Contact-Grounded Policy: Dexterous Visuotactile Policy with Generative Contact Grounding

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Zhengtong, Wang, Yeping, Abbatematteo, Ben, Preechayasomboon, Jom, Chan, Sonny, Colonnese, Nick, Memar, Amirhossein H.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911660322586624
author Xu, Zhengtong
Wang, Yeping
Abbatematteo, Ben
Preechayasomboon, Jom
Chan, Sonny
Colonnese, Nick
Memar, Amirhossein H.
author_facet Xu, Zhengtong
Wang, Yeping
Abbatematteo, Ben
Preechayasomboon, Jom
Chan, Sonny
Colonnese, Nick
Memar, Amirhossein H.
contents Contact-rich dexterous manipulation with multi-finger hands remains an open challenge in robotics because task success depends on multi-point contacts that continuously evolve and are highly sensitive to object geometry, frictional transitions, and slip. Recently, tactile-informed manipulation policies have shown promise. However, most use tactile signals as additional observations rather than modeling contact state or how their action outputs interact with low-level controller dynamics. We present Contact-Grounded Policy (CGP), a visuotactile policy that grounds multi-point contacts by predicting coupled trajectories of actual robot state and tactile feedback, and using a learned contact-consistency mapping to convert these predictions into executable target robot states for a compliance controller. CGP consists of two components: (i) a conditional diffusion model that forecasts future robot state and tactile feedback in a compressed latent space, and (ii) a learned contact-consistency mapping that converts the predicted robot state-tactile pair into executable targets for a compliance controller, enabling it to realize the intended contacts. We evaluate CGP using a physical four-finger Allegro V5 hand with Digit360 fingertip tactile sensors, and a simulated five-finger Tesollo DG-5F hand with dense whole-hand tactile arrays. Across a range of dexterous tasks including in-hand manipulation, delicate grasping, and tool use, CGP outperforms visuomotor and visuotactile diffusion-policy baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2603_05687
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Contact-Grounded Policy: Dexterous Visuotactile Policy with Generative Contact Grounding
Xu, Zhengtong
Wang, Yeping
Abbatematteo, Ben
Preechayasomboon, Jom
Chan, Sonny
Colonnese, Nick
Memar, Amirhossein H.
Robotics
Contact-rich dexterous manipulation with multi-finger hands remains an open challenge in robotics because task success depends on multi-point contacts that continuously evolve and are highly sensitive to object geometry, frictional transitions, and slip. Recently, tactile-informed manipulation policies have shown promise. However, most use tactile signals as additional observations rather than modeling contact state or how their action outputs interact with low-level controller dynamics. We present Contact-Grounded Policy (CGP), a visuotactile policy that grounds multi-point contacts by predicting coupled trajectories of actual robot state and tactile feedback, and using a learned contact-consistency mapping to convert these predictions into executable target robot states for a compliance controller. CGP consists of two components: (i) a conditional diffusion model that forecasts future robot state and tactile feedback in a compressed latent space, and (ii) a learned contact-consistency mapping that converts the predicted robot state-tactile pair into executable targets for a compliance controller, enabling it to realize the intended contacts. We evaluate CGP using a physical four-finger Allegro V5 hand with Digit360 fingertip tactile sensors, and a simulated five-finger Tesollo DG-5F hand with dense whole-hand tactile arrays. Across a range of dexterous tasks including in-hand manipulation, delicate grasping, and tool use, CGP outperforms visuomotor and visuotactile diffusion-policy baselines.
title Contact-Grounded Policy: Dexterous Visuotactile Policy with Generative Contact Grounding
topic Robotics
url https://arxiv.org/abs/2603.05687