Human-robot force cooperation analysis by deep reinforcement learning

Abstract

Purpose This study aims to realize natural and effort-saving motion behavior and improve effectiveness for different operators in human–robot force cooperation. Design/methodology/approach The parameter of admittance model is identified by deep deterministic policy gradient (DDPG) to realize human–robot force cooperation for different operators in this paper. The movement coupling problem of hybrid robot is solved by realizing position and pose drags. In DDPG, minimum jerk trajectory is selected as the reward objective function, and the variable prioritized experience replay is applied to balance the exploration and exploitation. Findings A series of simulations are implemented to validate the superiority and stability of DDPG. Furthermore, three sets of experiments involving mass parameter, damping parameter and DDPG are implemented, the effect of DDPG in real environment is validated and could meet the cooperation demand for different operators. Originality/value DDPG is applied in admittance model identification to realize human–robot force cooperation for different operators. And minimum jerk trajectory is introduced into reward objective to meet requirement of human arm free movements. The algorithm proposed in this paper could be further extended in the other operation task.