ResPilot: Teleoperated Finger Gaiting via Gaussian Process Residual Learning

TL;DR

ResPilot introduces a Gaussian Process residual learning approach to teleoperated finger gaiting, significantly expanding the robot hand's workspace and improving dexterous manipulation capabilities.

Contribution

The paper presents a novel residual Gaussian Process learning method that enhances teleoperated finger gaiting for multi-fingered robot hands, enabling more complex manipulation tasks.

Findings

Increased reachable workspace of the robot hand.

Successful completion of novel dexterous finger gaiting tasks.

Enhanced contact stability during manipulation.

Abstract

Dexterous robot hand teleoperation allows for long-range transfer of human manipulation expertise, and could simultaneously provide a way for humans to teach these skills to robots. However, current methods struggle to reproduce the functional workspace of the human hand, often limiting them to simple grasping tasks. We present a novel method for finger-gaited manipulation with multi-fingered robot hands. Our method provides the operator enhanced flexibility in making contacts by expanding the reachable workspace of the robot hand through residual Gaussian Process learning. We also assist the operator in maintaining stable contacts with the object by allowing them to constrain fingertips of the hand to move in concert. Extensive quantitative evaluations show that our method significantly increases the reachable workspace of the robot hand and enables the completion of novel dexterous finger gaiting tasks. Project website: http://respilot-hri.github.io