TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction

TL;DR

TRANSIC is a human-in-the-loop framework that enables robots to learn from online human corrections, effectively bridging the sim-to-real gap in complex manipulation tasks by integrating simulation and human-guided policies.

Contribution

It introduces a data-driven, human-in-the-loop method for closing sim-to-real gaps through online correction and residual policy learning.

Findings

Successful transfer in complex manipulation tasks like furniture assembly.

Effective integration of simulation and human correction policies.

Scales with human effort for improved sim-to-real transfer.

Abstract

Learning in simulation and transferring the learned policy to the real world has the potential to enable generalist robots. The key challenge of this approach is to address simulation-to-reality (sim-to-real) gaps. Previous methods often require domain-specific knowledge a priori. We argue that a straightforward way to obtain such knowledge is by asking humans to observe and assist robot policy execution in the real world. The robots can then learn from humans to close various sim-to-real gaps. We propose TRANSIC, a data-driven approach to enable successful sim-to-real transfer based on a human-in-the-loop framework. TRANSIC allows humans to augment simulation policies to overcome various unmodeled sim-to-real gaps holistically through intervention and online correction. Residual policies can be learned from human corrections and integrated with simulation policies for autonomous execution. We show that our approach can achieve successful sim-to-real transfer in complex and contact-rich manipulation tasks such as furniture assembly. Through synergistic integration of policies learned in simulation and from humans, TRANSIC is effective as a holistic approach to addressing various, often coexisting sim-to-real gaps. It displays attractive properties such as scaling with human effort. Videos and code are available at https://transic-robot.github.io/