UR robot manipulator collision avoidance for static obstacles via path planning

• Main Author: Zhao, Jiayi
• Other Authors: Hu Guoqiang
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2021
• Subjects: Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• Online Access: https://hdl.handle.net/10356/153122
• Institution: Nanyang Technological University

As one of the most attractive machine learning technologies, deep reinforcement learning has achieved great success in many applications. The aim of this thesis is to realize the static obstacle avoidance of UR manipulator by exploring the advantages and disadvantages of deep reinforcement learning and RRT and its derivation algorithm. However, DDPG, DQN and other algorithms are difficult to achieve obstacle avoidance, simulation results are difficult to converge, deep reinforcement learning needs further development. Through Matlab simulation, we can realize the static obstacle avoidance of the manipulator by RRT, RRT-connect, RRT* algorithm and the kinematics of the manipulator.