Integrating Model-based Control and RL for Sim2Real Transfer of Tight Insertion Policies

TL;DR

This paper presents a hybrid control and reinforcement learning approach for precise object insertion tasks, enabling zero-shot sim-to-real transfer with improved accuracy over existing methods.

Contribution

It introduces a novel integration of model-based control with residual RL for tight insertion, achieving effective sim-to-real transfer without additional real-world training.

Findings

Outperforms recent RL-based methods in insertion accuracy.

Effective zero-shot transfer from simulation to real robot.

Ablation studies confirm the importance of each component.

Abstract

Object insertion under tight tolerances ($< \hspace{-.02in} 1mm$) is an important but challenging assembly task as even small errors can result in undesirable contacts. Recent efforts focused on Reinforcement Learning (RL), which often depends on careful definition of dense reward functions. This work proposes an effective strategy for such tasks that integrates traditional model-based control with RL to achieve improved insertion accuracy. The policy is trained exclusively in simulation and is zero-shot transferred to the real system. It employs a potential field-based controller to acquire a model-based policy for inserting a plug into a socket given full observability in simulation. This policy is then integrated with residual RL, which is trained in simulation given only a sparse, goal-reaching reward. A curriculum scheme over observation noise and action magnitude is used for training the residual RL policy. Both policy components use as input the SE(3) poses of both the plug and the socket and return the plug's SE(3) pose transform, which is executed by a robotic arm using a controller. The integrated policy is deployed on the real system without further training or fine-tuning, given a visual SE(3) object tracker. The proposed solution and alternatives are evaluated across a variety of objects and conditions in simulation and reality. The proposed approach outperforms recent RL-based methods in this domain and prior efforts with hybrid policies. Ablations highlight the impact of each component of the approach.