High Fidelity Capture, Reconstruction, and Transfer of Human Demonstrations for Robot-Assisted Bathing

Venue: RSS 2026 (Sydney, Jul 13–17) · Session: Datasets and Benchmarks · paper #94 Authors: Arjun Lakshmipathy, Jonathan P. King, Ethan Zuo, Rohit Satishkumar, Hongyi Chen, Jeffrey Ichnowski, Dan Ding, Zackory Erickson, Nancy S. Pollard Program page: https://roboticsconference.org/program/papers/94/

No public preprint found (searched arXiv, Aug 2026); summary derived from the verified program abstract. The abstract below is verbatim from the program page (verified snapshot, Jul 2026). Trend placement and neighbors: RSS 2026 survey.

Summary

Problem. Robots are wanted for high-value clinical tasks like bathing, but current systems lack the safety and reliability needed for sustained, contact-rich physical interaction with humans, and collecting and transferring highly dynamic bathing demonstrations is difficult even with modern motion and tactile sensing. Method. The authors build a capture-reconstruction-transfer framework that uses contact regions as the key processing primitive, record a dataset of bathing demonstrations performed by trained clinicians on human subjects, and use it to design and control an arm-mounted dexterous soft hand executing bathing tasks on a mannequin with both open- and closed-loop strategies. Results. The dataset is claimed as the first with high-quality synchronized motion, shape, contact, and force during sustained contact-rich human-human interaction, the transfer strategies exercise these data across multiple levels of the robotics stack, and all materials are slated for public release for physical human-robot interaction (pHRI) research.

Abstract

Despite the demand for robots in high-value clinical tasks like bathing, contemporary systems still lack the safety and reliability required for complex, sustained physical interaction with humans. A key challenge hindering the development of such systems is that collecting, understanding, and effectively transferring highly dynamic, contact-rich human bathing demonstrations is difficult, even with modern motion and tactile sensing equipment. We present a straightforward, but effective framework for doing so with high fidelity by utilizing contact regions as a key processing primitive. We use our framework to build a dataset of bathing demonstrations performed by trained clinicians on human subjects. We then use this dataset to design and control an arm-mounted dexterous soft hand to perform bathing tasks on a mannequin using open- and closed-loop strategies. Our dataset is the first to provide high quality synchronized motion, shape, contact, and force during sustained, contact-rich human-human interaction, and our transfer strategies demonstrate effective use of these data across multiple levels of the robotics stack. All relevant materials will be publicly released to enable further advancements in physical human-robot interaction (pHRI) research.

Wiki context

Related topic reviews: Review-VLA-Evaluation

← Back to RSS 2026 survey · RSS-2026-Papers · Home