Search

CN-121977577-A - Inspection robot inspection action planning method and device, electronic equipment and medium

CN121977577ACN 121977577 ACN121977577 ACN 121977577ACN-121977577-A

Abstract

The application provides a routing inspection action planning method, a routing inspection robot, a routing inspection action planning device, electronic equipment and a medium for determining the freeness description information of the routing inspection robot, determining a camera feasible region of the routing inspection robot based on routing inspection paths, base movable information and camera movable information of the routing inspection robot, determining an ideal camera position of the routing inspection robot based on the camera feasible region and target object information of a target object to be acquired, determining at least one pose information of the routing inspection robot based on the ideal camera position, determining corresponding load state information and camera state information for each pose information, determining at least one action planning information combination, screening out the target action planning combination from the at least one action planning information combination, adjusting the routing inspection robot based on the target action planning combination, and acquiring a target image of the target object. Therefore, the inspection robot inspection action planning efficiency and the image acquisition accuracy can be improved.

Inventors

  • WU WEITONG

Assignees

  • 深圳市其域创新科技有限公司

Dates

Publication Date
20260505
Application Date
20260402

Claims (10)

  1. 1. The inspection action planning method of the inspection robot is characterized by comprising the following steps of: The method comprises the steps of determining the degree of freedom description information of the inspection robot, wherein the degree of freedom description information comprises base movable information of the inspection robot, camera movable information of the inspection robot and camera imaging parameters of a camera; Determining target object information of a target object of an image to be acquired and a patrol path of the patrol robot; Determining a camera feasible region of the inspection robot based on the inspection path, the base movable information and the camera movable information; determining an ideal camera position of the inspection robot based on the camera feasible region and the target object information; Determining at least one pose information of the inspection robot based on the ideal camera position, determining corresponding load state information and camera state information for each of the pose information, and combining the pose information, the load state information and the camera state information to determine at least one action planning information combination; And screening out a target action planning combination from at least one action planning information combination, and acquiring a target image of the target object after adjusting the pose, the load state and the camera state of the inspection robot based on the target action planning combination.
  2. 2. The inspection action planning method according to claim 1, wherein the determining a camera feasible region of the inspection robot based on the inspection path, the base movable information, and the camera movable information includes: And determining a camera feasible region of the inspection robot based on the position information of the camera of the inspection robot on the inspection path, the inspection path and the movable range of the camera, which is characterized in the camera movable information.
  3. 3. The inspection behavior planning method according to claim 1, wherein the target object information includes a target object center of the target object and directivity attribute information of the target object, wherein the determining an ideal camera position of the inspection robot based on the camera feasible region and the target object information includes: If the directivity attribute information indicates that the target object is a target object with directivity attribute, determining a normal ray based on the center of the target object and a normal vector of a main surface; Detecting whether an intersection point exists between the normal ray and the camera feasible region; If an intersection point exists between the normal ray and the camera feasible region, determining the position of the intersection point between the normal ray and the camera feasible region as the ideal camera position; If no intersection point exists between the normal ray and the camera feasible region, determining the ideal camera position in the camera feasible region according to an incident angle.
  4. 4. The inspection action planning method of claim 3, wherein the determining an ideal camera position of the inspection robot based on the camera feasible region and the target information further comprises: If the directivity attribute information indicates that the target object is a target object without directivity attribute, determining the position closest to the position of the target object in the camera feasible region as the ideal camera position, or And determining at least one projection position of the target object in the camera feasible region, and determining the projection position with the largest area in the projection positions as the ideal camera position.
  5. 5. The inspection action planning method of claim 1, wherein the determining at least one pose information of the inspection robot based on the ideal camera position comprises: and in the preset range of the ideal camera position, discrete sampling is carried out on the path position and the base orientation based on the inspection path and the base movable information, and at least one pose information of the inspection robot is determined.
  6. 6. The inspection behavior planning method according to claim 1, wherein the determining, for each of the pose information, the corresponding load state information and camera state information includes: Solving the pose information based on the structure of the inspection robot to determine the load state information; determining an adjustment position vector based on a target object center of the target object, a camera position of the camera; Determining a horizontal rotation angle and a vertical pitch angle of the camera based on the adjustment position vector; an optical zoom value of the camera is determined based on the camera imaging parameters.
  7. 7. The inspection activity planning method of claim 1 wherein said screening out a target activity planning combination from at least one of said activity planning information combinations comprises: for each action planning information combination, determining a base deviation routing path value, a camera position deviation value between a camera position and the ideal camera position and an incidence angle cost value corresponding to the action planning information combination; aiming at each action planning information combination, calculating candidate evaluation cost values corresponding to the action planning information combination according to the base deviation routing inspection path value, the camera position deviation value and the incidence angle cost value of the action planning information combination by a preset weight coefficient; And determining the action planning information combination with the minimum corresponding candidate evaluation cost value as the target action planning combination from at least one action planning information combination.
  8. 8. The utility model provides a patrol and examine action planning device of robot, its characterized in that, patrol and examine action planning device includes: The system comprises a degree of freedom description information determining module, a degree of freedom description information determining module and a camera processing module, wherein the degree of freedom description information determining module is used for determining degree of freedom description information of the inspection robot, and the degree of freedom description information comprises base movable information of the inspection robot, camera movable information of the inspection robot and camera imaging parameters of the camera; The inspection target determining module is used for determining target object information of a target object of an image to be acquired and an inspection path of the inspection robot; The camera feasible region determining module is used for determining a camera feasible region of the inspection robot based on the inspection path, the base movable information and the camera movable information; an ideal camera position determining module, configured to determine an ideal camera position of the inspection robot based on the camera feasible region and the target object information; a motion planning information combination determining module, configured to determine at least one pose information of the inspection robot based on the ideal camera position, determine, for each of the pose information, corresponding load state information and camera state information, and combine the pose information, the load state information and the camera state information to determine at least one motion planning information combination; And the action planning information combination screening module is used for screening out a target action planning combination from at least one action planning information combination, and collecting a target image of the target object after adjusting the pose, the load state and the camera state of the inspection robot based on the target action planning combination.
  9. 9. An electronic device comprising a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating over the bus when the electronic device is in operation, the processor executing the machine-readable instructions to perform the steps of the inspection action planning method of the inspection robot according to any one of claims 1 to 7.
  10. 10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, which when executed by a processor performs the steps of the inspection action planning method of an inspection robot according to any one of claims 1 to 7.

Description

Inspection robot inspection action planning method and device, electronic equipment and medium Technical Field The application relates to the technical field of robot control, in particular to a method, a device, electronic equipment and a medium for planning inspection actions of an inspection robot. Background The inspection robot can be applied to different industrial fields or intelligent fields, and for industrial facilities such as a large number of factory workshops and power substations, the inspection robot can be used for acquiring images of various targets needing visual inspection such as instrument panels, indicator lamps, valves, nameplates and insulators of the industrial facilities, so that the operation condition of the industrial facilities can be analyzed according to the acquired images. In the prior art, the inspection action planning of the inspection robot is generally set in advance according to planning experience by staff, the inspection robot set in the setting mode cannot adapt to different acquisition scenes and acquisition types, different inspection action planning schemes are required to be set for the inspection robots of different types, so that the inspection action planning efficiency of the inspection robot is lower, meanwhile, the quality of acquisition of the set inspection robot for a target object is not fixed according to the difference of experience of the staff of the inspection robot, and the image acquisition accuracy of the inspection robot is further influenced. Disclosure of Invention In view of the above, the present application aims to provide a method, an apparatus, an electronic device and a medium for planning an inspection robot, which automatically determine a camera feasible region of the inspection robot by constructing degree of freedom description information of the inspection robot and combining target object information of a target object to be acquired with an image and an inspection path of the inspection robot, determine an ideal camera position with an optimal acquisition effect by the camera feasible region, and further determine pose information, load state information and camera state information of the inspection robot according to the ideal camera position, and finally determine an optimal target action planning combination, thereby reducing the problems that manual planning cannot be combined with error of a specific acquisition scene and planning efficiency of manual inspection for different types of inspection robots is low, and improving the inspection robot inspection action planning efficiency and image acquisition accuracy. In a first aspect, an embodiment of the present application provides a method for planning a patrol action of a patrol robot, where the method for planning a patrol action includes: The method comprises the steps of determining the degree of freedom description information of the inspection robot, wherein the degree of freedom description information comprises base movable information of the inspection robot, camera movable information of the inspection robot and camera imaging parameters of a camera; Determining target object information of a target object of an image to be acquired and a patrol path of the patrol robot; Determining a camera feasible region of the inspection robot based on the inspection path, the base movable information and the camera movable information; determining an ideal camera position of the inspection robot based on the camera feasible region and the target object information; Determining at least one pose information of the inspection robot based on the ideal camera position, determining corresponding load state information and camera state information for each of the pose information, and combining the pose information, the load state information and the camera state information to determine at least one action planning information combination; And screening out a target action planning combination from at least one action planning information combination, and acquiring a target image of the target object after adjusting the pose, the load state and the camera state of the inspection robot based on the target action planning combination. In one possible implementation manner, the determining the camera feasible region of the inspection robot based on the inspection path, the base movable information and the camera movable information includes: And determining a camera feasible region of the inspection robot based on the position information of the camera of the inspection robot on the inspection path, the inspection path and the movable range of the camera, which is characterized in the camera movable information. In one possible implementation, the target object information includes a target object center of the target object and directional attribute information of the target object, and the determining, based on the camera feasible region and the target object information, an id