IEEE 18th International Conference on Automation Science and Engineering (CASE) - A Meta-Reinforcement Learning-Based Adaptive Robot Control for Human-Robot Collaboration in Personalized Production

Abstract

A Research Project utilized MAML-based 5-step PPO to improve robot’s productivity in HRC by about 75% on average. It aims to enable collaborative robots (cobots) to acquire basic skills and perform tasks based on personalised production requirements, made by KWOK Hin Chi , LI Chengxi, PANG Yat Ming, ZHENG Pai.