CN-120472433-B - Control method, equipment and storage medium of wall surface identification system

CN120472433BCN 120472433 BCN120472433 BCN 120472433BCN-120472433-B

Abstract

The application discloses a control method, equipment and storage medium of a wall surface identification system, and relates to the technical field of sensor positioning, wherein the method comprises the steps of determining target point cloud data corresponding to a wall surface according to a wall surface dividing line in the point cloud data; the method comprises the steps of determining a boundary point set of target point cloud data on a horizontal projection plane, traversing all subsets of the boundary point set, determining circumcircles corresponding to the subsets to obtain a circumcircle sequence, determining the minimum circumcircle surrounding the boundary point set in the circumcircle sequence, comparing the radius of the minimum circumcircle with a preset radius threshold, and generating obstacle detection information according to a comparison result. According to the application, the wall surface is judged by carrying out transverse straight line detection by the top laser radar and identifying the vertical direction of the wall surface by the multi-frame line laser, and then the recognition of the wall surface obstacle is carried out based on the algorithm of the method, so that the recognition capability of the floor sweeping robot on the wall surface obstacle is improved.

Inventors

DENG JIANDING
ZHONG JINGWEI
Request for anonymity
Request for anonymity

Assignees

深圳市亿道电子科技有限公司

Dates

Publication Date: 20260508
Application Date: 20250630

Claims (7)

1. A method for controlling a wall surface recognition system, the method comprising: Performing straight line fitting on the acquired point cloud data through a random sampling consistency algorithm, generating a plurality of random straight lines, and selecting the straight line with the highest internal point occupation ratio as an initial base line; splitting a part, in the initial baseline, of which the angle variation is larger than a preset angle variation threshold value into a plurality of sub-line segments; Based on the initial baseline and the plurality of sub-line segments, carrying out local correction on the initial baseline to generate a wall boundary; dividing the point cloud data into first point cloud data and second point cloud data based on the wall surface dividing line; Based on horizontal laser vertically irradiated to the wall surface in the transverse direction of the top laser radar, judging that a projection result corresponding to the horizontal laser intersects with partial point cloud data on one side of the straight line segment according to the projection result of the horizontal laser irradiation, wherein the partial point cloud data is identified as target point cloud data, and the partial point cloud data on the other side of the straight line segment is identified as ground point cloud data; Determining a boundary point set of the target point cloud data on a horizontal projection plane; Traversing all subsets of the boundary point set, and determining circumscribed circles corresponding to the subsets to obtain a circumscribed circle sequence, wherein the subsets comprise preset number of boundary points; determining a minimum circumscribed circle surrounding the boundary point set in the circumscribed circle sequence; based on the radius corresponding to each minimum circumscribing circle, comparing and judging with the radius threshold value, and determining each target circumscribing circle with the radius smaller than the radius threshold value; Establishing coordinates on a horizontal projection plane based on point clouds covered by all target circumscribing circles; determining the center coordinates of the target circumcircle on the horizontal projection plane through a coordinate system constructed on the horizontal projection plane; Based on the generated center coordinates, combining temporary obstacle judging conditions in preset obstacle judging conditions, and filtering out the center coordinates as temporary obstacles when the center coordinates are identified to dynamically pass.
2. The method for controlling a wall surface recognition system according to claim 1, wherein the step of filtering out the center coordinates as temporary obstacles when the center coordinates are recognized to dynamically pass by, based on the generated center coordinates, in combination with temporary obstacle judgment conditions among preset obstacle judgment conditions, further comprises: Calculating the distance between any two adjacent circle center coordinates based on each circle center coordinate in the obstacle detection information to obtain a plurality of circle center distances; Comparing and screening a plurality of circle center distances, and taking the circle center distance with the largest corresponding value as a target distance; and comparing the target distance with a preset distance threshold value, and determining a wall surface recognition result according to the comparison result.
3. The method of controlling a wall surface recognition system according to claim 2, wherein the step of determining the wall surface recognition result based on the comparison result comprises: if the comparison result shows that the target distance is smaller than the distance threshold, issuing a wall surface identification result comprising a wall surface detection success notification and the target point cloud data so as to identify that the wall surface detection accords with a preset protection rule; and if the comparison result shows that the target distance is larger than the distance threshold, issuing the wall surface identification result comprising a wall surface detection failure notification so as to identify that the wall surface does not accord with a preset protection rule.
4. The method for controlling a wall surface recognition system according to claim 1, wherein the step of generating the wall surface dividing line by locally correcting the initial baseline based on the initial baseline and the plurality of sub-line segments further comprises, before: Based on the laser irradiation of the line laser radar perpendicular to the ground and the transverse laser irradiation of the top laser radar, generating a projection result corresponding to the line laser radar and a transverse projection result corresponding to the top laser radar; and identifying and judging the projection result and the transverse projection result, and if the projection result and the transverse projection result are both straight lines, obtaining a wall surface at a sampling position in the projection result.
5. The method for controlling a wall surface recognition system according to claim 1, wherein the step of determining the set of boundary points of the target point cloud data on the horizontal projection plane further comprises: forming a projection surface based on a line laser straight line projected by the line laser radar and combining a transverse projection result of the top laser radar; based on the projection plane, controlling the robot to move along the direction parallel to the wall surface to obtain a multi-time sequence projection plane; and projecting on a horizontal plane according to the multi-time sequence projection plane to generate the horizontal projection plane.
6. A wall surface identification device, characterized in that it comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the method of controlling a wall surface identification system according to any one of claims 1 to 5.
7. A storage medium, characterized in that the storage medium is a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, realizes the steps of the control method of the wall surface identification system according to any one of claims 1 to 5.

Description

Control method, equipment and storage medium of wall surface identification system Technical Field The present application relates to the field of sensor positioning technologies, and in particular, to a method, an apparatus, and a storage medium for controlling a wall surface recognition system. Background The core function of the robot is autonomous navigation and obstacle avoidance, while wall surface recognition is a key technology for achieving the goal, and meanwhile, the wall surface is not only a boundary of a cleaning path, but also various obstacles exist. In the related art, a floor sweeping robot generally arranges a wall surface recognition sensor near the axis of a driving wheel, so that the collection surface of point cloud is smaller, and further, the accuracy of obstacle recognition is poor. The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present application and is not intended to represent an admission that the foregoing is prior art. Disclosure of Invention The application mainly aims to provide a control method, equipment and storage medium of a wall surface recognition system, and aims to solve the technical problem that a sweeping robot is limited by a physical installation position and a detection view angle of a sensor in the related art, so that the recognition sensor cannot provide complete wall surface information, and the sweeping robot collides with an obstacle. In order to achieve the above object, the present application provides a method for a multi-sensor time-sequence wall surface recognition system, the method comprising: Determining target point cloud data corresponding to the wall surface according to the wall surface dividing line in the point cloud data; Determining a boundary point set of the target point cloud data on a horizontal projection plane; Traversing all subsets of the boundary point set, and determining circumscribed circles corresponding to the subsets to obtain a circumscribed circle sequence, wherein the subsets comprise preset number of boundary points; determining a minimum circumscribed circle surrounding the boundary point set in the circumscribed circle sequence; and comparing the radius of the minimum circumscribing circle with a preset radius threshold value, and generating obstacle detection information according to a comparison result. In one embodiment, the collected point cloud data is subjected to straight line fitting through a random sampling consistency algorithm, multiple times of random straight line generation is carried out, and a straight line with the highest internal point occupation ratio is selected as an initial base line; splitting a part, in the initial baseline, of which the angle variation is larger than a preset angle variation threshold value into a plurality of sub-line segments; and carrying out local correction on the initial baseline based on the initial baseline and the plurality of sub-line segments to generate the wall surface dividing line. In an embodiment, the point cloud data is divided into first point cloud data and second point cloud data based on the wall surface dividing line; and combining a transverse projection result of the top laser radar, and determining the part, higher than the ground, of the first point cloud data and the second point cloud data as the target point cloud data. In an embodiment, based on the radius corresponding to each minimum circumscribing circle, comparing and judging with the radius threshold value, determining each target circumscribing circle with the radius smaller than the radius threshold value; According to each target circumscribing circle, combining the horizontal projection plane, and determining the center coordinates of each target circumscribing circle; and generating the obstacle detection information comprising the circle center coordinates based on the circle center coordinates of the target circumscribing circle. In an embodiment, based on each circle center coordinate in the obstacle detection information, performing distance calculation on any two adjacent circle center coordinates to obtain a plurality of circle center distances; Comparing and screening a plurality of circle center distances, and taking the circle center distance with the largest corresponding value as a target distance; and comparing the target distance with a preset distance threshold value, and determining a wall surface recognition result according to the comparison result. In an embodiment, if the comparison result shows that the target distance is smaller than the distance threshold, the wall surface recognition result including a wall surface detection success notification and the target point cloud data is issued to identify that the wall surface detection meets a preset protection rule; and if the comparison result shows that the target distance is larger than the distance threshold, issuing the wall surface identificati