Zhang Tiancheng; Li Qilin; Pei Tianshuo

Authors: School of Mechanical Engineering, Jiangsu Institute of Technology

Publishing: Machinery &; Electrical engineering technology)

Yearbook: May 20221Volume 9

Page number:127-131+177

China Library Classification: S225 [Agricultural Science-Agricultural Engineering] TP 18 [Industrial Technology-Automation Technology, Computer Technology] TP24 1 [Industrial Technology-Automation Technology, Computer Technology]

Subject classification: 08 [Engineering] 0828 [Engineering-Agricultural Engineering] 081[Engineering-Control Science and Engineering] 08 1 1 04 [Engineering-Pattern Recognition and Intelligent System] 0802 [Engineering-Mechanical Engineering]

Ji Jin: Innovation Plan for Postgraduates' Scientific Research Practice in Jiangsu Institute of Technology (No.:XSJCX 20 _ 45)

Main topic: Simulation of improved artificial potential field RRT* algorithm for picking robot motion planning.

Abstract: In the process of agricultural picking robot operation, whether the mechanical arm can avoid obstacles in the working environment to complete picking is very important to ensure farmers' income. Taking the path planning algorithm of robot arm in the environment of picking bunches of tomatoes as the research object, a path planning algorithm based on robot arm obstacle planning is proposed, which improves the artificial potential field method and combines it with RRT* algorithm. The algorithm improves the repulsive potential field function of artificial potential field method, and according to the limitation that artificial potential field method is easy to fall into extreme value, combined with RRT* algorithm to guide the picking manipulator to escape from extreme value state. Finally, in order to verify the robustness of the algorithm in the tomato string picking environment and its superiority compared with the artificial potential field method before improvement, the tomato string picking environment is simulated in MATLAB software, and the simulation experiment of robot arm obstacle avoidance path planning is carried out. The experimental results show that the algorithm is robust in different picking environments. Compared with the artificial potential field method, it can guide the picking manipulator to successfully escape from the extreme value and complete the obstacle avoidance path planning in an adaptive way, which verifies its superiority.