "VL shape"). In some embodiments, a straight line structure refers to a structure in which the border or surface structure exhibits a number of straight line segments. In some embodiments, the V-shaped structure refers to a structure having a V shape, the V-shaped structure has a specific included angle, the specific included angle can be designed based on actual needs, as an example, the V-shaped structure of the charging pile has an included angle of 120 degrees, and thus, the charging pile comprises a specific shape formed by combining a V shape with an included angle of 120 degrees and a straight line. In some embodiments, the charging post includes two charging posts for interfacing with a charging pole piece located on the mobile robot. In some embodiments, when the charging pile is docked with the mobile robot, the charging pile generates a voltage signal and returns the voltage signal to the mobile robot to indicate that the docking is successful, and the mobile robot turns on the relay to charge after receiving the voltage signal. In some embodiments, the V-shaped structure is embedded into one side of the linear structure, and the charge pole may be mounted on the side at any position other than the embedding position of the V-shaped structure; as a preferable scheme, the charging pole is located below the embedding position of the V-shaped structure on the linear structure, in this case, the mobile robot can determine the position of the charging pile directly by recognizing a specific shape structure; in some embodiments, the charging post is spaced apart from the V-shaped structure by a certain distance, in which case the mobile robot determines the position of the charging post by recognizing the specific shape structure and combining the relative position information between the charging post and the V-shaped structure. In some embodiments, the charging pile further comprises a base located below the linear structure, the base is used for supporting, and the application is not limited to the specific shape structure of the base.
Fig. 1 shows a front view of a charging pole according to an example of the present application, and fig. 2 shows a side view of the charging pole shown in fig. 1. The electric pile that fills of this embodiment includes V-arrangement 101, two utmost point post 102 that charge, linear structure 103, utmost point post protective housing 104 and base 105 charge, wherein, V-arrangement 101 has 120 degrees contained angles, and V-arrangement 101 imbeds to the upper left side of linear structure 103 one side, and utmost point post 102 that charges is located the below of V-arrangement 101's embedding position and is closely adjacent to this embedding position, and two utmost point posts 102 that charge are used for the electrode piece that charges on the butt joint mobile robot automobile body to this completion charges. It should be noted that, although the charging post 102 is located below and immediately adjacent to the embedding position of the V-shaped structure 101 in the embodiment, it should be understood by those skilled in the art that the charging post 102 may be disposed at any other position on the side, such as above the embedding position of the V-shaped structure 101, or at the lower right of the side, so long as the mobile robot stores the relative position information between the charging post 102 and the V-shaped structure 101, the mobile robot can determine the position of the charging post 102 based on the identified position of the charging post and the relative position information, and implement the docking.
FIG. 3 illustrates a rear view of a mobile robot of one example of the present application; fig. 4 shows a side view of the mobile robot of fig. 3. The mobile robot of this example includes robot charging pole piece 201, locomotive radar 202, rear of a vehicle radar 203 and wheel 204, when using the electric pile of filling of this application to realize independently charging, charging pole piece 201 is used for with fill the butt joint of electric pile's the utmost point post that charges, locomotive radar 202 and rear of a vehicle radar 203 are used for sending laser signal, when mobile robot accepts the task of charging, can independently navigate to fill electric pile the place ahead, and can read the real-time point cloud data that mobile robot scanned towards the radar (probably for locomotive radar 202 or rear of a vehicle radar 203) that fills electric pile one side, with the position of discernment and the completion and the butt joint that fills electric pile. It should be noted that the mobile robot shown in fig. 3 is only an example, and is not a limitation of the present application.
Fig. 5 shows a flow diagram of a method for autonomous charging of a mobile robot according to an embodiment of the application. The method of the present embodiment includes step S11, step S12, and step S13. In step S11, the mobile robot acquires point cloud data of radar scanning of the mobile robot facing a charging pile side at a detection position, and divides the point cloud data into a plurality of point cloud subsets, wherein the charging pile includes a specific shape structure; in step S12, the mobile robot matches each of the point cloud subsets with the point cloud template corresponding to the specific shape structure, and determines the position and direction information of the charging pile according to the matching result; in step S13, the mobile robot completes docking with the charging pile according to the position and direction information, and starts charging.
It should be noted that, before executing the autonomous charging task, a point cloud template corresponding to a specific shape structure of the charging pile needs to be obtained, where the point cloud template actually strictly conforms to the real shape distribution, point cloud data with the same adjacent point distance and a smaller adjacent point distance, and charging piles with different specific shape structures correspond to different point cloud templates, and the implementation manner of obtaining the point cloud template corresponding to the specific shape structure of the charging pile will be described in detail in the following embodiments, which is not described herein again. In some embodiments, the maximum length of the point cloud template (i.e. the maximum distance of the distances between any two points in the point cloud template) is determined based on the specific shape structure to which it corresponds, and preferably, the maximum distance from the point corresponding to the specific shape structure (i.e. the maximum distance of the distances between any two points in the specific shape structure) is determined as the maximum length of the point cloud template; for example, the charging pile shown in fig. 1 includes a VL shape, and the maximum length of the point cloud template corresponding to the VL shape is the distance between the end point far away from L and the farthest end of L in the V shape; for another example, the specific shape structure is a wave shape, and the maximum length of the point cloud template corresponding to the wave shape is the distance between two end points of the wave shape.
In step S11, the mobile robot acquires point cloud data of radar scanning of the mobile robot facing a charging pile side at the detection position, and divides the point cloud data into a plurality of point cloud subsets, wherein the charging pile includes a specific shape structure.
The mobile robot can autonomously navigate to the front of the charging pile when receiving the charging task, the navigation process of the mobile robot autonomously navigating to the front of the charging pile is not limited, and any implementation mode of autonomously navigating to the front of the charging pile when receiving the charging task should be included in the protection range of the mobile robot.
In some embodiments, after the mobile robot autonomously navigates to the front of the charging pile, a radar facing one side of the charging pile sends out a laser signal, the mobile robot reads real-time point cloud data scanned by the radar, and the point cloud data is divided into a plurality of point cloud subsets. Wherein the real-time point cloud data may be divided into a plurality of point cloud subsets in any feasible manner. As a preferred scheme, the dividing the point cloud data into a plurality of point cloud subsets includes: taking a first point in the point cloud data as a starting point; traversing from the starting point, and if a target point with the distance length between the starting point and the target point according with the length of the point cloud template is found, dividing the point cloud data from the starting point to the target point into a point cloud subset; if the target point is the last point in the point cloud data, the division operation is ended, otherwise, the next point of the starting point is used as a new starting point, and the traversal operation is repeated. And if the target point is the last point in the point cloud data, all point cloud subsets corresponding to the point cloud data are obtained. As an example, the scanning angle range of the radar on the mobile robot is to scan from-135 degrees to 135 degrees with the center of the radar as the origin, the scanning resolution of the radar is 0.25, and the scanning angle of the radar is 270 degrees (i.e., the angle value from-135 degrees to 135 degrees), so that the number of points can be calculated to be 270/0.25 to 1080, i.e., the read real-time point cloud data includes the 0 th to 1080 th points arranged according to the scanning order, i.e., a total of 1081 point, and then, backward traversal is started with the 0 th point as the starting point to find the mth point (i.e., the target point corresponding to the 0 th point), the distance length from the 0 th point to the mth point approximately matches (e.g., is equal to or closest to) the maximum length of the point cloud template, the points in the point cloud data with the interval of [0, m ] are divided into a point cloud subset, and then backward traversal is started with the 1 st point as, and (3) finding the nth point (namely the target point corresponding to the 1 st point), dividing the points with the interval of [1, n ] in the point cloud data into point cloud subsets if the distance length from the 1 st point to the nth point approximately conforms to the maximum length of the point cloud template, and repeating the steps until all the point cloud subsets are found in 1081 points (the maximum distance of each point cloud subset meets the maximum length of the point cloud template), and finishing the division operation.
It should be noted that the above division is only an example and not a limitation of the present application, and other implementations of dividing the point cloud data into a plurality of point cloud subsets are also included in the scope of the present application.
In step S12, the mobile robot matches each of the point cloud subsets with the point cloud template corresponding to the specific shape structure, and determines the position and direction information of the charging pile according to the matching result.
In some embodiments, each point cloud subset is matched with the point cloud template corresponding to the specific shape structure, and the position and direction information of the charging pile is determined according to the point cloud subset with the highest matching degree (and exceeding a predetermined matching degree threshold).
In some embodiments, the point cloud template matching algorithm includes a coarse matching process and a fine matching process, and the matching value of two pieces of point cloud is designed as an average value of the distance between corresponding points in the two pieces of point cloud. In some embodiments, the matching each of the plurality of point cloud subsets with the point cloud template corresponding to the specific shape structure and determining the position and direction information of the charging pile according to the matching result includes: for each point cloud subset in the plurality of point cloud subsets, transforming the point cloud subset through an initial pose, performing rough matching on the transformed point cloud subset and the point cloud template to obtain a rough matching result, judging whether the rough matching result meets a rough matching threshold condition, if not, giving up the point cloud subset, if so, performing precise matching on the point cloud subset and the point cloud template based on a closest point iteration algorithm to obtain a precise matching result, judging whether the precise matching result meets a precise matching threshold condition, if not, giving up the point cloud subset, and if so, determining the position and direction information of the charging pile according to the rough matching result and the precise matching result. Fig. 6a is a schematic diagram illustrating a rough matching result of an example of the present application, and fig. 6b is a schematic diagram illustrating a fine matching result of an example of the present application, where 301 is a point cloud template corresponding to a VL shape of the charging pile shown in fig. 1, 302 is a rough matching result of real-time point cloud data, and 303 is a fine matching result of the real-time point cloud data, and then the position and direction information of the charging pile is determined according to a pose result of 303.
In some embodiments, in the rough matching process, firstly, point cloud subsets meeting the characteristics of a point cloud template are searched on real-time point cloud data scanned by a radar, the point cloud subsets are transformed to the vicinity of the point cloud template through an initial pose, if a rough matching result between one transformed point cloud subset and the point cloud template cannot meet a rough matching threshold condition, the rough matching result is failed, the point cloud subset is considered not to be a charging pile to be detected, if a rough matching result between one transformed point cloud subset and the point cloud template meets the rough matching threshold condition, the point cloud subset is considered to be a possible charging pile shape, and a fine matching process can be carried out; in the fine matching process, the template matching is continuously performed on the possible point cloud subsets based on the closest point iterative algorithm to obtain a fine matching result, if the fine matching result is better than the fine matching threshold (for example, if the fine matching threshold is set to be 0.3cm, if the fine matching result indicates that the average value of the distance between the corresponding points between the point cloud subsets and the point cloud template is 0.2cm, and since the average value is smaller than the fine matching threshold, the fine matching result is considered to be better than the fine matching threshold, that is, the smaller the average value of the distance between the corresponding points in the two point clouds is, the more the two point clouds are matched), which indicates that the point cloud subset is the charging pile to be searched by the mobile robot, and the pose result indicated by the fine matching result is the position and the direction of the charging pile, that is, the position and the direction of the pose transformation result of the coarse matching process and the, and translating and rotating the point cloud A in the rough matching process to obtain a transformed point cloud subset A1, translating and rotating the point cloud subset A1 in the fine matching process to obtain a transformed point cloud subset A2 if the rough matching is successful, and considering that the charging pile is found if the fine matching result is superior to a fine matching threshold value, and combining the pose transformation matrix T of the two translations and the two rotations to obtain the position and the direction of the charging pile. As an example, based on the point cloud template matching algorithm, when the charging pile is identified through a rough matching process and a fine matching process, a rotation matrix R and a translation vector t are obtained, where the rotation matrix R can represent a rotation relationship between a real-time point cloud coordinate system and a template coordinate system, the translation vector t can represent a translation relationship between the real-time point cloud coordinate system and the template coordinate system, and the calculation of the rotation matrix R and the translation vector t satisfies the following relational expression:
Figure BDA0002662080180000101
wherein the content of the first and second substances,
Figure BDA0002662080180000102
representing a radar data point of the real-time point cloud data after pose transformation,
Figure BDA0002662080180000103
representing point cloud on template
Figure BDA0002662080180000104
The radar data points with the closest point Euclidean distances, n represents the total number of radar points of the real-time point cloud data, based on the formula, the rotation matrix R and the translation vector t are the optimal solution which can lead the sum of the Euclidean distances of all corresponding points of the real-time point cloud data and the point cloud template data to be the minimum, and the pose transformation relation is formed by the rotation matrix R and the translation vector t, and the formula is as follows
Figure BDA0002662080180000105
Wherein, [ x ]input,yinput]Representing real-time point cloud data, theta represents the charging pile orientation obtained according to a point cloud template matching algorithm, and a vector [ x ]t,yt]The position of the charging pile is obtained according to a point cloud template matching algorithm.
It should be noted that, the above formula and the implementation manner of determining the position and the direction information of the charging pile according to the matching result are only examples and are not limited to the present application, and those skilled in the art should understand that any implementation manner of determining the position and the direction information of the charging pile according to the matching result should be included in the scope of the present application.
In step S13, the mobile robot completes docking with the charging pile according to the position and direction information, and starts charging. Specifically, the mobile robot rotates and moves according to the position and direction information to complete the butt joint with a charging pole on the charging pile, and a relay is started to start charging after the butt joint is successful.
In some embodiments, the step S13 further includes: determining target position posture information according to the position and direction information; rotating and moving according to the target position and posture information to enable the mobile robot to move to a target position and a target posture; and moving backwards at a low speed, and starting charging if detecting a voltage signal returned by the charging pile. In some embodiments, the target position and posture information is used to indicate a target position to which the mobile robot needs to move and a target posture of the mobile robot, where the target position is a fixed distance away from the front of the charging pile, and the target posture is a recognition direction of the charging pile (i.e., the detected orientation of the charging pile). The mobile robot may rotate and move to a target position and a target pose in any feasible manner, such as by using a dial number of degrees, or by using an instant positioning and mapping technique. In some embodiments, the mobile robot determines target position and posture information according to the position and direction information, generates an instruction including the target position and posture information, then rotates and moves according to the instruction, so that the mobile robot moves to the target position and the target posture, and moves backward at a low speed after reaching the target position until a charging pole piece of the mobile robot contacts with two charging poles of a charging pile and detects a voltage signal returned by the charging pile, and then the mobile robot determines that autonomous charging docking is successful, and turns on a relay to perform a charging task.
In some embodiments, if it is detected that the abnormal triggering condition is satisfied during the backward movement, the mobile robot stops the backward movement and returns to the detection position to try the autonomous charging again (i.e., repeatedly perform steps S11, S12, and S13). In some embodiments, the abnormal triggering condition includes, but is not limited to, the absence of detection of a voltage signal from the charging post (e.g., the voltage signal is not detected when a predetermined time is reached or a predetermined distance has been moved), the presence of an obstacle, etc. Based on the fault-tolerant mechanism, the mobile robot can stop backing in time after finding abnormality, return to the initial detection position and perform charging attempt again, so that the success rate of autonomous charging can be ensured under some abnormal conditions.
In some embodiments, the method further includes a step S14 (not shown) performed before the step S11, and in step S14, the mobile robot obtains a point cloud template corresponding to the specific shape structure. For example, the mobile robot obtains a point cloud template corresponding to the VL shape of the charging pile shown in fig. 1 to perform autonomous charging using the charging pile shown in fig. 1 later.
In some embodiments, the step S14 is further configured to: and generating a point cloud template corresponding to the specific shape structure according to the specific shape structure. For example, according to the VL shape of the charging pile shown in fig. 1, a point cloud template corresponding to the VL shape is generated, the point cloud template is a real shape distribution strictly conforming to the VL shape, and the point cloud data has the same adjacent point distance and smaller adjacent point distance. In some embodiments, a point cloud template corresponding to the specific shape structure may be generated in advance, and the point cloud template is loaded when the charging task is started. In some embodiments, a point cloud template corresponding to the particular shape structure is generated when a charging task begins.
In some embodiments, the step S14 is further configured to: and obtaining a point cloud template set, and determining a point cloud template corresponding to the specific shape structure from the point cloud template set. The point cloud template set comprises point cloud templates corresponding to various specific shape structures, and the point cloud templates corresponding to the specific shape structures of the charging piles to be docked can be determined from the point cloud templates so as to use the charging piles to perform autonomous charging. The method for obtaining the point cloud template set by the mobile robot is not limited, for example, the point cloud template set sent by other equipment through a network can be received, or the point cloud template set input through an external input device is read, or the point cloud template set is downloaded through a specific application program, for example, point cloud templates can be respectively generated aiming at different specific shape structures, so that the point cloud template set is obtained. In some embodiments, a specific shape structure may be set by default in the mobile robot, or a specific shape structure may be set by a user based on actual needs, the mobile robot may determine a point cloud template corresponding to the specific shape structure set by default or the user from a point cloud template set for autonomous charging, and thus, the mobile robot may support a variety of charging piles having different specific shapes, and the user may select the charging pile based on needs or preferences; preferably, if the mobile robot adopts the determined point cloud template and does not detect the charging pile, the point cloud template can be automatically replaced to try to detect the charging pile by using other point cloud templates, so that the automatic charging failure caused by the fact that the user does not update the setting in time after replacing the charging pile is avoided.
In some embodiments, the mobile robot reads real-time radar data in the whole autonomous charging process, so that an obstacle avoidance function is realized through the radar data, and the safety of the whole autonomous charging process is improved.
Fig. 7 shows an autonomous charging flow diagram of an example of the present application. The specific process is as follows: when a charging task starts, the mobile robot loads a point cloud template corresponding to a specific shape structure of a charging pile, then moves to a detection position, and acquires point cloud data scanned by a radar on one side, facing the charging pile, of the mobile robot at the detection position; intercepting a section of point cloud subset (namely, one point cloud subset obtained by dividing according to the dividing method in the embodiment), performing point cloud template matching on the point cloud subset, if the point cloud subset does not meet a threshold, abandoning the point cloud subset and re-intercepting a section of point cloud subset for performing point cloud template matching, if the threshold is met, rotating and moving the mobile robot, starting charging after the docking with the charging pile is successful, if the charging is successful, finishing the charging task, otherwise, returning the detection position by the mobile robot, re-obtaining real-time point cloud data, and repeating the matching process.
Fig. 8 shows a schematic structural diagram of an apparatus for autonomous charging of a mobile robot according to an embodiment of the present application. The apparatus for autonomous charging of a mobile robot (hereinafter, simply referred to as "autonomous charging apparatus") includes a first apparatus 11, a second apparatus 12, and a third apparatus 13.
It should be noted that, before executing the autonomous charging task, a point cloud template corresponding to a specific shape structure of the charging pile needs to be obtained, where the point cloud template actually strictly conforms to the real shape distribution, point cloud data with the same adjacent point distance and a smaller adjacent point distance, and charging piles with different specific shape structures correspond to different point cloud templates, and the implementation manner of obtaining the point cloud template corresponding to the specific shape structure of the charging pile will be described in detail in the following embodiments, which is not described herein again. In some embodiments, the maximum length of the point cloud template (i.e. the maximum distance of the distances between any two points in the point cloud template) is determined based on the specific shape structure to which it corresponds, and preferably, the maximum distance from the point corresponding to the specific shape structure (i.e. the maximum distance of the distances between any two points in the specific shape structure) is determined as the maximum length of the point cloud template; for example, the charging pile shown in fig. 1 includes a VL shape, and the maximum length of the point cloud template corresponding to the VL shape is the distance between the end point far away from L and the farthest end of L in the V shape; for another example, the specific shape structure is a wave shape, and the maximum length of the point cloud template corresponding to the wave shape is the distance between two end points of the wave shape.
The first device 11 is configured to acquire point cloud data of radar scanning of a side, facing a charging pile, of the mobile robot at a detection position, and divide the point cloud data into a plurality of point cloud subsets, wherein the charging pile includes a specific shape structure.
The mobile robot can autonomously navigate to the front of the charging pile when receiving the charging task, the navigation process of the mobile robot autonomously navigating to the front of the charging pile is not limited, and any implementation mode of autonomously navigating to the front of the charging pile when receiving the charging task should be included in the protection range of the mobile robot.
In some embodiments, after the mobile robot autonomously navigates to the front of the charging pile, a radar facing one side of the charging pile sends out a laser signal, and the first device 11 reads real-time point cloud data scanned by the radar and divides the point cloud data into a plurality of point cloud subsets. Wherein the real-time point cloud data may be divided into a plurality of point cloud subsets in any feasible manner. As a preferred scheme, the dividing the point cloud data into a plurality of point cloud subsets includes: taking a first point in the point cloud data as a starting point; traversing from the starting point, and if a target point with the distance length between the starting point and the target point according with the length of the point cloud template is found, dividing the point cloud data from the starting point to the target point into a point cloud subset; if the target point is the last point in the point cloud data, the division operation is ended, otherwise, the next point of the starting point is used as a new starting point, and the traversal operation is repeated. And if the target point is the last point in the point cloud data, all point cloud subsets corresponding to the point cloud data are obtained. As an example, the scanning angle range of the radar on the mobile robot is to scan from-135 degrees to 135 degrees with the center of the radar as the origin, the scanning resolution of the radar is 0.25, and the scanning angle of the radar is 270 degrees (i.e., the angle value from-135 degrees to 135 degrees), so that the number of points can be calculated to be 270/0.25 to 1080, i.e., the read real-time point cloud data includes the 0 th to 1080 th points arranged according to the scanning order, i.e., a total of 1081 point, and then, backward traversal is started with the 0 th point as the starting point to find the mth point (i.e., the target point corresponding to the 0 th point), the distance length from the 0 th point to the mth point approximately matches (e.g., is equal to or closest to) the maximum length of the point cloud template, the points in the point cloud data with the interval of [0, m ] are divided into a point cloud subset, and then backward traversal is started with the 1 st point as, and (3) finding the nth point (namely the target point corresponding to the 1 st point), dividing the points with the interval of [1, n ] in the point cloud data into point cloud subsets if the distance length from the 1 st point to the nth point approximately conforms to the maximum length of the point cloud template, and repeating the steps until all the point cloud subsets are found in 1081 points (the maximum distance of each point cloud subset meets the maximum length of the point cloud template), and finishing the division operation.
It should be noted that the above division is only an example and not a limitation of the present application, and other implementations of dividing the point cloud data into a plurality of point cloud subsets are also included in the scope of the present application.
The second device 12 is configured to match each of the point cloud subsets with the point cloud template corresponding to the specific shape structure, and determine the position and direction information of the charging pile according to the matching result.
In some embodiments, each point cloud subset is matched with the point cloud template corresponding to the specific shape structure, and the position and direction information of the charging pile is determined according to the point cloud subset with the highest matching degree (and exceeding a predetermined matching degree threshold).
In some embodiments, the point cloud template matching algorithm includes a coarse matching process and a fine matching process, and the matching value of two pieces of point cloud is designed as an average value of the distance between corresponding points in the two pieces of point cloud. In some embodiments, the matching each of the plurality of point cloud subsets with the point cloud template corresponding to the specific shape structure and determining the position and direction information of the charging pile according to the matching result includes: for each point cloud subset in the plurality of point cloud subsets, transforming the point cloud subset through an initial pose, performing rough matching on the transformed point cloud subset and the point cloud template to obtain a rough matching result, judging whether the rough matching result meets a rough matching threshold condition, if not, giving up the point cloud subset, if so, performing precise matching on the point cloud subset and the point cloud template based on a closest point iteration algorithm to obtain a precise matching result, judging whether the precise matching result meets a precise matching threshold condition, if not, giving up the point cloud subset, and if so, determining the position and direction information of the charging pile according to the rough matching result and the precise matching result. Fig. 6a is a schematic diagram illustrating a rough matching result of an example of the present application, and fig. 6b is a schematic diagram illustrating a fine matching result of an example of the present application, where 301 is a point cloud template corresponding to a VL shape of the charging pile shown in fig. 1, 302 is a rough matching result of real-time point cloud data, and 303 is a fine matching result of real-time point cloud data, and then position and direction information of the charging pile is determined according to a pose result of 303, and the matching result is obtained by implementing the autonomous charging process of the mobile robot shown in fig. 3 based on the charging pile shown in fig. 1.
In some embodiments, in the rough matching process, firstly, point cloud subsets meeting the characteristics of a point cloud template are searched on real-time point cloud data scanned by a radar, the point cloud subsets are transformed to the vicinity of the point cloud template through an initial pose, if a rough matching result between one transformed point cloud subset and the point cloud template cannot meet a rough matching threshold condition, the rough matching result is failed, the point cloud subset is considered not to be a charging pile to be detected, if a rough matching result between one transformed point cloud subset and the point cloud template meets the rough matching threshold condition, the point cloud subset is considered to be a possible charging pile shape, and a fine matching process can be carried out; in the fine matching process, the template matching is continuously performed on the possible point cloud subsets based on the closest point iterative algorithm to obtain a fine matching result, if the fine matching result is better than the fine matching threshold (for example, if the fine matching threshold is set to be 0.3cm, if the fine matching result indicates that the average value of the distance between the corresponding points between the point cloud subsets and the point cloud template is 0.2cm, and since the average value is smaller than the fine matching threshold, the fine matching result is considered to be better than the fine matching threshold, that is, the smaller the average value of the distance between the corresponding points in the two point clouds is, the more the two point clouds are matched), which indicates that the point cloud subset is the charging pile to be searched by the mobile robot, and the pose result indicated by the fine matching result is the position and the direction of the charging pile, that is, the position and the direction of the pose transformation result of the coarse matching process and the, and translating and rotating the point cloud A in the rough matching process to obtain a transformed point cloud subset A1, translating and rotating the point cloud subset A1 in the fine matching process to obtain a transformed point cloud subset A2 if the rough matching is successful, and considering that the charging pile is found if the fine matching result is superior to a fine matching threshold value, and combining the pose transformation matrix T of the two translations and the two rotations to obtain the position and the direction of the charging pile. As an example, based on the point cloud template matching algorithm, when the charging pile is identified through a rough matching process and a fine matching process, a rotation matrix R and a translation vector t are obtained, where the rotation matrix R can represent a rotation relationship between a real-time point cloud coordinate system and a template coordinate system, the translation vector t can represent a translation relationship between the real-time point cloud coordinate system and the template coordinate system, and the calculation of the rotation matrix R and the translation vector t satisfies the following relational expression:
Figure BDA0002662080180000161
wherein the content of the first and second substances,
Figure BDA0002662080180000162
representing a radar data point of the real-time point cloud data after pose transformation,
Figure BDA0002662080180000163
representing point cloud on template
Figure BDA0002662080180000164
The radar data points with the closest point Euclidean distances, n represents the total number of radar points of the real-time point cloud data, based on the formula, the rotation matrix R and the translation vector t are the optimal solution which can lead the sum of the Euclidean distances of all corresponding points of the real-time point cloud data and the point cloud template data to be the minimum, and the pose transformation relation is formed by the rotation matrix R and the translation vector t, and the formula is as follows
Figure BDA0002662080180000171
Wherein, [ x ]input,yinput]Representing real-time point cloud data, theta represents the charging pile orientation obtained according to a point cloud template matching algorithm, and a vector [ x ]t,yt]The position of the charging pile is obtained according to a point cloud template matching algorithm.
It should be noted that, the above formula and the implementation manner of determining the position and the direction information of the charging pile according to the matching result are only examples and are not limited to the present application, and those skilled in the art should understand that any implementation manner of determining the position and the direction information of the charging pile according to the matching result should be included in the scope of the present application.
And the third device 13 completes the butt joint with the charging pile according to the position and direction information and starts charging. Specifically, the mobile robot rotates and moves according to the position and direction information to complete the butt joint with a charging pole on the charging pile, and a relay is started to start charging after the butt joint is successful.
In some embodiments, the third device 13 is further configured to: determining target position posture information according to the position and direction information; rotating and moving according to the target position and posture information to enable the mobile robot to move to a target position and a target posture; and moving backwards at a low speed, and starting charging if detecting a voltage signal returned by the charging pile. In some embodiments, the target position and posture information is used to indicate a target position to which the mobile robot needs to move and a target posture of the mobile robot, where the target position is a fixed distance away from the front of the charging pile, and the target posture is a recognition direction of the charging pile (i.e., the detected orientation of the charging pile). The mobile robot may rotate and move to a target position and a target pose in any feasible manner, such as by using a dial number of degrees, or by using an instant positioning and mapping technique. In some embodiments, the mobile robot determines target position and posture information according to the position and direction information, generates an instruction including the target position and posture information, then rotates and moves according to the instruction, so that the mobile robot moves to the target position and the target posture, and moves backward at a low speed after reaching the target position until a charging pole piece of the mobile robot contacts with two charging poles of a charging pile and detects a voltage signal returned by the charging pile, and then the mobile robot determines that autonomous charging docking is successful, and turns on a relay to perform a charging task.
In some embodiments, if it is detected that the abnormal triggering condition is satisfied during the backward movement, the mobile robot stops the backward movement and returns to the detection position to try the autonomous charging again (i.e., to trigger the first device 11, the second device 12, and the third device 13 to repeatedly perform the operation). In some embodiments, the abnormal triggering condition includes, but is not limited to, the absence of detection of a voltage signal from the charging post (e.g., the voltage signal is not detected when a predetermined time is reached or a predetermined distance has been moved), the presence of an obstacle, etc. Based on the fault-tolerant mechanism, the mobile robot can stop backing in time after finding abnormality, return to the initial detection position and perform charging attempt again, so that the success rate of autonomous charging can be ensured under some abnormal conditions.
In some embodiments, the automatic charging device further includes a fourth device (not shown) for performing an operation before the first device 11, and the fourth device is configured to obtain a point cloud template corresponding to the specific shape structure. For example, the mobile robot obtains a point cloud template corresponding to the VL shape of the charging pile shown in fig. 1 to perform autonomous charging using the charging pile shown in fig. 1 later.
In some embodiments, the fourth means is further for: and generating a point cloud template corresponding to the specific shape structure according to the specific shape structure. For example, according to the VL shape of the charging pile shown in fig. 1, a point cloud template corresponding to the VL shape is generated, the point cloud template is a real shape distribution strictly conforming to the VL shape, and the point cloud data has the same adjacent point distance and smaller adjacent point distance. In some embodiments, a point cloud template corresponding to the specific shape structure may be generated in advance, and the point cloud template is loaded when the charging task is started. In some embodiments, a point cloud template corresponding to the particular shape structure is generated when a charging task begins.
In some embodiments, the fourth means is further for: and obtaining a point cloud template set, and determining a point cloud template corresponding to the specific shape structure from the point cloud template set. The point cloud template set comprises point cloud templates corresponding to various specific shape structures, and the point cloud templates corresponding to the specific shape structures of the charging piles to be docked can be determined from the point cloud templates so as to use the charging piles to perform autonomous charging. The method for obtaining the point cloud template set by the mobile robot is not limited, for example, the point cloud template set sent by other equipment through a network can be received, or the point cloud template set input through an external input device is read, or the point cloud template set is downloaded through a specific application program, for example, point cloud templates can be respectively generated aiming at different specific shape structures, so that the point cloud template set is obtained. In some embodiments, a specific shape structure may be set by default in the mobile robot, or a specific shape structure may be set by a user based on actual needs, the fourth means may determine a point cloud template corresponding to the specific shape structure set by default or by the user from the point cloud template set for autonomous charging, whereby the mobile robot may support a plurality of charging piles having different specific shapes, and the user may select the charging pile based on needs or preferences; preferably, if the mobile robot adopts the determined point cloud template and does not detect the charging pile, the point cloud template can be automatically replaced to try to detect the charging pile by using other point cloud templates, so that the automatic charging failure caused by the fact that the user does not update the setting in time after replacing the charging pile is avoided.
In some embodiments, the mobile robot reads real-time radar data in the whole autonomous charging process, so that an obstacle avoidance function is realized through the radar data, and the safety of the whole autonomous charging process is improved.
According to the scheme of the application, the point cloud subsets obtained by dividing the real-time point cloud data can be matched with the point cloud templates corresponding to the specific shape structures of the charging piles, so that the accurate positions and directions of the charging piles are obtained, and safe and efficient butt joint between the mobile robot and the charging piles and automatic charging of the mobile robot are realized; the charging pile has wide applicable scenes, does not need to modify the environment, can be arranged by placing the charging pile at any position, is simple and convenient, and is not limited in use scenes; the method has the advantages that the cost is low, the laser radar of the robot is reused, no auxiliary mark is required to be added in a scene, and no new sensor is required to be added on the mobile robot and the charging pile, so that the manufacturing cost and the later maintenance cost of the mobile robot are greatly reduced, the point cloud template can be quickly generated aiming at different specific shape structures, the method can adapt to the design of the charging piles in various shapes, and the shape detection algorithm based on template matching has high robustness; the detection result has high precision, the shape detection algorithm based on template matching can maximally utilize input data, the detection resolution can reach millimeter-level precision, and the result is more accurate compared with other detection algorithms; because the radar sensing system of the mobile robot is used, the surrounding environment can be sensed in real time in the autonomous charging process. When pedestrians or obstacles appear around the robot, the robot can effectively and automatically avoid the obstacles, so that the damage to the people or the environment is avoided; in addition, for the detection failure and few unexpected cases which may occur, effective trial can be performed again when the charging fails, so that the probability of the charging failure can be greatly reduced.
It should be noted that, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Claims (16)

1. A method for autonomous charging of a mobile robot, wherein the method comprises:
acquiring point cloud data scanned by a radar on one side, facing a charging pile, of the mobile robot at a detection position, and dividing the point cloud data into a plurality of point cloud subsets, wherein the charging pile comprises a specific-shape structure;
matching each point cloud subset in the plurality of point cloud subsets with a point cloud template corresponding to the specific shape structure, and determining the position and direction information of the charging pile according to the matching result;
and finishing the butt joint with the charging pile according to the position and direction information, and starting charging.
2. The method of claim 1, wherein the partitioning the point cloud data into a plurality of point cloud subsets comprises:
taking a first point in the point cloud data as a starting point;
traversing from the starting point, and if a target point with the distance length between the starting point and the target point according with the length of the point cloud template is found, dividing the point cloud data from the starting point to the target point into a point cloud subset;
if the target point is the last point in the point cloud data, the division operation is ended, otherwise, the next point of the starting point is used as a new starting point, and the traversal operation is repeated.
3. The method of claim 1, wherein the method further comprises:
and obtaining a point cloud template corresponding to the specific shape structure.
4. The method of claim 3, wherein the obtaining the point cloud template corresponding to the particular shaped structure comprises:
and generating a point cloud template corresponding to the specific shape structure according to the specific shape structure.
5. The method of claim 3, wherein the obtaining the point cloud template corresponding to the particular shaped structure comprises:
and obtaining a point cloud template set, and determining a point cloud template corresponding to the specific shape structure from the point cloud template set.
6. The method of any one of claims 1 to 5, wherein the matching each of the plurality of point cloud subsets with a point cloud template corresponding to the particular shape structure and determining the location and orientation information of the charging pile according to the matching result comprises:
for each point cloud subset in the plurality of point cloud subsets, transforming the point cloud subset through an initial pose, performing rough matching on the transformed point cloud subset and the point cloud template to obtain a rough matching result, judging whether the rough matching result meets a rough matching threshold condition, if not, giving up the point cloud subset, if so, performing precise matching on the point cloud subset and the point cloud template based on a closest point iteration algorithm to obtain a precise matching result, judging whether the precise matching result meets a precise matching threshold condition, if not, giving up the point cloud subset, and if so, determining the position and direction information of the charging pile according to the rough matching result and the precise matching result.
7. The method of any one of claims 1 to 6, wherein the completing the docking with the charging post and starting the charging according to the position and direction information comprises:
determining target position posture information according to the position and direction information;
rotating and moving according to the target position posture information so as to enable the mobile robot to move to a target position;
and moving backwards at a low speed, and starting charging if detecting a voltage signal returned by the charging pile.
8. The method of claim 7, wherein the method further comprises:
if the condition of meeting the abnormal triggering condition is detected in the backward movement process, the backward movement is stopped, and the backward movement is returned to the detection position so as to restart the scanning and try the charging again.
9. An apparatus for autonomous charging in a mobile robot, wherein the apparatus comprises:
the device comprises a device for acquiring point cloud data scanned by a radar of one side, facing a charging pile, of the mobile robot at a detection position and dividing the point cloud data into a plurality of point cloud subsets, wherein the charging pile comprises a specific shape structure;
the device is used for matching each point cloud subset in the plurality of point cloud subsets with the point cloud template corresponding to the specific shape structure, and determining the position and direction information of the charging pile according to the matching result;
and the device is used for completing the butt joint with the charging pile according to the position and direction information and starting charging.
10. The apparatus of claim 9, wherein the partitioning of the point cloud data into a plurality of point cloud subsets comprises:
taking a first point in the point cloud data as a starting point;
traversing from the starting point, and if a target point with the distance length between the starting point and the target point according with the length of the point cloud template is found, dividing the point cloud data from the starting point to the target point into a point cloud subset;
if the target point is the last point in the point cloud data, the division operation is ended, otherwise, the next point of the starting point is used as a new starting point, and the traversal operation is repeated.
11. The apparatus of claim 9, wherein the apparatus further comprises:
and the device is used for obtaining a point cloud template corresponding to the specific shape structure.
12. The apparatus of claim 11, wherein the means for obtaining the point cloud template corresponding to the particular shaped structure is configured to:
and generating a point cloud template corresponding to the specific shape structure according to the specific shape structure.
13. The apparatus of claim 11, wherein the means for obtaining the point cloud template corresponding to the particular shaped structure is configured to:
and obtaining a point cloud template set, and determining a point cloud template corresponding to the specific shape structure from the point cloud template set.
14. The apparatus of any of claims 9 to 13, wherein the means for matching each of the plurality of point cloud subsets to a point cloud template corresponding to the particular shape structure and determining location and orientation information of the charging post from the matching result is configured to:
for each point cloud subset in the plurality of point cloud subsets, transforming the point cloud subset through an initial pose, performing rough matching on the transformed point cloud subset and the point cloud template to obtain a rough matching result, judging whether the rough matching result meets a rough matching threshold condition, if not, giving up the point cloud subset, if so, performing precise matching on the point cloud subset and the point cloud template based on a closest point iteration algorithm to obtain a precise matching result, judging whether the precise matching result meets a precise matching threshold condition, if not, giving up the point cloud subset, and if so, determining the position and direction information of the charging pile according to the rough matching result and the precise matching result.
15. The apparatus of any one of claims 9 to 14, wherein the means for completing docking with the charging post and initiating charging according to the position and orientation information is configured to:
determining target position posture information according to the position and direction information;
rotating and moving according to the target position posture information so as to enable the mobile robot to move to a target position;
and moving backwards at a low speed, and starting charging if detecting a voltage signal returned by the charging pile.
16. The apparatus of claim 15, wherein the mobile robot further comprises:
if the condition of meeting the abnormal triggering condition is detected in the backward movement process, the backward movement is stopped, and the backward movement is returned to the detection position so as to restart the scanning and try the charging again.
CN202010907714.6A 2020-09-02 2020-09-02 Method and apparatus for autonomous charging of mobile robot Pending CN112198871A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010907714.6A CN112198871A (en) 2020-09-02 2020-09-02 Method and apparatus for autonomous charging of mobile robot

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010907714.6A CN112198871A (en) 2020-09-02 2020-09-02 Method and apparatus for autonomous charging of mobile robot

Publications (1)

Publication Number Publication Date
CN112198871A true CN112198871A (en) 2021-01-08

Family

ID=74006275

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010907714.6A Pending CN112198871A (en) 2020-09-02 2020-09-02 Method and apparatus for autonomous charging of mobile robot

Country Status (1)

Country Link
CN (1) CN112198871A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113297989A (en) * 2021-05-28 2021-08-24 深圳市优必选科技股份有限公司 Charging pile identification method and device, robot and computer readable storage medium
CN113341396A (en) * 2021-05-28 2021-09-03 深圳市优必选科技股份有限公司 Robot and charging pile identification method and device thereof
CN113341963A (en) * 2021-05-31 2021-09-03 深圳市威睿晶科电子有限公司 Navigation method and system for robot to automatically return to base station based on laser radar
CN114355889A (en) * 2021-12-08 2022-04-15 上海擎朗智能科技有限公司 Control method, robot charging stand, and computer-readable storage medium
CN115220446A (en) * 2022-06-30 2022-10-21 北京三快在线科技有限公司 Robot pile searching method and device and robot
CN115933706A (en) * 2023-02-07 2023-04-07 科大讯飞股份有限公司 Robot charging method and device, robot and robot system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110307838A (en) * 2019-08-26 2019-10-08 深圳市优必选科技股份有限公司 Robot method for relocating, device, computer readable storage medium and robot
CN110758152A (en) * 2019-10-08 2020-02-07 北京创新工场旷视国际人工智能技术研究院有限公司 Intelligent robot, charging pile and intelligent robot autonomous charging and docking method
CN110824491A (en) * 2019-10-24 2020-02-21 北京迈格威科技有限公司 Charging pile positioning method and device, computer equipment and storage medium
CN111324121A (en) * 2020-02-27 2020-06-23 四川阿泰因机器人智能装备有限公司 Mobile robot automatic charging method based on laser radar
CN111352420A (en) * 2020-03-03 2020-06-30 厦门大学 High-precision positioning and target alignment control method for laser navigation AGV

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110307838A (en) * 2019-08-26 2019-10-08 深圳市优必选科技股份有限公司 Robot method for relocating, device, computer readable storage medium and robot
CN110758152A (en) * 2019-10-08 2020-02-07 北京创新工场旷视国际人工智能技术研究院有限公司 Intelligent robot, charging pile and intelligent robot autonomous charging and docking method
CN110824491A (en) * 2019-10-24 2020-02-21 北京迈格威科技有限公司 Charging pile positioning method and device, computer equipment and storage medium
CN111324121A (en) * 2020-02-27 2020-06-23 四川阿泰因机器人智能装备有限公司 Mobile robot automatic charging method based on laser radar
CN111352420A (en) * 2020-03-03 2020-06-30 厦门大学 High-precision positioning and target alignment control method for laser navigation AGV

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113297989A (en) * 2021-05-28 2021-08-24 深圳市优必选科技股份有限公司 Charging pile identification method and device, robot and computer readable storage medium
CN113341396A (en) * 2021-05-28 2021-09-03 深圳市优必选科技股份有限公司 Robot and charging pile identification method and device thereof
WO2022247137A1 (en) * 2021-05-28 2022-12-01 深圳市优必选科技股份有限公司 Robot and charging pile recognition method and apparatus therefor
CN113341396B (en) * 2021-05-28 2023-12-15 深圳市优必选科技股份有限公司 Robot and charging pile identification method and device thereof
CN113297989B (en) * 2021-05-28 2024-04-16 优必康(青岛)科技有限公司 Charging pile identification method, device, robot and computer readable storage medium
CN113341963A (en) * 2021-05-31 2021-09-03 深圳市威睿晶科电子有限公司 Navigation method and system for robot to automatically return to base station based on laser radar
CN113341963B (en) * 2021-05-31 2023-08-22 深圳市威睿晶科电子有限公司 Laser radar-based navigation method and system for automatically returning robot to base station
CN114355889A (en) * 2021-12-08 2022-04-15 上海擎朗智能科技有限公司 Control method, robot charging stand, and computer-readable storage medium
CN115220446A (en) * 2022-06-30 2022-10-21 北京三快在线科技有限公司 Robot pile searching method and device and robot
CN115220446B (en) * 2022-06-30 2023-12-08 北京三快在线科技有限公司 Robot pile searching method and device and robot
CN115933706A (en) * 2023-02-07 2023-04-07 科大讯飞股份有限公司 Robot charging method and device, robot and robot system

Similar Documents

Publication Publication Date Title
CN112198871A (en) Method and apparatus for autonomous charging of mobile robot
CN112217248A (en) Charging pile, and method and device for autonomous charging of mobile robot
US11340628B2 (en) Marker-combined simultaneous localization and mapping navigation method, device and system
JP3561473B2 (en) Object position tracking / detection method and vehicle
CN110757446B (en) Robot recharging login method and device and storage device
Olson Probabilistic self-localization for mobile robots
KR101927038B1 (en) Vehicle position estimating apparatus, vehicle position estimating method
US7696894B2 (en) Method for determining a relative position of a mobile unit by comparing scans of an environment and mobile unit
EP3226207B1 (en) Automatic operation vehicle
Zhang et al. Robust appearance based visual route following for navigation in large-scale outdoor environments
CN108481327B (en) Positioning device, positioning method and robot for enhancing vision
CN108544494B (en) Positioning device, method and robot based on inertia and visual characteristics
JP7199937B2 (en) parking assist device
JP2005528707A (en) Feature mapping between data sets
Nüchter et al. Skyline-based registration of 3D laser scans
CN113900454A (en) Charging pile aligning method, device, equipment and storage medium
JP5032953B2 (en) Self-position recognition system
Wirbel et al. Humanoid robot navigation: From a visual SLAM to a visual compass
CN212044739U (en) Positioning device and robot based on inertial data and visual characteristics
Lin et al. Robust outdoor stereo vision SLAM for heavy machine rotation sensing
Krajník et al. A simple visual navigation system with convergence property
JP2637764B2 (en) Fingerprint center detection method
He et al. S4OM: A real-time LiDAR odometry and mapping system based on super4pcs scan-matching
US20240142992A1 (en) Map generation device and map generation system
EP4012655A1 (en) Positioning system and method for determining the three-dimensional position of a movable object

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right

Effective date of registration: 20210805

Address after: Room 1101-2, floor 11, block B, No. 3, Haidian Street, Haidian District, Beijing 100080

Applicant after: Beijing Jiexiang Lingyue Technology Co.,Ltd.

Address before: 100080 room 1001-003, building 1, No.3 Haidian Street, Haidian District, Beijing

Applicant before: SINOVATION VENTURES (BEIJING) ENTERPRISE MANAGEMENT Co.,Ltd.

TA01 Transfer of patent application right