analiza aiqbench
This research investigates how wearable exoskeleton geometry alters tactile data collection and robot learning policies, demonstrating that interface design directly impacts the quality of demonstrations used for training dexterous tasks. The study finds that spatial-plus-force inputs derived from revised interfaces yield superior policy performance compared to binary aggregation or baseline hardware across multiple precision manipulation tasks.
From Wearable Interfaces to Dexterous Policies: Contact Shifts and Tactile Representations
arXiv:2610.08870v1 Announce Type: new Abstract: Unlike conventional teleoperation, wearable interfaces allow operators to collect dexterous demonstrations through their own hand motions while directly interacting with task objects. This direct interaction reduces dependence on the target robot during collection, but it also makes the collection hardware part of the physical process that generates each demonstration. Interface geometry can influence both how a task is performed and what tactile observations are recorded for learning. We study two versions of a DexUMI-family exoskeleton that share the same robot command definition, mapping procedure, and tactile module type but differ in hand-side geometry. The revised interface reduces reported physical demand, improves selected device ratings, enables tactile access in a precision grasp that is mechanically blocked by the baseline, and produces task-dependent changes in recorded contact. Lid twisting primarily exhibits a change in contact location, whereas egg carton opening primarily exhibits a change in contact occurrence. We then train matched policies using either a binary aggregate input or a spatial-plus-force input. On lid twisting and egg carton opening, policies trained on revised-interface demonstrations achieve higher success than those trained on baseline demonstrations, with a significant pooled interface effect. Across these and two additional tasks, USB insertion and soldering tool pick and place, the spatial-plus-force input likewise outperforms binary aggregation. These results show that wearable collection hardware is part of the data-generation process for robot learning. Such interfaces should therefore be evaluated not only through operator experience, but also through the tactile interactions they make recordable and the policy performance their demonstrations support.
Abstract:Unlike conventional teleoperation, wearable interfaces allow operators to collect dexterous demonstrations through their own hand motions while directly interacting with task objects. This direct interaction reduces dependence on the target robot during collection, but it also makes the collection hardware part of the physical process that generates each demonstration. Interface geometry can influence both how a task is performed and what tactile observations are recorded for learning. We study two versions of a DexUMI-family exoskeleton that share the same robot command definition, mapping procedure, and tactile module type but differ in hand-side geometry. The revised interface reduces reported physical demand, improves selected device ratings, enables tactile access in a precision grasp that is mechanically blocked by the baseline, and produces task-dependent changes in recorded contact. Lid twisting primarily exhibits a change in contact location, whereas egg carton opening primarily exhibits a change in contact occurrence. We then train matched policies using either a binary aggregate input or a spatial-plus-force input. On lid twisting and egg carton opening, policies trained on revised-interface demonstrations achieve higher success than those trained on baseline demonstrations, with a significant pooled interface effect. Across these and two additional tasks, USB insertion and soldering tool pick and place, the spatial-plus-force input likewise outperforms binary aggregation. These results show that wearable collection hardware is part of the data-generation process for robot learning. Such interfaces should therefore be evaluated not only through operator experience, but also through the tactile interactions they make recordable and the policy performance their demonstrations support.
8 pages, 6 figures. Submitted to ICRA 2027
Robotics (cs.RO)
arXiv:2610.08870 [cs.RO]
(or arXiv:2610.08870v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.08870 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 350 cuvinte
Subiecte conexe
RealDexUMI: A Wearable Universal Manipulation Interface for Dexterous Robot Learning
arXiv · 9 iun. 2026
RealDexUMI: A Wearable Universal Manipulation Interface for Dexterous Robot Learning
arXiv · 5 iun. 2026
Bench2Dex: Benchmarking Visuo-Tactile Bimanual Dexterous Manipulation Across Dexterous Hands
arXiv · 16 sept. 2026
FingerEye: Learning Dexterous Manipulation with Continuous Vision-Tactile Sensing
arXiv · 7 oct. 2026