An Intelligent Control System of Manipulator Based on Multi-eye Stereo Vision

Abstract

The invention discloses an intelligent control system of a manipulator based on multi-eye stereo vision, which includes a manipulator and a manipulator controller connected to the manipulator signal; a binocular camera image acquisition unit acting on a target object is fixedly installed around the manipulator, and the two The image acquisition unit of the eye camera is connected to the host computer through a data line; the image acquisition unit of the binocular camera adopts an improved cross-scale guided filter combined with a weighted median filter parallax refinement algorithm to realize the three-dimensional reconstruction of the target object and complete the target object. Coarse positioning, and use the 5-3-5 polynomial interpolation trajectory planning method to plan the trajectory of the mechanical arm; the gripper of the manipulator is equipped with a monocular camera image acquisition unit, which moves with the mechanical arm to obtain images; the monocular camera The image acquisition unit communicates with the host computer through the wireless transmission module, and the monocular camera image acquisition unit uses the template matching method based on SURF to accurately locate the target object.

Description

technical field [0001] The invention relates to the technical fields of image recognition and mechanical arm, in particular to an intelligent control system of a mechanical arm based on multi-eye stereo vision. Background technique [0002] Since the advent of the world's first robot in the 1960s, the research and application of robot technology has been widely concerned and developed rapidly for nearly 60 years. Application scenarios of various types of robots have emerged. As a big manufacturing country, my country has a lot of large-scale industrial production. In many scenarios, it is necessary to detect, identify, classify and assemble products in real time, which will lead to rapid development of robot technology. [0003] At present, due to errors in image processing, the robotic arm cannot achieve accurate grasping. Furthermore, during the grasping process of the manipulator, there is jumping between the joints, which will seriously damage the manipulator and the m...

AI Technical Summary

Problems solved by technology

[0003] At present, the robotic arm cannot achieve accurate grasping due to image processing errors

Furthermore, during the grasping process of the manipulator, there is a jumping phenomenon between the joints, which will seriously damage the manipulator and the motor.

Images