A Contact-Safe Reinforcement Learning Framework for Contact-Rich Robot Manipulation

TL;DR

This paper introduces a contact-safe reinforcement learning framework for robot manipulation that detects and limits collisions and contact forces, ensuring safety and robustness during training and real-world deployment.

Contribution

It proposes a novel framework that maintains safety in contact-rich tasks by detecting collisions and controlling contact forces, enabling safe transfer from simulation to real robots.

Findings

Effective collision detection and force control in real-time

Maintains small contact forces during unseen scenarios

Robust to external disturbances in contact-rich tasks

Abstract

Reinforcement learning shows great potential to solve complex contact-rich robot manipulation tasks. However, the safety of using RL in the real world is a crucial problem, since unexpected dangerous collisions might happen when the RL policy is imperfect during training or in unseen scenarios. In this paper, we propose a contact-safe reinforcement learning framework for contact-rich robot manipulation, which maintains safety in both the task space and joint space. When the RL policy causes unexpected collisions between the robot arm and the environment, our framework is able to immediately detect the collision and ensure the contact force to be small. Furthermore, the end-effector is enforced to perform contact-rich tasks compliantly, while keeping robust to external disturbances. We train the RL policy in simulation and transfer it to the real robot. Real world experiments on robot wiping tasks show that our method is able to keep the contact force small both in task space and joint space even when the policy is under unseen scenario with unexpected collision, while rejecting the disturbances on the main task.