Unlock instant, AI-driven research and patent intelligence for your innovation.

Self-adaptive particle filter-based robot vision servo control method

A technology of robot vision and particle filtering, applied in manipulators, manufacturing tools, etc., can solve problems such as interference from environmental changes and parameters that are susceptible to parameter changes.

Inactive Publication Date: 2011-05-18
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the structural parameters of the system are partially unknown, they can be obtained through an appropriate calibration process, but for complex system or image features, the parameters obtained through calibration are easily disturbed by parameter changes and environmental changes

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Self-adaptive particle filter-based robot vision servo control method
  • Self-adaptive particle filter-based robot vision servo control method
  • Self-adaptive particle filter-based robot vision servo control method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0041] The hardware part in the embodiment is mainly composed of a robot, a computer, a camera and necessary connections. Such as figure 2 Shown is a schematic diagram of a two-degree-of-freedom arm robot. The length of the two rods of the robot is 0.5m, and the camera is fixed at the end of the robot. The distance between the camera and the plane where the target is located is 35cm. The task of the servo control system is to capture the position of the target by the camera, calculate the coordinates of the target center in the image, and compare it with the desired image coordinates. If it is zero, stop the control function, and if it is not zero, control The robot moves until the two are equal.

[0042] Adopt the servo control method that the present invention proposes to carry out actual control, its step is as follows:

[0043] In the first step, the image feature selects the coordinates of the target center to give the desired target image feature y d =[240,240] T ,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a self-adaptive particle filter-based robot vision servo control method which belongs to the technical field of computer artificial intelligence. The method comprises the following steps of: providing an expected target image characteristic and corresponding robot joint angle according to practical demand; then shooting the image and reading the robot joint angle at the moment; calculating the practical image characteristic of an object according to the image; calculating image characteristic deviation and transformation; if image characteristic deviation is zero, indicating that a robot arrives in the preset position and finishing the control process; otherwise, obtaining an image jacobian matrix; and finally, obtaining an estimating value of joint angle variation according to the obtained image jacobian matrix and image characteristic transformation. The estimating value of joint angle variation is input into a robot controller, and the controller controls and adjusts the motion of the robot according to the estimating value of joint angle variation. The method of the invention can be suitable for a nonlinear non-Gaussian control system by introducing a self-adaptive particle filter algorithm.

Description

technical field [0001] The invention relates to a robot vision servo control method, which belongs to the technical field of computer artificial intelligence. Background technique [0002] Robot visual servoing means that the robot can imitate the human visual perception system, and guide the robot to perform various operations through visual feedback information, and can complete various tasks that serve humans such as welding, assembly, and moving objects. [0003] Over the years, there is a lot of literature on the research of robot visual servo control. When the system structure parameters are known, conventional control methods can be used for control. When the system structure parameters are partially unknown, they can be obtained through a suitable calibration process, but for complex system or image features, the parameters obtained through calibration are easily disturbed by parameter changes and environmental changes. Therefore, some robot visual servo control me...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): B25J13/00B25J19/00
Inventor 赵清杰马捷
Owner BEIJING INSTITUTE OF TECHNOLOGYGY