Robot repositioning method and apparatus, storage medium, and electronic device

Abstract

The application provides a robot repositioning method and device, a storage medium and an electronic device. The method comprises: performing point cloud matching on first point cloud data collected by a mobile robot at a first position and a target area map to obtain a group of candidate poses; obtaining second point cloud data collected by the mobile robot when traveling to a second position; updating the group of candidate poses using a target pose parameter to obtain a group of updated poses, wherein the target pose parameter is used to represent a pose change of the mobile robot when moving from the first position to the second position; and repositioning the mobile robot using the second point cloud data and the group of updated poses. The above technical solution solves the problem of low accuracy of robot repositioning caused by the easy occurrence of mismatching in the related art robot repositioning method.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of robots, and in particular, to a robot repositioning method and device, a storage medium and an electronic device.

BACKGROUND

[0002] Currently, when repositioning a robot, the robot generally performs point cloud to map matching repositioning in situ, that is, the position of the robot matched each time and the score of the matching of the point cloud of the robot and the map are obtained, and the position with the highest score (i.e., the solution with the highest score) is determined as the current position of the robot.

[0003] However, using the above-mentioned robot repositioning method, only the solution with the highest score is obtained, and for a scene with similar environments on the map, the repositioning may fail. It can be seen that the robot repositioning method in the related art has the problem of low accuracy of robot repositioning due to the easy occurrence of mismatching.

SUMMARY

[0004] The present application aims to at least solve the problem of low accuracy of robot repositioning due to the easy occurrence of mismatching in the related art robot repositioning method.

[0005] The purpose of the present application is achieved by the following technical solutions:

[0006] According to an aspect of an embodiment of the present application, a robot repositioning method is provided, comprising: performing point cloud matching of first point cloud data collected by a mobile robot at a first position and a target region map to obtain a group of candidate poses; obtaining second point cloud data collected by the mobile robot when traveling to a second position; updating the group of candidate poses using a target pose parameter to obtain a group of updated poses, wherein the target pose parameter is used to represent the pose change of the mobile robot when moving from the first position to the second position; and repositioning the mobile robot using the second point cloud data and the group of updated poses.

[0007] In one exemplary embodiment, the target pose parameter of the mobile robot is obtained according to the following manner: obtaining the target mileage information generated by the mobile robot when moving from the first position to the second position through a target odometer on the mobile robot, wherein the target pose parameter includes the target mileage information.

[0008] In an example embodiment, the relocalizing the mobile robot using the second point cloud data and the set of updated poses comprises: determining point cloud data corresponding to each updated pose in the set of updated poses in the target area map; and relocalizing the mobile robot according to matching degrees of the point cloud data corresponding to each updated pose and the second point cloud data.

[0009] In an example embodiment, the relocalizing the mobile robot according to matching degrees of the point cloud data corresponding to each updated pose and the second point cloud data comprises: sequentially performing the following operations on each updated pose until a check stop condition is met, wherein each updated pose is a current updated pose in the process of performing the following operations, and the check stop condition comprises at least one of the following: the mobile robot is successfully relocalized, and all updated poses have been checked: in a case where the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is greater than or equal to a matching degree threshold, determining that the current updated pose passes the check, wherein the pose to which the mobile robot is relocalized is the current updated pose; and in a case where the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is less than the matching degree threshold, determining that the current updated pose fails the check, wherein the pose to which the mobile robot is relocalized is not the current updated pose.

[0010] In an example embodiment, the relocalizing the mobile robot according to matching degrees of the point cloud data corresponding to each updated pose and the second point cloud data comprises: determining, as the pose to which the mobile robot is relocalized, an updated pose in the set of updated poses for which the matching degree of the corresponding point cloud data and the second point cloud data is the highest and greater than or equal to a matching degree threshold.

[0011] In an example embodiment, the point cloud matching the first point cloud data collected by the mobile robot at the first position with the target area map to obtain a set of candidate poses comprises: determining a set of to-be-matched grid cells from the target area map, wherein the target area map is a grid map, and each to-be-matched grid cell in the set of to-be-matched grid cells is a grid cell in the target area map that allows the mobile robot to enter; and performing point cloud matching on the first point cloud data and point cloud data corresponding to each to-be-matched grid cell to obtain the set of candidate poses.

[0012] In an example embodiment, the method further includes: determining a plurality of candidate moving directions, wherein each candidate moving direction in the plurality of candidate moving directions is a moving direction allowed for the mobile robot at the first position; selecting a target moving direction from the plurality of candidate moving directions, wherein the target moving direction corresponds to a largest amount of point cloud data; and controlling the mobile robot to move along the target moving direction until the second position.

[0013] According to another aspect of the embodiments of the present application, a robot repositioning apparatus is provided, including: a matching unit configured to perform point cloud matching between first point cloud data collected by a mobile robot at a first position and a target area map, to obtain a set of candidate poses; a first obtaining unit configured to obtain second point cloud data collected by the mobile robot when the mobile robot travels to a second position; an updating unit configured to update the set of candidate poses using a target pose parameter, to obtain a set of updated poses, wherein the target pose parameter is used to represent a pose change of the mobile robot when moving from the first position to the second position; and a repositioning unit configured to reposition the mobile robot using the second point cloud data and the set of updated poses.

[0014] In an example embodiment, the apparatus further includes a second obtaining unit configured to obtain the target pose parameter of the mobile robot in the following manner: obtaining a target mileage information by obtaining a mileage increment generated by the mobile robot when moving from the first position to the second position through a target odometer on the mobile robot, wherein the target pose parameter includes the target mileage information.

[0015] In an example embodiment, the repositioning unit includes: a first determining module configured to determine point cloud data in the target area map corresponding to each updated pose in the set of updated poses; and a repositioning module configured to reposition the mobile robot according to a matching degree between the point cloud data corresponding to each updated pose and the second point cloud data.

[0016] In an example embodiment, the repositioning module comprises: an execution submodule for sequentially performing the following operations on each of the updated poses until a check stop condition is met, wherein in the process of performing the following operations, the updated pose is a current updated pose, and the check stop condition comprises at least one of the following: the mobile robot successfully repositions, and all updated poses have been checked; a first determination submodule for determining that the current updated pose passes the check when the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is greater than or equal to a matching degree threshold, wherein the pose to which the mobile robot repositions is the current updated pose; and a second determination submodule for determining that the current updated pose fails the check when the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is less than the matching degree threshold, wherein the pose to which the mobile robot repositions is not the current updated pose.

[0017] In an example embodiment, the repositioning module comprises: a third determination submodule for determining, as the pose to which the mobile robot repositions, an updated pose in the set of updated poses, the matching degree of the point cloud data corresponding to the updated pose and the second point cloud data being the highest and greater than or equal to a matching degree threshold.

[0018] In an example embodiment, the matching unit comprises: a second determination module for determining a set of to-be-matched grid units from the target area map, wherein the target area map is a grid map, and each to-be-matched grid unit in the set of to-be-matched grid units is a grid unit in the target area map that allows the mobile robot to enter; and a matching module for performing point cloud matching on the first point cloud data and the point cloud data corresponding to each to-be-matched grid unit to obtain the set of candidate poses.

[0019] In an example embodiment, the apparatus further comprises: a determination unit for determining a plurality of candidate moving directions, wherein each candidate moving direction in the plurality of candidate moving directions is a moving direction allowed for the mobile robot at the first position; a selection unit for selecting, from the plurality of candidate moving directions, a moving direction corresponding to the largest amount of point cloud data to obtain a target moving direction; and a control unit for controlling the mobile robot to move along the target moving direction until the second position.

[0020] According to another aspect of the embodiments of the present application, a computer readable storage medium is provided, the computer readable storage medium storing a computer program, wherein the computer program is configured to execute the robot repositioning method when running.

[0021] According to a further aspect of the embodiments of the present application, an electronic device is provided, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the robot repositioning method described above through the computer program.

[0022] In the embodiments of the present application, the first point cloud data collected by the mobile robot at the first position is matched with the target area map based on point cloud matching to obtain a group of candidate poses in the manner of first determining candidate solutions based on point cloud matching and then screening the candidate solutions through brief exploration; the second point cloud data collected by the mobile robot when moving to the second position is obtained; the target pose parameter is used to update the group of candidate poses to obtain a group of updated poses, wherein the target pose parameter is used to represent the pose change of the mobile robot when moving from the first position to the second position; and the mobile robot is repositioned using the second point cloud data and the group of updated poses. Since in the process of repositioning the robot, a plurality of candidate poses (i.e., candidate solutions) are first screened based on point cloud data, then the candidate poses are updated based on the pose change after the robot moves a distance (i.e., brief exploration), and the candidate poses are verified through the point cloud data collected at the moved position, the robot is repositioned, the candidate solutions for repositioning are screened through brief exploration, the purpose of reducing the occurrence of mismatching is achieved, the technical effect of improving the accuracy of robot repositioning is achieved, and thus the problem in the related art that the robot repositioning method has low accuracy of robot repositioning due to the easy occurrence of mismatching is solved. BRIEF DESCRIPTION OF DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application together with the specification.

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without any creative effort.

[0025] Figure 1 is a schematic diagram of a hardware environment of an optional robot repositioning method according to an embodiment of the present application;

[0026] Figure 2 is a flowchart of an optional robot repositioning method according to an embodiment of the present application;

[0027] Figure 3 is a flowchart of another optional robot repositioning method according to an embodiment of the present application;

[0028] Figure 4 This is a structural block diagram of an optional robot relocation device according to an embodiment of this application;

[0029] Figure 5 This is a structural block diagram of an optional electronic device according to an embodiment of this application.

Detailed Implementation Methods

[0030] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0032] According to one aspect of the embodiments of this application, a robot relocalization method is provided. Optionally, in this embodiment, the above-described robot relocalization method can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102, mobile robot 104, and server 106. For example... Figure 1 As shown, the terminal device 102 can connect to the mobile robot 104 and / or the server 106 (e.g., an IoT platform or a cloud server) via a network to control the mobile robot 104, such as binding to the mobile robot 104 and configuring the tasks to be performed by the mobile robot 104.

[0033] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network (WAN), metropolitan area network (MAN), local area network (LAN). The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth, infrared. The network used by terminal device 102 to communicate with mobile robot 104 and / or server 106 may be the same as or different from the network used by mobile robot 104 to communicate with server 106.

[0034] The terminal device 102 is not limited to PCs, mobile phones, tablets, etc.; the mobile robot 104 can be a cleaning robot, such as a sweeping robot, a floor washing robot, a robot that integrates washing and mopping, or other robots with cleaning functions. The mobile robot 104 can also be a delivery robot, such as a food delivery robot, a package delivery robot, or a robot that delivers other items. In this embodiment, the types of terminal devices and mobile robots are not limited.

[0035] The robot repositioning method of the embodiments of the present application can be performed by the mobile robot 104 alone, or by the mobile robot 104 together with at least one of the terminal device 102 and the server 106. Wherein, the terminal device 102 or the mobile robot 104 performing the robot repositioning method of the embodiments of the present application can also be performed by a client installed thereon.

[0036] Taking the mobile robot 104 performing the robot repositioning method in the embodiments as an example, Figure 2 is a flowchart of an optional robot repositioning method according to the embodiments of the present application, as Figure 2 shown, the flow of the method can include the following steps:

[0037] Step S202, performing point cloud matching on the first point cloud data collected by the mobile robot at the first position and the target area map, to obtain a set of candidate poses.

[0038] The robot repositioning method in the embodiments can be applied to a scenario of repositioning a robot based on point cloud data collected by a mobile robot, the mobile robot can be the aforementioned cleaning robot, delivery robot, or flight robot, or other types of robots, and the repositioning can be repositioning of the robot in an indoor environment, which is not limited herein. The repositioning can be repositioning performed after the mobile robot is picked up and then placed on the ground, or repositioning when the current position cannot be determined, or repositioning in other scenarios. The embodiments do not limit this.

[0039] Optionally, the mobile robot is provided with a perception sensor for collecting point cloud data, which can be a TOF (Time of Flight) sensor, a laser radar, a depth camera, a monocular camera, a binocular stereo camera, etc. For example, the perception sensor can be a laser radar, such as an LDS (Laser Distance Sensor) sensor. The laser radar can be a radar system that emits a laser beam to detect the position, speed, and other characteristic quantities of the target. The laser of the laser radar can convert an electrical pulse into a light pulse and emit it. The light receiver of the laser radar restores the light pulse reflected from the target into an electrical pulse and sends it to the display for display (i.e., in the form of point cloud).

[0040] In this embodiment, when the relocation needs to be performed, the mobile robot can perform point cloud data collection at a first position (for example, in place) through the perception sensor thereon to obtain first point cloud data. For example, the mobile robot can emit a laser beam to the space environment where the mobile robot is located through the light emitter of the laser radar in place, and restore the light pulse reflected from the target into an electric pulse through the light receiver of the laser radar, so as to obtain the corresponding point cloud data at the current pose of the mobile robot, that is, the first point cloud data.

[0041] After obtaining the first point cloud data, the mobile robot can perform point cloud matching between the first point cloud data and a target area map. The target area map is a region map of the target area saved by the mobile robot in advance, for example, a region map of a user's home region. When performing the point cloud matching, the first point cloud data can be projected onto the target area map according to a preset pose. If there is a position on the target area map that has a matching degree greater than or equal to a first matching threshold with the projected point cloud data, the position on the target area map and the preset pose can be taken as a candidate pose, that is, a possible pose of the mobile robot. In this way, a group of candidate poses can be obtained.

[0042] For example, when the mobile robot needs to perform the point cloud data to saved map matching relocation in place, the point cloud matching is performed through a SLAM (Simultaneous Localization and Mapping) algorithm, the pose (that is, the solution) is solved, and all candidate poses with scores exceeding a threshold, that is, candidate solutions, are reserved, so that a group of candidate solutions can be obtained.

[0043] Step S204: obtaining second point cloud data collected by the mobile robot when moving to a second position.

[0044] In this embodiment, after obtaining the first point cloud data, the mobile robot can be controlled to move. The moving direction of the mobile robot can be arbitrary or selected based on the point cloud data of each moving direction, which is not limited in this embodiment. After the mobile robot is controlled to move, the mobile robot can perform point cloud data collection through the perception sensor at the second position reached by the mobile robot to obtain second point cloud data. The perception sensor used to collect the second point cloud data can be the same as or different from the perception sensor used to collect the first point cloud data, which is not limited in this embodiment.

[0045] Step S206: updating the group of candidate poses using a target pose parameter to obtain a group of updated poses, wherein the target pose parameter is used to represent the pose change of the mobile robot when moving from the first position to the second position.

[0046] In this embodiment, during the process of controlling the mobile robot to move, the pose at which the first point cloud data is collected can be taken as an initial pose, the change in pose from the position at which the first point cloud data is collected to the position at which the second point cloud data is collected is counted, and the target pose parameter is obtained. It should be noted that the pose of the mobile robot can include the position and the attitude, and if the attitude of the mobile robot cannot be determined, the position of the mobile robot can be repositioned only, in which case the attitude of the mobile robot can be a preset attitude, for example, the mobile robot can be defaulted to be located on a plane and the attitude can be a fixed attitude.

[0047] For a set of candidate poses, the mobile robot can increase the pose change indicated by the target pose parameter on the basis of each candidate pose to obtain an updated pose corresponding to each candidate pose, thereby obtaining a set of updated poses. When each candidate pose is updated, the candidate position in each candidate pose can be increased by the position change indicated by the target pose parameter to obtain an updated position in the corresponding updated pose, and the candidate attitude in each candidate pose can be increased by the attitude change indicated by the target pose parameter to obtain an updated attitude in the corresponding updated pose, thereby obtaining the updated pose corresponding to each candidate pose.

[0048] In step S208, the mobile robot is repositioned using the second point cloud data and the set of updated poses.

[0049] In this embodiment, the set of updated poses can be verified using the second point cloud data to obtain a verification result of at least part of the updated poses, thereby obtaining a repositioning result of the mobile robot. The verification result of an updated pose is used to indicate the confidence (or possibility, reliability, etc.) of the updated pose being the pose of the mobile robot. The repositioning result can be that the mobile robot is successfully repositioned, for example, the pose to which the mobile robot is repositioned, or that the mobile robot fails to be repositioned.

[0050] There can be various ways to reposition the mobile robot using the second point cloud data and the set of updated poses. For example, the second point cloud data can be subjected to point cloud matching with the target area map to obtain a set of reference poses, and the set of reference poses can be obtained in a manner similar to that of the set of candidate poses, which will not be described herein. After obtaining the set of reference poses, the set of updated poses can be subjected to a screening operation according to the set of reference poses to reposition the mobile robot.

[0051] The way to perform the screening operation on the set of updated poses according to the set of reference poses can be to determine the matching degree, for example, the pose difference, between a reference pose in the set of reference poses and an updated pose in the set of updated poses, and to reposition the mobile robot according to the matching degree between the reference pose and the updated pose.

[0052] Optionally, the repositioning the mobile robot according to the matching degree between the reference poses and the updated poses can comprise: sequentially performing the following operations on each updated pose until a matching stop condition is met, wherein each updated pose is a current updated pose in the process of performing the following operations, and the matching stop condition comprises at least one of the following: the repositioning of the mobile robot is successful, and all updated poses have completed matching: sequentially determining the pose difference between the current updated pose and each reference pose; in a case where there is a reference pose whose pose difference with the current updated pose is less than or equal to a pose difference threshold, determining the current updated pose as the pose to which the mobile robot is repositioned.

[0053] Optionally, the repositioning the mobile robot according to the matching degree between the reference poses and the updated poses can comprise: determining the minimum pose difference between each updated pose and a reference pose in a set of reference poses, to obtain a corresponding minimum pose difference for each updated pose; and determining, as the pose to which the mobile robot is repositioned, the updated pose with the minimum corresponding minimum pose difference and the corresponding minimum pose difference being less than or equal to a pose difference threshold.

[0054] Through the steps S202 to S208, the first point cloud data collected by the mobile robot at the first position is matched with the target region map to obtain a set of candidate poses; the second point cloud data collected by the mobile robot when moving to the second position is obtained; the set of candidate poses is updated using target pose parameters to obtain a set of updated poses, wherein the target pose parameters are used to represent the pose change of the mobile robot when moving from the first position to the second position; and the mobile robot is repositioned using the second point cloud data and the set of updated poses, which solves the problem of low accuracy of robot repositioning due to the easy occurrence of mismatching in the related art, and improves the accuracy of robot repositioning.

[0055] In one example embodiment, the target pose parameters of the mobile robot are obtained in the following manner:

[0056] S11, obtaining the target mileage information generated by the mobile robot when moving from the first position to the second position through the target odometer on the mobile robot, wherein the target pose parameters comprise the target mileage information.

[0057] In this embodiment, the target pose parameter can include target odometry information, i.e., odometry information (or travel information) generated by the second position traveled from the first position. A target odometer can be arranged on the mobile robot, for example, an IMU (Inertial Measurement Unit). The target odometer can be arranged at a predetermined position of the mobile robot, for example, the chassis of the mobile robot, or other positions of the mobile robot.

[0058] During movement of the mobile robot, the target odometer can record the odometry increment generated by the movement of the mobile robot, thereby obtaining the target odometry information. The odometry increment can be obtained by integration of the IMU. The obtained target odometry information can be used as the target pose parameter, or can be used together with the pose parameter detected by other components for detecting the pose change of the mobile robot.

[0059] By this embodiment, the pose change of the mobile robot is determined by obtaining the increment of the odometer on the mobile robot, which can improve the convenience of determining the pose change.

[0060] In one example embodiment, the mobile robot is repositioned using the second point cloud data and the set of updated poses, comprising:

[0061] S21, determining point cloud data corresponding to each updated pose in the set of updated poses in the target area map;

[0062] S22, repositioning the mobile robot according to the matching degree of the point cloud data corresponding to each updated pose and the second point cloud data.

[0063] In this embodiment, the mobile robot can be repositioned according to the matching degree of the point cloud data corresponding to each updated pose in the target area map and the second point cloud data. For each updated pose, the point cloud data corresponding to each updated pose in the target area map can be determined, the matching degree of the point cloud data corresponding to each updated pose and the second point cloud data can be determined, and the mobile robot can be repositioned according to the matching degree of the point cloud data corresponding to each updated pose and the second point cloud data. The way of determining the matching degree of the two point cloud data can refer to related technologies, which is not limited in this embodiment.

[0064] According to the matching degree of the point cloud data corresponding to each updated pose and the second point cloud data, the mobile robot can be repositioned in multiple ways. The updated pose with the highest matching degree with the second point cloud data can be determined as the pose to which the mobile robot is repositioned. An updated pose with a matching degree with the second point cloud data reaching a second matching degree threshold can be determined as the pose to which the mobile robot is repositioned. Other repositioning manners can also be used, which are not limited in the embodiment.

[0065] According to the matching degree of the point cloud data corresponding to each updated pose and the second point cloud data, the mobile robot can be repositioned based on the matching degree of the point cloud data corresponding to the updated pose and the collected point cloud data. The efficiency of repositioning of the mobile robot can be improved.

[0066] In an example embodiment, the mobile robot is repositioned according to the matching degree of the point cloud data corresponding to each updated pose and the second point cloud data, including:

[0067] S31, sequentially performing the following operations on each updated pose until a check stop condition is met, wherein during the execution of the following operations, each updated pose is a current updated pose, and the check stop condition includes at least one of the following: the mobile robot is successfully repositioned, and all updated poses have completed checking:

[0068] In a case where the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is greater than or equal to the matching degree threshold, it is determined that the current updated pose passes the check, and the pose to which the mobile robot is repositioned is the current updated pose.

[0069] In a case where the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is less than the matching degree threshold, it is determined that the current updated pose fails the check, and the pose to which the mobile robot is repositioned is not the current updated pose.

[0070] In the embodiment, each updated pose can be checked according to the matching degree of the point cloud data corresponding to each updated pose and the second point cloud data. The check is whether the updated pose is the current pose of the mobile robot. For each updated pose, the following operations can be performed with the updated pose as the current updated pose until a check stop condition is met. The check stop condition includes at least one of the following: the mobile robot is successfully repositioned, and all updated poses have completed checking.

[0071] If the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is greater than or equal to the matching degree threshold, the mobile robot can be repositioned to the current updated pose. At this time, the current updated pose passes the check.

[0072] If the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is less than the matching degree threshold, it can be determined that the pose of the mobile robot is not the current updated pose, at this time, the current updated pose verification fails.

[0073] Through the embodiment, by sequentially traversing each updated pose, the matching degree of the point cloud data corresponding to the current updated pose and the point cloud data collected by the mobile robot at the current position is used to verify the current updated pose, which can improve the efficiency of the mobile robot repositioning.

[0074] In an example embodiment, the mobile robot is repositioned according to the matching degree of the point cloud data corresponding to each updated pose and the second point cloud data, comprising:

[0075] S41, among a group of updated poses, the updated pose corresponding to the point cloud data and the second point cloud data has the highest matching degree and is greater than or equal to the matching degree threshold, and the updated pose is determined as the pose of the mobile robot repositioned.

[0076] Optionally, the number of updated poses corresponding to the point cloud data and the second point cloud data in the group of updated poses can be one or more, or zero. If it is zero, at least one of the following processes can be performed: controlling the mobile robot to explore the current area as a new area, sending a repositioning failure prompt information to the terminal device matched with the mobile robot. If the number of updated poses corresponding to the point cloud data and the second point cloud data is one, the updated pose can be determined as the pose of the mobile robot repositioned.

[0077] If the number of updated poses corresponding to the point cloud data and the second point cloud data is more than one, the updated pose with the highest matching degree can be determined as the pose of the mobile robot repositioned. Optionally, the mobile robot can be controlled to re-perform short-term detection, and then the pose of the mobile robot repositioned is selected from the plurality of updated poses.

[0078] Through the embodiment, the updated pose with the highest matching degree is selected as the pose of the mobile robot repositioned according to the matching degree threshold, which can improve the accuracy of the mobile robot repositioning.

[0079] In an example embodiment, the first point cloud data collected by the mobile robot at the first position is matched with the target area map to obtain a group of candidate poses, comprising:

[0080] S51, determine a set of to-be-matched grid cells from the target area map, wherein the target area map is a grid map, and each to-be-matched grid cell in the set of to-be-matched grid cells is a grid cell in the target area map that allows the mobile robot to enter;

[0081] S52, perform point cloud matching on the first point cloud data and the point cloud data corresponding to each to-be-matched grid cell to obtain a set of candidate poses.

[0082] In this embodiment, the target area map can be a grid map, which can include a plurality of grid cells divided in advance, and the size of each grid cell can be the same. The information recorded in each grid cell of the target area map can include a passable value of each grid cell, which can have a value range of [0, 1], 0 indicating impassable and 1 indicating completely passable, in addition, the target area map can also record the size of the gap in the opening and the like.

[0083] When performing point cloud matching on the first point cloud data and the target area map, the target area map can be first screened to select the grid cells that the mobile robot can enter as the grid cells for point cloud matching with the mobile robot: a set of to-be-matched grid cells can be determined from the target area map, and each to-be-matched grid cell is a grid cell in the target area map that allows the mobile robot to enter.

[0084] For example, the grid cells with a passable value greater than or equal to a passable threshold value are determined as to-be-matched grid cells; or, the grid cells that the mobile robot can enter are determined by comparing the passable value and the size of the gap in the opening in the target area map with the size of the mobile robot.

[0085] After obtaining the set of to-be-matched grid cells, the first point cloud data can be subjected to point cloud matching with the point cloud data corresponding to each to-be-matched grid cell, thereby obtaining a set of candidate poses, and determining the set of candidate poses can be a process of solving candidate poses. Since the solving of candidate poses is changed from solving from the entire map to solving only the grid cells that allow the mobile robot to enter, the amount of data required for solving candidate poses can be reduced, and the determination efficiency of candidate poses is improved.

[0086] Through this embodiment, by screening the grid cells that the mobile robot can enter and solving candidate poses, the amount of data required for solving candidate poses can be reduced, and the determination efficiency of candidate poses is improved.

[0087] In one exemplary embodiment, the above method further includes:

[0088] S61, determine a plurality of candidate moving directions, wherein each candidate moving direction in the plurality of candidate moving directions is a moving direction allowed for the mobile robot at the first position;

[0089] S62, selecting a moving direction corresponding to the largest point cloud data from the plurality of candidate moving directions, to obtain a target moving direction;

[0090] S63, controlling the mobile robot to move along the target moving direction until the second position.

[0091] In this embodiment, when controlling the mobile robot to move, a plurality of candidate moving directions can be determined first, where the candidate moving direction is a moving direction allowed for the mobile robot at the first position, and the plurality of candidate moving directions can be obtained through the perception sensor on the mobile robot, for example, a direction corresponding to a passable width greater than the width of the mobile robot sensed by the perception sensor, or a passable direction selected from a set of preset directions, and the determination manner of the candidate moving direction is not limited in this embodiment.

[0092] For each candidate moving direction, point cloud data corresponding to each candidate moving direction can be obtained through the perception sensor on the mobile robot (the point cloud data corresponding to each candidate moving direction can also be determined from the first point cloud data); the moving direction corresponding to the largest point cloud data from the plurality of candidate moving directions is determined as the target moving direction of the mobile robot. Optionally, the mobile robot can also determine a target moving position corresponding to the target moving direction, such as a distance moved along the target moving direction.

[0093] After determining the target moving direction, the mobile robot can move along the target moving direction, and the distance of the movement can be the distance of the movement along the target moving direction determined above, or a movement distance determined according to a preset movement rule, so as to reach the second position above.

[0094] Through this embodiment, the moving direction of the mobile robot is determined according to the data amount of the corresponding point cloud data, which can improve the flexibility of the mobile robot movement control, and also improve the accuracy of the mobile robot repositioning.

[0095] The robot repositioning method in this embodiment will be explained in combination with an optional example. In this optional example, the mobile robot is an LDS robot, and the mobile robot is currently in an indoor environment (the repositioning manner in other environments is similar).

[0096] In the related art, the LDS robot performs point cloud to map matching repositioning in place. The above method only obtains the highest score solution (i.e., the robot position), and the score only looks at the proportion of points in the point cloud that can be matched to the occupied grid of the map. If all candidate solutions exceeding a certain threshold are taken, the screening cannot be completed in place.

[0097] To solve at least part of the above technical problems, provided in this alternative example is a solution to improve the relocalization performance of LDS robots in indoor environments, as shown in Figure 3 The flow of the robot relocalization method in this alternative example can include the following steps:

[0098] Step S302, the LDS robot performs point cloud to saved map matching relocalization in situ, and retains all candidate solutions whose scores exceed the threshold, i.e., the pose of the robot.

[0099] Step S304, the LDS robot performs short exploration to the new environment, and in this process, the previously retained candidate solutions are verified.

[0100] The verification process can be: when the LDS robot moves, first obtain the increment of the odometer, use the increment to obtain the radar matching priori with the candidate solution, and then use the current point cloud to obtain the updated candidate solution based on radar matching with the priori point cloud, i.e., the increment based on radar matching, compare the two increments, if the difference is small, the verification is passed; if the difference is large or the current radar matching fails, the verification fails.

[0101] Step S306, at the end of the exploration, the candidate solution is filtered, and the relocalization ends.

[0102] Through this example, the relocalization performance of the robot in the indoor environment is improved, and the possibility of invalidation of the saved map is reduced.

[0103] It should be noted that for the above-mentioned method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the order of the described actions, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0104] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software on a general hardware platform required by the software, and of course can also be implemented by hardware, but in many cases the former is a better implementation. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product in essence or the part that contributes to the prior art, and the computer software product is stored in a storage medium (such as a ROM (Read-Only Memory), a RAM (Random Access Memory), a magnetic disk, or an optical disk), and includes a number of instructions for making a terminal device (which can be a mobile phone, a computer, a server, or a network device) execute the method described in each embodiment of the present application.

[0105] According to still another aspect of the embodiments of the present application, a robot repositioning device for implementing the above robot repositioning method is further provided. Figure 4 is a structural block diagram of an optional robot repositioning device according to the embodiments of the present application, as shown in the figure, the device can include: Figure 4

[0106] The matching unit 402 is configured to perform point cloud matching on the first point cloud data collected by the mobile robot at the first position and the target area map, to obtain a group of candidate poses.

[0107] The first obtaining unit 404 is connected with the matching unit 402 and is configured to obtain second point cloud data collected by the mobile robot at the position to which the mobile robot moves.

[0108] The updating unit 406 is connected with the first obtaining unit 404 and is configured to update the group of candidate poses using target pose parameters, to obtain a group of updated poses, wherein the target pose parameters are used to represent the pose change of the mobile robot from the first position to the second position.

[0109] The repositioning unit 408 is connected with the updating unit 406 and is configured to reposition the mobile robot using the second point cloud data and the group of updated poses.

[0110] It should be noted that the matching unit 402 in this embodiment can be configured to perform the above step S202, the first obtaining unit 404 in this embodiment can be configured to perform the above step S204, the updating unit 406 in this embodiment can be configured to perform the above step S206, and the repositioning unit 408 in this embodiment can be configured to perform the above step S208.

[0111] ​The first point cloud data collected by the mobile robot at the first position is matched with the target area map through the above module to obtain a group of candidate poses. The second point cloud data collected by the mobile robot when moving to the second position is obtained. The target pose parameter is used to update the group of candidate poses to obtain a group of updated poses. The target pose parameter is used to represent the pose change of the mobile robot when moving from the first position to the second position. The mobile robot is repositioned using the second point cloud data and the group of updated poses, which solves the problem of low accuracy of robot repositioning due to the easy occurrence of mismatch in the related art, and improves the accuracy of robot repositioning.

[0112] In an example embodiment, the apparatus further includes:

[0113] The second obtaining unit is configured to obtain the target pose parameter of the mobile robot in the following manner: obtaining the mileage increment generated when the mobile robot moves from the first position to the second position through the target odometer on the mobile robot to obtain target mileage information, wherein the target pose parameter includes the target mileage information.

[0114] In an example embodiment, the repositioning unit includes:

[0115] The first determining module is configured to determine the point cloud data in the target area map corresponding to each updated pose in the group of updated poses.

[0116] The repositioning module is configured to reposition the mobile robot according to the matching degree of the point cloud data corresponding to each updated pose and the second point cloud data.

[0117] In an example embodiment, the repositioning module includes:

[0118] The execution submodule is configured to sequentially execute the following operations on each updated pose until the verification stop condition is met, wherein each updated pose is a current updated pose during execution of the following operations, and the verification stop condition includes at least one of the following: the mobile robot is successfully repositioned, and all updated poses have been verified:

[0119] In a case where the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is greater than or equal to the matching degree threshold, it is determined that the current updated pose passes the verification, and the pose to which the mobile robot is repositioned is the current updated pose.

[0120] In a case where the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is less than the matching degree threshold, it is determined that the current updated pose fails the verification, and the pose to which the mobile robot is repositioned is not the current updated pose.

[0121] In an example embodiment, the repositioning module comprises:

[0122] The determining sub-module is configured to determine, from the set of updated poses, an updated pose corresponding to the point cloud data that has the highest matching degree with the second point cloud data and is greater than or equal to the matching degree threshold, as the pose to which the mobile robot is repositioned.

[0123] In an example embodiment, the matching unit comprises:

[0124] The second determining module is configured to determine a set of to-be-matched grid units from the target area map, wherein the target area map is a grid map, and each to-be-matched grid unit in the set of to-be-matched grid units is a grid unit in the target area map that allows the mobile robot to enter;

[0125] The matching module is configured to perform point cloud matching between the first point cloud data and the point cloud data corresponding to each to-be-matched grid unit to obtain a set of candidate poses.

[0126] In an example embodiment, the apparatus further comprises:

[0127] The determining unit is configured to determine a plurality of candidate moving directions, wherein each candidate moving direction in the plurality of candidate moving directions is a moving direction allowed for the mobile robot at the first position;

[0128] The selecting unit is configured to select, from the plurality of candidate moving directions, a moving direction corresponding to the largest amount of point cloud data to obtain a target moving direction;

[0129] The control unit is configured to control the mobile robot to move along the target moving direction until the second position.

[0130] It should be noted that the above modules and examples and application scenarios implemented by the corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules as part of the apparatus can run in the hardware environment shown in Figure 1 , and can be implemented by software or hardware, wherein the hardware environment includes a network environment.

[0131] According to another aspect of the embodiments of the present application, a storage medium is provided. Optionally, in the present embodiment, the storage medium can be used to execute the program code of any of the above robot repositioning methods.

[0132] Optionally, in the present embodiment, the storage medium can be located on at least one of the plurality of network devices in the network shown in the above embodiments.

[0133] Optionally, in the embodiment, the storage medium is configured to store program code for implementing the following steps:

[0134] S1, performing point cloud matching between first point cloud data collected by the mobile robot at a first position and a target area map to obtain a set of candidate poses;

[0135] S2, obtaining second point cloud data collected by the mobile robot when moving to a second position, and obtaining a target pose parameter of the mobile robot;

[0136] S3, updating the set of candidate poses using the target pose parameter to obtain a set of updated poses, wherein the target pose parameter is used to represent a pose change of the mobile robot from the first position to the second position;

[0137] S4, repositioning the mobile robot using the second point cloud data and the set of updated poses.

[0138] Optionally, in the embodiment, the storage medium can include but is not limited to a U disk, a ROM, a RAM, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0139] According to another aspect of the embodiment of the application, an electronic device for implementing the above-mentioned robot repositioning method is also provided, which can be a server, a terminal, or a combination thereof.

[0140] Figure 5 is a structural block diagram of an optional electronic device according to the embodiment of the application, as shown in Figure 5 including a processor 502, a communication interface 504, a memory 506 and a communication bus 508, wherein the processor 502, the communication interface 504 and the memory 506 complete mutual communication through the communication bus 508, wherein,

[0141] the memory 506 is configured to store a computer program;

[0142] the processor 502 is configured to execute the computer program stored in the memory 506 to implement the following steps:

[0143] S1, performing point cloud matching between first point cloud data collected by the mobile robot at a first position and a target area map to obtain a set of candidate poses;

[0144] S2, obtaining second point cloud data collected by the mobile robot when moving to a second position;

[0145] S3, updating the set of candidate poses using the target pose parameter to obtain a set of updated poses, wherein the target pose parameter is used to represent a pose change of the mobile robot from the first position to the second position;

[0146] S4, relocalizing the mobile robot using the second point cloud data and the set of updated poses.

[0147] Optionally, in the embodiment, the communication bus can be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The communication bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 5 Only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus. The communication interface is used for communication between the electronic device and other devices.

[0148] The memory described above can include a RAM and can also include a non-volatile memory, for example, at least one disk memory. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0149] As an example, the memory 506 described above can include, but is not limited to, the matching unit 402, the first acquisition unit 404, the updating unit 406, and the relocalization unit 408 in the control device of the device described above. In addition, other module units in the control device of the device described above can also be included, but are not limited to, which will not be described in detail in the example.

[0150] The processor described above can be a general-purpose processor, which can include, but is not limited to, a CPU (Central Processing Unit), an NP (Network Processor), and the like; and can also be a DSP (Digital Signal Processing), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0151] Optionally, the specific examples in the embodiment can refer to the examples described in the above-described embodiments, which will not be described in detail in the embodiment.

[0152] Those of ordinary skill in the art can understand that, Figure 5The structure shown is only schematic, and the device implementing the above robot repositioning method can be a terminal device, which can be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, or the like. Figure 5 It does not limit the structure of the above electronic device. For example, the electronic device can further include more or fewer components (such as a network interface, a display device, etc.) than those shown in the figure, or have a different configuration from that shown in the figure. Figure 5 Figure 5 The structure shown is only schematic, and the device implementing the above robot repositioning method can be a terminal device, which can be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, or the like.

[0153] A person of ordinary skill in the art can understand that all or part of the steps of various methods in the above embodiments can be completed by instructing the hardware related to the terminal device by a program, and the program can be stored in a computer readable storage medium, which can include a flash disk, a ROM, a RAM, a magnetic disk, an optical disk, etc.

[0154] The serial numbers of the above embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0155] The integrated units in the above embodiments, if realized in the form of software function units and sold or used as independent products, can be stored in the above computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing one or more computer devices (which can be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the above method of each embodiment of the present application.

[0156] In the above embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0157] In the several embodiments provided by the present application, it should be understood that the disclosed client can be implemented in other ways. Of course, the above device embodiment is only schematic, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, unit or module, and can be electrical or other forms.

[0158] ​The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the scheme provided in the embodiment.

[0159] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0160] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled persons in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A robot repositioning method, characterized by, The method comprises the following steps: performing point cloud matching on first point cloud data collected by a mobile robot at a first position and a target area map to obtain a group of candidate poses; obtaining second point cloud data collected by the mobile robot when the mobile robot travels to a second position; updating the group of candidate poses using target pose parameters to obtain a group of updated poses, wherein the target pose parameters are used to represent a pose change of the mobile robot when the mobile robot moves from the first position to the second position; repositioning the mobile robot using the second point cloud data and the group of updated poses; wherein the repositioning of the mobile robot using the second point cloud data and the group of updated poses comprises: performing point cloud matching on the second point cloud data and the target area map to obtain a group of reference poses; after obtaining the group of reference poses, performing a screening operation on the group of updated poses according to the group of reference poses to determine a pose difference between a reference pose in the group of reference poses and an updated pose in the group of updated poses; sequentially performing the following operations on each updated pose until a matching stop condition is met, so that the mobile robot is repositioned, wherein during the performance of the following operations, each updated pose is a current updated pose, and the matching stop condition comprises at least one of the following: after the mobile robot is successfully repositioned and all updated poses have completed matching, the pose difference between the current updated pose and each reference pose is sequentially determined; in the case where there is a reference pose whose pose difference with the current updated pose is less than or equal to a pose difference threshold, the current updated pose is determined as the pose to which the mobile robot is repositioned.

2. The method of claim 1, wherein, The target pose parameters of the mobile robot are obtained in the following manner: obtaining a target mileage information by a target odometer on the mobile robot, wherein the target mileage information represents a mileage increment generated when the mobile robot moves from the first position to the second position, and the target pose parameters comprise the target mileage information.

3. The method of claim 1, wherein, The repositioning of the mobile robot using the second point cloud data and the group of updated poses further comprises: determining point cloud data in the target area map corresponding to each updated pose in the group of updated poses; repositioning the mobile robot according to a matching degree of the point cloud data corresponding to each updated pose and the second point cloud data.

4. The method of claim 3, wherein, The repositioning of the mobile robot according to the matching degree of the point cloud data corresponding to each updated pose and the second point cloud data comprises: sequentially performing the following operations on each updated pose until a verification stop condition is met, wherein during the performance of the following operations, each updated pose is a current updated pose, and the verification stop condition comprises at least one of the following: the mobile robot is successfully repositioned, and all updated poses have completed verification. In a case where the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is greater than or equal to a matching degree threshold, it is determined that the current updated pose passes the verification, and the pose to which the mobile robot is repositioned is the current updated pose. In a case where the matching degree of the point cloud data corresponding to the current updated pose and the second point cloud data is less than the matching degree threshold, it is determined that the current updated pose fails the verification, and the pose to which the mobile robot is repositioned is not the current updated pose.

5. The method of claim 3, wherein, The repositioning of the mobile robot according to the matching degrees of the point cloud data corresponding to each updated pose and the second point cloud data comprises: The updated pose in the group of updated poses, for which the matching degree of the corresponding point cloud data and the second point cloud data is the highest and greater than or equal to the matching degree threshold, is determined as the pose to which the mobile robot is repositioned.

6. The method of claim 1, wherein, The point cloud matching of the first point cloud data collected by the mobile robot at the first position and the target region map comprises: A group of to-be-matched grid units are determined from the target region map, wherein the target region map is a grid map, and each to-be-matched grid unit in the group of to-be-matched grid units is a grid unit in the target region map that allows the mobile robot to enter; The first point cloud data is subjected to point cloud matching with the point cloud data corresponding to each to-be-matched grid unit, to obtain the group of candidate poses.

7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: A plurality of candidate moving directions are determined, wherein each candidate moving direction in the plurality of candidate moving directions is a moving direction allowed for the mobile robot at the first position; A target moving direction is selected from the plurality of candidate moving directions, for which the amount of corresponding point cloud data is the largest; The mobile robot is controlled to move along the target moving direction until the second position.

8. A robotic repositioning device, characterized in that, It comprises: A matching unit is configured to perform point cloud matching of first point cloud data collected by a mobile robot at a first position and a target region map, to obtain a group of candidate poses. A first obtaining unit is configured to obtain second point cloud data collected by the mobile robot when traveling to a second position. An updating unit is configured to update the group of candidate poses using target pose parameters, to obtain a group of updated poses, wherein the target pose parameters are used to represent a pose change of the mobile robot when moving from the first position to the second position. A repositioning unit is configured to reposition the mobile robot using the second point cloud data and the group of updated poses. The repositioning of the mobile robot using the second point cloud data and the group of updated poses comprises: The second point cloud data is subjected to point cloud matching with the target region map, to obtain a group of reference poses. After obtaining the group of reference poses, a screening operation is performed on the group of updated poses according to the group of reference poses, to determine a pose difference between a reference pose in the group of reference poses and an updated pose in the group of updated poses. performing the following operations on each updated pose in sequence until a matching stop condition is met, so that the mobile robot relocalizes, wherein, in the process of performing the following operations, each updated pose is a current updated pose, and the matching stop condition comprises at least one of the following: after the mobile robot relocalization succeeds and all updated poses have completed matching, sequentially determining a pose difference between the current updated pose and each reference pose; in the case where there exists a reference pose whose pose difference with the current updated pose is less than or equal to a pose difference threshold, determining the current updated pose as the pose to which the mobile robot relocalizes.

9. A computer readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 7. 10.An electronic device comprising a memory and a processor, the electronic device characterized by, The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 7 by using the computer program. The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 7 by using the computer program.

Images