Improving Low-Cost Teleoperation: Augmenting GELLO with Force

TL;DR

This paper enhances a low-cost teleoperation system by adding force feedback and force data integration, improving user experience and task success in dexterous manipulation tasks.

Contribution

The work introduces force feedback and force data integration into GELLO teleoperation, enabling more effective manipulation and learning.

Findings

Force feedback improved user experience for experienced users.

Force data enhanced imitation learning performance.

Task success increased with force information.

Abstract

In this work we extend the low-cost GELLO teleoperation system, initially designed for joint position control, with additional force information. Our first extension is to implement force feedback, allowing users to feel resistance when interacting with the environment. Our second extension is to add force information into the data collection process and training of imitation learning models. We validate our additions by implementing these on a GELLO system with a Franka Panda arm as the follower robot, performing a user study, and comparing the performance of policies trained with and without force information on a range of simulated and real dexterous manipulation tasks. Qualitatively, users with robotics experience preferred our controller, and the addition of force inputs improved task success on the majority of tasks.