Reinforcement learning of variable admittance control for human-robot co-manipulation

In this paper, a variable admittance controller based on reinforcement learning is proposed for human-robot co-manipulation tasks. Setting as the goal of the reinforcement learning algorithm the minimisation of the jerk throughout a point-to-point movement, the proposed controller can learn the appropriate damping for effective cooperation without any prior knowledge of the target position or other task characteristics. The performance of the proposed variable admittance controller is investigated on a co-manipulation task with a number of subjects using a KUKA LWR robot, demonstrating considerable reduction both in the effort required by the operator and in the completion time of the task.