Research on dynamic target steady and quasi-grasping method of coal gangue sorting robot based on global planning and local vision

ABSTRACT

Using robots instead of manual sorting of coal gangue can significantly improve the sorting rate. However, the stable grasping of the target gangue by the manipulator is the key to the efficient sorting of robot. The coal gangue on the belt conveyor has the characteristics of high speed and high quality. In the process of grasping, the velocity difference between the end of the manipulator and the coal gangue will cause impact load. In addition, the belt speed fluctuation and deviation also lead to the inaccurate location of the gangue, resulting in excessive position error of the manipulator during grasping, leading to grasping failure. For this reason, a synchronous tracking trajectory planning method of manipulator based on global planning and local visual servo is proposed in this paper. In this method, the manipulator is controlled by the BPNG method to reach the top of the target gangue quickly, and the accurate location of the target gangue is completed by the extended FDSST tracking algorithm. The manipulator uses the “position-velocity-acceleration” three-loop PID square method to realize the synchronous tracking trajectory planning of the target gangue. The experimental results show that this method can achieve stable and accurate grasping of target gangue by manipulator.

KEYWORDS:

• Coal gangue sorting robot
• track planning
• tracking grab
• dynamic target crawling
• position-velocity-acceleration control

Disclosure Statement

No potential conflict of interest was reported by the author(s).