Multi-agent Reinforcement Learning Method for Disassembly Sequential Task Optimization Based on Human-Robot Collaborative Disassembly in Electric Vehicle Battery Recycling

Abstract

With the wide application of new electric vehicle (EV) battery in various industrial fields, it is important to establish a systematic intelligent battery recycling system that can be used to find out the resource wastes and environmental impacts for the retired EV battery. By combining the disassembly and echelon utilization of EV battery recycling in the re-manufacturing fields, human-robot collaboration (HRC) disassembly method can be used to solve many huge challenges about the efficiency and safety of retired EV battery recycling. In order to find out the common problems in the human-robot collaboration disassembly process of EV battery recycling, a dynamic disassembly process optimization method based on Multi-Agent Reinforcement Learning (MARL) algorithm is proposed. Furthermore, it is necessary to disassemble the EV battery disassembly task trajectory based on human-robot collaboration disassembly task in 2D planar, which can be used to acquire the optimal disassembly paths in the same disassembly planar combining the Q-learning algorithm. The disassembly task sequence can be completed through standard trajectory matching. Finally the feasibility of the method is verified by disassembly operations for a specific battery module case.