Search

CN-116100537-B - Robot control method, robot, storage medium and grabbing system

CN116100537BCN 116100537 BCN116100537 BCN 116100537BCN-116100537-B

Abstract

The application discloses a control method of a robot, the robot, a storage medium and a grabbing system. The method comprises the steps of obtaining an image of a target area, identifying the image by utilizing a YOLO algorithm to determine the target position of a target object in the image, generating a target instruction based on the target position, calculating a running track in a pulse neural network based on the target instruction, and controlling a robot to grasp the target object according to the running track. Through the mode, the robot based on the pulse neural network has the function of image recognition, and the robot is more intelligent.

Inventors

  • CHEN XIN
  • LI XIAOJIAN

Assignees

  • 中国科学院深圳先进技术研究院

Dates

Publication Date
20260508
Application Date
20211111

Claims (5)

  1. 1. A method of controlling a robot, the method comprising: Analyzing the acquired electroencephalogram signals of the user to obtain corresponding analysis signals, wherein the analysis signals are used for representing grabbing target objects; acquiring a first image and a second image of the target area according to the analysis signal; Identifying the first image using a YOLO algorithm or an image recognition model trained based on the YOLO algorithm to determine a first target location of the target item in the first image, and identifying the second image to determine a second target location of the target item in the second image; determining an initial third target position; acquiring a parameter matrix of image acquisition equipment corresponding to the first image or the second image; obtaining a plurality of fourth target positions by using the initial third target position and the parameter matrix, wherein Newton method is adopted to determine the fourth target positions; when any one of the fourth target positions and the first target position meet a preset condition, and any one of the fourth target positions and the second target position meet a preset condition, determining the initial third target position as a final third target position; Generating a target instruction based on the third target position, and calculating a running track in a pulse neural network based on the target instruction; and controlling the robot to grasp the target object according to the running track, and moving the robot to a user.
  2. 2. The method of claim 1, wherein controlling the robot to grasp the target object according to the trajectory comprises: generating a first instruction according to a running track, wherein the first instruction is used for controlling the robot to move to a first position on the running track; acquiring feedback data of the robot moving to the first position; Calculating trajectory correction data in the impulse neural network based on the first instruction and the feedback data; and generating a second instruction according to the running track, wherein the second instruction and the track correction data are used for controlling the robot to move from the first position to a second position on the running track, and further controlling a mechanical arm of the robot to grasp the target object.
  3. 3. A robot comprising a processor and a memory coupled to the processor; Wherein the memory is for storing a computer program, the processor being for executing the computer program to implement the method of any of claims 1-2.
  4. 4. A computer readable storage medium for storing a computer program for implementing the method according to any one of claims 1-2 when executed by a processor.
  5. 5. A grasping system, characterized in that the grasping system comprises: The image acquisition device is used for acquiring a first image and a second image of a target area according to an analysis signal, wherein the analysis signal is obtained by analyzing the acquired brain electrical signals of a user; The controller is connected with the image acquisition device and is used for identifying the first image by utilizing a YOLO algorithm or an image identification model trained based on the YOLO algorithm so as to determine a first target position of the target object in the first image, identifying the second image so as to determine a second target position of the target object in the second image, determining an initial third target position, acquiring a parameter matrix of image acquisition equipment corresponding to the first image or the second image, acquiring a plurality of fourth target positions by utilizing the initial third target position and the parameter matrix, determining the fourth target position by adopting a Newton method, determining the initial third target position as a final third target position when any one of the fourth target position and the first target position meets a preset condition, and determining the initial third target position as the final third target position when any one of the fourth target position and the second target position meets the preset condition, generating a target instruction based on the third target position, and calculating a pulse track in a neural network based on the target instruction; and the robot is connected with the controller and used for grabbing the target object according to the running track and moving the target object to a user.

Description

Robot control method, robot, storage medium and grabbing system Technical Field The present application relates to the field of robots, and in particular, to a control method for a robot, a storage medium, and a gripping system. Background There are many severely paralyzed patients in the world who can only complete activities necessary for daily living, such as drinking water, with the help of others. With the continuous development of artificial intelligence and robotics, more and more research results are being applied to assist such people in order to improve their quality of life, wherein the brain-computer interface (Brain Computer Interface, BCI) field is a branch of the nerve engineering field, and has a rapid development and a wide prospect, and the research of people on the brain-computer interface field is stimulated. In the aspect of current robot control, only simple and even preset mechanical arm action control can be finished, and the advantages are not fully exerted. Disclosure of Invention The application mainly solves the technical problem of providing a control method of a robot, the robot, a storage medium and a grabbing system, which can enable the robot based on the pulse neural network to have an image recognition function and enable the robot to be more intelligent. In order to solve the problems, the technical scheme adopted by the application is to provide a control method of a robot, which comprises the steps of obtaining an image of a target area, identifying the image by utilizing a YOLO algorithm to determine the target position of a target object in the image, generating a target instruction based on the target position, calculating a running track in a pulse neural network based on the target instruction, and controlling the robot to grasp the target object according to the running track. The method comprises the steps of obtaining a first image and a second image of a target area, and identifying the images by utilizing a YOLO algorithm to determine the target position of a target object in the images, wherein the step of identifying the first image by utilizing the YOLO algorithm to determine the first target position of the target object in the first image and the step of identifying the second image to determine the second target position of the target object in the second image. The method comprises the steps of generating a target instruction based on the target position, wherein the target instruction comprises the steps of generating a third target position of a target object under a world coordinate system based on the first target position and the second target position, and generating the target instruction based on the third target position. The method comprises the steps of generating a third target position of a target object under a world coordinate system based on a first target position and a second target position, determining an initial third target position, obtaining a plurality of corresponding fourth target positions by using the initial third target position, and determining the initial third target position as a final third target position when any one of the fourth target positions and the first target position meet preset conditions and any one of the fourth target positions and the second target position meet preset conditions. The method comprises the steps of obtaining a plurality of corresponding fourth target positions by utilizing an initial third target position, wherein the method comprises the steps of obtaining a parameter matrix of image acquisition equipment corresponding to a first image or a second image, and obtaining the plurality of fourth target positions by utilizing the initial third target position and the parameter matrix. The method comprises the steps of utilizing a YOLO algorithm to identify an image to determine the target position of a target object in the image, and utilizing a trained image identification model to identify the image to determine the target position of the target object in the image, wherein the trained image identification model is obtained after training a sample image of the target object based on the YOLO algorithm. The method comprises the steps of generating a first instruction according to the running track, wherein the first instruction is used for controlling the robot to move to a first position on the running track, acquiring feedback data of the robot moving to the first position, calculating track correction data in a pulse neural network based on the first instruction and the feedback data, generating a second instruction according to the running track, wherein the second instruction and the track correction data are used for controlling the robot to move from the first position to a second position on the running track, and further controlling a mechanical arm of the robot to grasp the target object. In order to solve the above problems, another technical solution adopted by the present app