Dynamic Obstacle Avoidance for Cable-Driven Parallel Robots With Mobile Bases via Sim-to-Real Reinforcement Learning

摘要

A Cable-Driven Parallel Robot (CDPR) with Mobile Bases (MBs) can modify its geometric architecture and is suitable for manipulation tasks in constrained environments. In manipulation tasks, a CDPR with MBs inevitably encounters obstacles, including dynamic obstacles. However, the high dimensional state space and a considerable number of constraints caused by multiple cables and MBs make the real-time dynamic obstacle avoidance of a CDPR with MBs challenging. This letter proposes a Reinforcement Learning (RL)-based dynamic obstacle avoidance method for a CDPR with MBs to deal with dynamic obstacles in real time. To explain the RL-based dynamic obstacle avoidance method, this letter focuses on a CDPR with four fixed-length cables connected to four MBs. An RL-based Obstacle Avoidance Controller (OAC) is developed and integrated into a trajectory tracking controller to address the dynamic obstacle avoidance problem of a CDPR with MBs tracking a target trajectory. To explain and evaluate the RL-based dynamic obstacle avoidance method further, an RL-based OAC is trained in a Mujoco simulator and transferred to a CDPR with four fixed-length cables connected to four MBs in the real world.