FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning

TL;DR

FACTR introduces a force-attending curriculum training method for contact-rich policy learning, leveraging force feedback in teleoperation to improve robot generalization to unseen objects by 43%.

Contribution

The paper presents a novel curriculum training approach that guides policies to attend to force feedback, enhancing contact-rich task performance.

Findings

Significant 43% improvement in generalization to unseen objects.

Effective use of force feedback in policy learning.

A low-cost teleoperation setup for data collection.

Abstract

Many contact-rich tasks humans perform, such as box pickup or rolling dough, rely on force feedback for reliable execution. However, this force information, which is readily available in most robot arms, is not commonly used in teleoperation and policy learning. Consequently, robot behavior is often limited to quasi-static kinematic tasks that do not require intricate force-feedback. In this paper, we first present a low-cost, intuitive, bilateral teleoperation setup that relays external forces of the follower arm back to the teacher arm, facilitating data collection for complex, contact-rich tasks. We then introduce FACTR, a policy learning method that employs a curriculum which corrupts the visual input with decreasing intensity throughout training. The curriculum prevents our transformer-based policy from over-fitting to the visual input and guides the policy to properly attend to the force modality. We demonstrate that by fully utilizing the force information, our method significantly improves generalization to unseen objects by 43\% compared to baseline approaches without a curriculum. Video results, codebases, and instructions at https://jasonjzliu.com/factr/