CN-116641532-B - Intelligent control method and device for mechanical arm based on dynamic vision and brick laying robot

CN116641532BCN 116641532 BCN116641532 BCN 116641532BCN-116641532-B

Abstract

The invention discloses a dynamic vision-based intelligent control method and device for a mechanical arm and a brick laying robot, wherein the mechanical arm is arranged on the brick laying robot, and a camera is arranged on the brick laying robot; and when the brick paving robot reaches the second brick paving point, determining the movement control parameters of the mechanical arm based on the image information of the brick to be paved acquired by the camera, and controlling the mechanical arm to execute the operation matched with the movement control parameters. Therefore, the intelligent movement control of the mechanical arm of the brick laying robot can be realized based on dynamic vision, and the efficiency and the accuracy of brick laying operation of the brick laying robot are improved.

Inventors

KUANG ZHONG
Li Feipian
LIU DAWEI
LIU HAIQIN

Assignees

广东博智林机器人有限公司

Dates

Publication Date: 20260508
Application Date: 20221130

Claims (8)

1. The utility model provides a mechanical arm intelligent control method based on dynamic vision which characterized in that, the mechanical arm is installed on the tiling robot, install the camera on the tiling robot, the method includes: Determining target compensation information of the brick paving robot based on the posture information of the brick paving robot acquired by the camera in the process that the brick paving robot moves to a first brick paving point, wherein the posture information of the brick paving robot comprises brick grabbing posture information of the brick paving robot and/or chassis posture information of the brick paving robot, and the first brick paving point is a brick paving point corresponding to a target moving track generated by a track simulation model; performing correction operation on the first brick paving point according to the target compensation information to obtain a second brick paving point, and controlling the brick paving robot to move to the second brick paving point; When the brick paving robot reaches the second brick paving point, determining movement control parameters of the mechanical arm based on the to-be-paved environment image information acquired by the camera, and controlling the mechanical arm to execute the operation matched with the movement control parameters; Before the tiling robot moves to the first tiling point, the method further comprises: acquiring target environment information corresponding to a position of a brick to be paved, and inputting the target environment information and structural information of the brick paving robot into a preset track simulation model to obtain a target moving track of the brick paving robot, wherein the target moving track comprises a target brick taking point and a first brick paving point; Controlling the brick laying robot to move to the target brick taking point based on the target moving track, and controlling the brick laying robot to execute brick grabbing operation when the brick laying robot reaches the target brick taking point; Judging whether the brick laying robot finishes brick grabbing operation or not; When the brick laying robot is judged to finish the brick grabbing operation, controlling the brick laying robot to move to the first brick laying point; When judging that the brick-laying robot does not complete the brick-grabbing operation, re-triggering and executing the steps of controlling the brick-laying robot to execute the brick-grabbing operation and judging whether the brick-laying robot has completed the brick-grabbing operation; The mechanical arm is provided with a sucker which is used for grabbing bricks; The judging whether the brick laying robot finishes brick grabbing operation or not comprises the following steps: acquiring a vacuum value of the sucker, and judging whether the vacuum value is larger than a preset vacuum threshold; When the vacuum value is judged to be larger than the preset vacuum threshold value, determining that the brick laying robot has completed brick grabbing operation; And when the vacuum value is not larger than the preset vacuum threshold value, determining that the brick-laying robot does not complete the brick-grabbing operation.
2. The dynamic vision-based mechanical arm intelligent control method according to claim 1, wherein when the posture information of the brick laying robot includes the brick gripping posture information of the brick laying robot, the determining the target compensation information of the brick laying robot based on the posture information of the brick laying robot acquired by the camera includes: based on the brick grabbing posture information of the brick paving robot acquired by the camera, judging whether the brick grabbing posture information meets preset brick grabbing posture conditions or not; When the brick grabbing posture information is judged to not meet the preset brick grabbing posture condition, acquiring first environment information of the first brick paving point; Determining first error information of the brick laying robot according to the brick grabbing posture information and the first environment information, and generating first compensation information based on the first error information, wherein the first error information is error information generated by the brick laying robot in the process of executing the brick grabbing operation; And determining target compensation information of the brick laying robot according to the first compensation information.
3. The intelligent control method of a mechanical arm based on dynamic vision according to claim 1, wherein when the posture information of the brick laying robot includes chassis posture information of the brick laying robot, the determining target compensation information of the brick laying robot based on the posture information of the brick laying robot acquired by the camera includes: Judging whether the chassis posture information meets preset chassis posture conditions or not based on the chassis posture information, which is acquired by the camera and is aimed at the brick laying robot; when the chassis posture information is judged to not meet the preset chassis posture condition, determining a chassis inclination coefficient of the brick laying robot according to the chassis posture information of the brick laying robot; Determining second error information of the brick laying robot based on the chassis inclination coefficient of the brick laying robot, and generating second compensation information based on the second error information, wherein the second error information is the chassis inclination error information of the brick laying robot; And determining target compensation information of the brick laying robot according to the second compensation information.
4. The intelligent control method of the mechanical arm based on dynamic vision according to any one of claims 1 to 3, wherein the determining the control parameters of the mechanical arm based on the image information of the environment to be tiled acquired by the camera includes: based on the real-time image information of the target object acquired by the camera, calculating the brick joint distance between a first brick site corresponding to the brick to be paved and a predetermined reference object, and judging whether the brick joint distance meets a preset brick joint condition; When the brick joint distance is judged to not meet the preset brick joint condition, determining a dynamic tracking parameter of the mechanical arm according to the brick joint distance and the first brick joint point; generating a movement control parameter of the mechanical arm according to the dynamic tracking parameter, wherein the dynamic tracking parameter is used for representing a dynamic relative position relationship between the mechanical arm and the first brick site; and controlling the mechanical arm to execute the operation matched with the movement control parameter, including: and controlling the mechanical arm to move based on the movement control parameters so that the brick joint distance between the first brick site corresponding to the brick to be paved and the predetermined reference object meets the preset brick joint condition.
5. The intelligent control method of a mechanical arm based on dynamic vision according to claim 4, wherein after the brick laying robot reaches the second brick laying point, before determining the control parameters of the mechanical arm based on the environmental image information to be brick laid acquired by the camera, the method further comprises: the method comprises the steps of controlling a camera to acquire environmental image information of a brick to be paved, determining a brick paving position relation between the mechanical arm and the ground of the brick to be paved based on a visual servo technology and the environmental image information of the brick to be paved, and judging whether the brick paving position relation meets a preset position condition or not, wherein the brick paving position relation is used for representing the relative position relation between the mechanical arm and bricks included in the ground of the brick to be paved; when the brick laying position relation is judged to not meet the preset position condition, triggering and executing the operation of determining the control parameters of the mechanical arm based on the image information of the brick laying environment to be laid acquired by the camera; and when judging that the brick laying position relation meets the preset position condition, controlling the brick laying robot to execute brick laying operation.
6. Mechanical arm intelligent control device based on dynamic vision, a serial communication port, the device is applied to the tiling robot, the mechanical arm is installed on the tiling robot, install the camera on the tiling robot, the device includes: the system comprises a determination module, a control module and a control module, wherein the determination module is used for determining target compensation information of the brick laying robot based on the posture information of the brick laying robot acquired by the camera in the process of moving the brick laying robot to a first brick laying point, wherein the posture information of the brick laying robot comprises brick grabbing posture information of the brick laying robot and/or chassis posture information of the brick laying robot, and the first brick laying point is a brick laying point corresponding to a target moving track generated by a track simulation model; the correction module is used for executing correction operation on the first brick paving point according to the target compensation information to obtain a second brick paving point; the control module is used for controlling the brick laying robot to move to the second brick laying point; the determining module is further used for determining movement control parameters of the mechanical arm based on the image information of the environment to be paved, which is acquired by the camera, when the brick paving robot reaches the second brick paving point; the control module is also used for controlling the mechanical arm to execute the operation matched with the movement control parameters, and the environment image information of the brick to be paved comprises real-time image information of a target object; The acquisition module is used for acquiring target environment information corresponding to the position of the brick to be paved before the brick paving robot moves to the first brick paving point; The input module is used for inputting the target environment information and the structural information of the brick laying robot into a preset track simulation model to obtain a target moving track of the brick laying robot, wherein the target moving track comprises a target brick taking point and a first brick laying point; The control module is further used for controlling the brick laying robot to move to the target brick taking point based on the target moving track, and controlling the brick laying robot to execute brick grabbing operation when the brick laying robot reaches the target brick taking point; When judging that the brick laying robot does not finish the brick grabbing operation, re-triggering the control module to execute the operation for controlling the brick laying robot to execute the brick grabbing operation and judging whether the brick laying robot finishes the brick grabbing operation; the control module is further used for controlling the brick laying robot to move to the first brick laying point when the judging module judges that the brick grabbing operation of the brick laying robot is finished; The mechanical arm is provided with a sucker which is used for grabbing bricks; the specific mode for judging whether the brick laying robot finishes brick grabbing operation or not by the judging module comprises the following steps: acquiring a vacuum value of the sucker, and judging whether the vacuum value is larger than a preset vacuum threshold; When the vacuum value is judged to be larger than the preset vacuum threshold value, determining that the brick laying robot has completed brick grabbing operation; And when the vacuum value is not larger than the preset vacuum threshold value, determining that the brick-laying robot does not complete the brick-grabbing operation.
7. Mechanical arm intelligent control device based on dynamic vision, characterized in that, the device is applied to tiling robot, the device includes: A memory storing executable program code; A processor coupled to the memory; The processor invokes the executable program code stored in the memory to perform the dynamic vision-based robotic arm intelligent control method of any one of claims 1-5.
8. The brick laying robot is characterized in that the mechanical arm is arranged on the brick laying robot, and a camera is arranged on the brick laying robot; wherein the tiling robot is used for executing the intelligent control method of the mechanical arm based on dynamic vision as claimed in any one of claims 1 to 5.

Description

Intelligent control method and device for mechanical arm based on dynamic vision and brick laying robot Technical Field The invention relates to the technical field of intelligent control, in particular to a mechanical arm intelligent control method and device based on dynamic vision and a brick laying robot. Background Along with development of science and technology, automatic paving can be realized by a paving robot instead of the traditional manual paving in the building direction, so that the paving efficiency is greatly improved. Most of the existing paving robots adopt visual detection, and the mechanical arm of the paving robot is controlled based on the visual detection result to realize the paving operation, so that the paving robot has low efficiency in the paving process. It is important to provide a novel intelligent control method for paving bricks by using a mechanical arm to improve the paving efficiency of a paving robot. Disclosure of Invention The invention aims to solve the technical problem of providing a dynamic vision-based intelligent control method and device for a mechanical arm and a brick laying robot, which can realize intelligent movement control of the mechanical arm of the brick laying robot based on dynamic vision, and are beneficial to improving the efficiency of brick laying operation of the brick laying robot and the accuracy of brick laying operation of the brick laying robot. In order to solve the technical problem, a first aspect of the invention discloses an intelligent control method of a mechanical arm based on dynamic vision, wherein the mechanical arm is arranged on a brick laying robot, a camera is arranged on the brick laying robot, and the method comprises the following steps: Determining target compensation information of the brick paving robot based on the posture information of the brick paving robot acquired by the camera in the process that the brick paving robot moves to a first brick paving point, wherein the posture information of the brick paving robot comprises brick grabbing posture information of the brick paving robot and/or chassis posture information of the brick paving robot, and the first brick paving point is a brick paving point corresponding to a target moving track generated by a track simulation model; performing correction operation on the first brick paving point according to the target compensation information to obtain a second brick paving point, and controlling the brick paving robot to move to the second brick paving point; When the brick paving robot reaches the second brick paving point, determining movement control parameters of the mechanical arm based on the brick paving environment image information to be acquired by the camera, and controlling the mechanical arm to execute the operation matched with the movement control parameters, wherein the brick paving environment image information comprises real-time image information of a target object. As an alternative embodiment, in the first aspect of the present invention, before the tile robot moves to the first tile point, the method further comprises: acquiring target environment information corresponding to a position of a brick to be paved, and inputting the target environment information and structural information of the brick paving robot into a preset track simulation model to obtain a target moving track of the brick paving robot, wherein the target moving track comprises a target brick taking point and a first brick paving point; Controlling the brick laying robot to move to the target brick taking point based on the target moving track, and controlling the brick laying robot to execute brick grabbing operation when the brick laying robot reaches the target brick taking point; Judging whether the brick laying robot finishes brick grabbing operation or not; When the brick laying robot is judged to finish the brick grabbing operation, controlling the brick laying robot to move to the first brick laying point; and when judging that the brick-grabbing operation is not completed by the brick-laying robot, re-triggering and executing the steps of controlling the brick-laying robot to execute the brick-grabbing operation and judging whether the brick-grabbing operation is completed by the brick-laying robot. As an optional implementation manner, in the first aspect of the present invention, when the pose information of the brick laying robot includes the brick grabbing pose information of the brick laying robot, the determining, based on the pose information of the brick laying robot acquired by the camera, target compensation information of the brick laying robot includes: based on the brick grabbing posture information of the brick paving robot acquired by the camera, judging whether the brick grabbing posture information meets preset brick grabbing posture conditions or not; When the brick grabbing posture information is judged to not meet the preset brick grabbing posture co