A Learning Approach to Robot-Agnostic Force-Guided High Precision Assembly

In this work we propose a learning approach to high-precision robotic assembly problems in the continuous action domain. Unlike many learning-based approaches that heavily rely on vision or spatial tracking, our approach takes force/torque as the only observation. Each learned policy from our approach is robot-agnostic, which can be applied to different robotic arms. These two features can greatly reduce complexity and cost to perform robotic assembly in the real world, especially in unstructured settings such as in architectural construction. To achieve it, we have developed a new distributed RL agent, named Recurrent Distributed DDPG (RD2), which extends Ape-X DDPG with recurrency and makes two structural improvements on prioritized experience replay. Our results show that RD2 is able to solve two fundamental high-precision assembly tasks, lap-joint and peg-in-hole, and outperforms two state-of-the-art algorithms, Ape-X DDPG and PPO with LSTM. We have successfully evaluated our robot-agnostic policies on three robotic arms, Kuka KR60, Franka Panda, and UR10, in simulation. The video presenting our experiments is available at https://sites.google.com/view/rd2-rl