aiqbench analysis
ReTouch introduces a vision-language-action model capable of contact-rich dexterous manipulation by continuously refining tactile predictions using real-time execution feedback. This closed-loop approach, validated on the XHT-Dataset across seven tasks, significantly improves robustness against physical interaction changes and action errors compared to standard baselines. The work advances robotic autonomy in complex environments where fine-grained haptic sensing is critical for success.
ReTouch: Empowering Contact-Rich Dexterous Manipulation with Online-Refined Tactile Prediction
arXiv:2608.01824v1 Announce Type: new Abstract: Fusing tactile signals has proven effective for contact-rich manipulation, enabling robots to perceive contact states and adapt to rapidly changing physical interactions. Yet effectively integrating tactile feedback into dexterous manipulation remains underexplored. In this work, we introduce ReTouch, a vision-language-action model (VLA) that supports contact-rich dexterous manipulation through tactile predictions continually refined online using execution-time feedback. ReTouch builds on two main innovations for tactile representation and closed-loop action generation. First, its Tactile-Patch Encoder represents tactile observations as structured tactile patch features that preserve finger identity and local contact structure, providing contact cues for fine-grained dexterous control. Second, its high-frequency action module jointly predicts future tactile states and action chunks and refines both using incoming tactile feedback during execution. This closed-loop refinement keeps tactile predictions aligned with evolving physical interactions, enabling responsive action correction and improving robustness to contact changes and execution errors. We further introduce XHT-Dataset, comprising 900 real-world demonstrations across seven contact-rich tasks collected on an XHand--UR7e platform, and evaluate ReTouch through closed-loop real-robot experiments. ReTouch surpasses the strongest baseline by 18.4 and 23.8 percentage points in average success rate under standard and challenging conditions, respectively, demonstrating its effectiveness and robustness.
Abstract:Fusing tactile signals has proven effective for contact-rich manipulation, enabling robots to perceive contact states and adapt to rapidly changing physical interactions. Yet effectively integrating tactile feedback into dexterous manipulation remains underexplored. In this work, we introduce ReTouch, a vision-language-action model (VLA) that supports contact-rich dexterous manipulation through tactile predictions continually refined online using execution-time feedback. ReTouch builds on two main innovations for tactile representation and closed-loop action generation. First, its Tactile-Patch Encoder represents tactile observations as structured tactile patch features that preserve finger identity and local contact structure, providing contact cues for fine-grained dexterous control. Second, its high-frequency action module jointly predicts future tactile states and action chunks and refines both using incoming tactile feedback during execution. This closed-loop refinement keeps tactile predictions aligned with evolving physical interactions, enabling responsive action correction and improving robustness to contact changes and execution errors. We further introduce XHT-Dataset, comprising 900 real-world demonstrations across seven contact-rich tasks collected on an XHand--UR7e platform, and evaluate ReTouch through closed-loop real-robot experiments. ReTouch surpasses the strongest baseline by 18.4 and 23.8 percentage points in average success rate under standard and challenging conditions, respectively, demonstrating its effectiveness and robustness.
Robotics (cs.RO)
arXiv:2608.01824 [cs.RO]
(or arXiv:2608.01824v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2608.01824 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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.
Full text under the publisher's open licence · 285 words
Related coverage
SkillWeave: Weaving Heterogeneous Demonstrations into Long-Horizon Manipulation Skills
arXiv · Oct 9, 2026
HACo: Learning Haptic Active Compliance for Force-Aware Dexterous Manipulation
arXiv · Sep 30, 2026
BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models
arXiv · Oct 2, 2026
Rapid Learning of Dexterous In-Hand Pen Writing through Real-Time Jacobian Estimation
arXiv · Sep 11, 2026