Learning Switching Criteria for Sim2Real Transfer of Robotic Fabric Manipulation Policies

TL;DR

This paper develops automatic criteria to determine the optimal point to transfer simulation-trained robotic fabric manipulation policies to real robots, improving reliability and efficiency in sim2real transfer.

Contribution

It introduces confidence-based switching criteria for sim2real transfer, specifically addressing challenges in fabric manipulation tasks.

Findings

Switching criteria correlate well with real-world performance.

Achieved fabric coverage of 87.2-93.7% within 55-60% of training budget.

Method reduces overfitting and improves transfer reliability.

Abstract

Simulation-to-reality transfer has emerged as a popular and highly successful method to train robotic control policies for a wide variety of tasks. However, it is often challenging to determine when policies trained in simulation are ready to be transferred to the physical world. Deploying policies that have been trained with very little simulation data can result in unreliable and dangerous behaviors on physical hardware. On the other hand, excessive training in simulation can cause policies to overfit to the visual appearance and dynamics of the simulator. In this work, we study strategies to automatically determine when policies trained in simulation can be reliably transferred to a physical robot. We specifically study these ideas in the context of robotic fabric manipulation, in which successful sim2real transfer is especially challenging due to the difficulties of precisely modeling the dynamics and visual appearance of fabric. Results in a fabric smoothing task suggest that our switching criteria correlate well with performance in real. In particular, our confidence-based switching criteria achieve average final fabric coverage of 87.2-93.7% within 55-60% of the total training budget. See https://tinyurl.com/lsc-case for code and supplemental materials.