ResPilot: Teleoperated Finger Gaiting via Gaussian Process Residual Learning

Patrick Naughton, Jinda Cui, Karankumar Patel, Soshi Iba
Proceedings of The 8th Conference on Robot Learning, PMLR 270:4410-4424, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-naughton25a, title = {ResPilot: Teleoperated Finger Gaiting via Gaussian Process Residual Learning}, author = {Naughton, Patrick and Cui, Jinda and Patel, Karankumar and Iba, Soshi}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {4410--4424}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/naughton25a/naughton25a.pdf}, url = {https://proceedings.mlr.press/v270/naughton25a.html}, 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.} }
Endnote
%0 Conference Paper %T ResPilot: Teleoperated Finger Gaiting via Gaussian Process Residual Learning %A Patrick Naughton %A Jinda Cui %A Karankumar Patel %A Soshi Iba %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-naughton25a %I PMLR %P 4410--4424 %U https://proceedings.mlr.press/v270/naughton25a.html %V 270 %X 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.
APA
Naughton, P., Cui, J., Patel, K. & Iba, S.. (2025). ResPilot: Teleoperated Finger Gaiting via Gaussian Process Residual Learning. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:4410-4424 Available from https://proceedings.mlr.press/v270/naughton25a.html.

Related Material