Optimized Control for Human-Multi-Robot Collaboration via Multi-Agent Adaptive Dynamic Programming

Abstract

Abstract In this paper we consider the problem of controlling the dynamic behavior of the robot agents while collaborating with the human worker. The presented dynamic behavior control method leads to achieving optimized interaction performance of the human-multi-robot collaboration system. We investigate in depth the dynamics equation of the robot agents collaborating with the human worker. Considering the unknown parameters in the system dynamics, the adaptive dynamic programming method is utilized to deal with the optimized interaction control problems during human-multi-robot collaboration process. To achieve the coordination of the multi robot agents, multi-agent adaptive dynamic programming method is employed in this paper. The neural networks with one hidden layer are utilized to approximate both the unknown system dynamics as well as the optimized cost function. The simulation studies verify the effectiveness of the presented algorithm.