Priority-Based Reward Mechanism for Dual-Robot Path Planning in Dynamic Environments

Abstract

The definition of motion priority enables robot groups to handle competition and cooperation better when performing physical tasks. In this paper, we propose a priority-based step reward mechanism, which is a new reward mechanism for deep reinforcement learning of multi-robot systems and can improve collaboration between robotic arms in shared workspaces. The intention of each agent is provided to other agents, presenting a 2D map of the head that is visually consistent, with state and action representations aligned spatially. Guided by priority-based step rewards, the dual-robots are sequentially assigned high priority, enabling them to pass through complex environments in sequence. We validated our method on a path planning task where two robots collaborate to transport cubes in dynamic environments. The two robots need to consider obstacle avoidance while handing cubes to the human operator. The experimental environment includes Free space, obstacles in the middle, obstacles on both sides, and combinations of several environments. The results show that priority step rewards improve the performance of robot collaborative tasks and significantly enhance cooperative behavior.