A transfer reinforcement learning and digital-twin based task allocation method for human-robot collaboration assembly

Currently, human-robot collaboration systems are considered to have great application potential in complex and flexible assembly tasks. In human-robot collaborative assembly systems, the roles and tasks allocation between human and robot are the vital stage to exert and integrate the strength of both. Current many researches of task allocation mainly train decision-making model depending on a large number of predefined standard assembly data such as assembly time and assembly difficulty. However, due to individual differences and frequent product updates, the dynamic assembly conditions lack enough data for model training, and the constructed model based on historical data may not adapt to the new condition. To solve this gap, a transfer reinforcement learning and digital-twin based task allocation method is proposed to achieve the accurate and efficient multi-agent human-robot collaboration task allocation policy learning. Firstly, based on the digital twin of human-robot collaboration environment, the augmented reality is leveraged to simulate assembly process and collect execution data of workers and robots before the physical assembly. Secondly, a multi-agent reinforcement learning method is introduced to use domain randomization strategy to pre-train decision policy before the accurate model training. Thirdly, the knowledge distillation is leveraged to develop the transfer reinforcement learning framework to learn the accurate decision policy by reusing the pre-trained policy and utilizing the collected assembly simulation data. Finally, a case study is performed to demonstrate the effectiveness of the proposed method.