AUTHOR=Ku Tao , Li Jin , Liu Jinxin , Lin Yuexin , Liu Xinyu 

TITLE=A Motion Planning Algorithm for Live Working Manipulator Integrating PSO and Reinforcement Learning Driven by Model and Data

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.957869

DOI=10.3389/fenrg.2022.957869

ISSN=2296-598X

ABSTRACT=In order to solve the motion planning problem of the live working manipulator, this paper proposes a data model hybrid driving algorithm-P-SAC algorithm. In the model-driven part, in order to avoid obstacles and make the trajectory as smooth as possible, we designed the trajectory model of the sixth-order polynomial, and used the PSO algorithm to optimize the parameters of the trajectory model. The data generated by the model-driven part is then passed into the replay buffer to pre-train the agent. Meanwhile, in order to guide the manipulator reach the target point, we propose a reward function design based on region guidance. The experimental results show that the P-SAC algorithm can reduce the unnecessary exploration in the early stage of reinforcement learning, and can improve the learning ability of the model-driven algorithm for the environment.