analiza aiqbench
This research introduces Uni-VLaT, a novel architecture that integrates whole-body distributed tactile sensing into vision-language-action policies for humanoid robots. By training latent states to predict future tactile, proprioceptive, and visual inputs, the method significantly enhances performance in contact-rich tasks like loco-manipulation and human-robot interaction. The study demonstrates that predictive tactile learning effectively extends pretrained VLA models to handle complex physical interactions where vision alone is insufficient.
Uni-VLaT: Whole-Body Tactile Adaptation of VLA Policies for Humanoid Loco-Manipulation
arXiv:2609.35450v1 Announce Type: new Abstract: Physical contact often determines how a humanoid should respond during loco-manipulation, yet vision and proprioception alone are often insufficient to characterize physical interaction, especially when the contact region is occluded. Unlike sparse force or torque measurements at predefined regions, distributed tactile sensing preserves spatially resolved contact patterns across the robot body. We therefore study how to integrate such whole-body tactile information into vision-language-action (VLA) policies for contact-rich control. Our approach, Uni-VLaT, introduces a tactile pathway whose latent state is trained not only for action generation, but also to predict future tactile, proprioceptive, and visual representations. This predictive objective builds a tactile-anchored multimodal context, encouraging a more structured understanding of the physical world. We evaluate Uni-VLaT on five real-robot tasks covering tactile-triggered locomotion, sustained physical interaction, human-robot contact, and loco-manipulation. Uni-VLaT achieves a 75% average success rate, outperforming a baseline without tactile input by 43 points and a tactile-input baseline without predictive supervision by 7 points. Across two pretrained VLA backbones, our method improves Table Sweeping by 30 points on both backbones and Back-Tap Walking by 85-90 points. Ablations further show that contextualized tactile prediction and absolute future targets are critical to performance. These results indicate that predictive tactile learning provides an effective route for extending pretrained VLA policies to whole-body physical interaction.
Abstract:Physical contact often determines how a humanoid should respond during loco-manipulation, yet vision and proprioception alone are often insufficient to characterize physical interaction, especially when the contact region is occluded. Unlike sparse force or torque measurements at predefined regions, distributed tactile sensing preserves spatially resolved contact patterns across the robot body. We therefore study how to integrate such whole-body tactile information into vision-language-action (VLA) policies for contact-rich control. Our approach, Uni-VLaT, introduces a tactile pathway whose latent state is trained not only for action generation, but also to predict future tactile, proprioceptive, and visual representations. This predictive objective builds a tactile-anchored multimodal context, encouraging a more structured understanding of the physical world. We evaluate Uni-VLaT on five real-robot tasks covering tactile-triggered locomotion, sustained physical interaction, human-robot contact, and loco-manipulation. Uni-VLaT achieves a 75% average success rate, outperforming a baseline without tactile input by 43 points and a tactile-input baseline without predictive supervision by 7 points. Across two pretrained VLA backbones, our method improves Table Sweeping by 30 points on both backbones and Back-Tap Walking by 85-90 points. Ablations further show that contextualized tactile prediction and absolute future targets are critical to performance. These results indicate that predictive tactile learning provides an effective route for extending pretrained VLA policies to whole-body physical interaction.
Robotics (cs.RO)
arXiv:2609.35450 [cs.RO]
(or arXiv:2609.35450v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.35450 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.
Text integral sub licența deschisă a publicației · 305 cuvinte
Subiecte conexe
HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL
arXiv · 18 aug. 2026
Learning Versatile Humanoid Manipulation with Touch Dreaming
arXiv · 18 aug. 2026
Towards a General Humanoid Loco-Manipulation Model via Egocentric Whole-Body Human Data Pretraining
arXiv · 2 oct. 2026
X-Loco: Towards Generalist Humanoid Locomotion Control via Synergetic Policy Distillation
arXiv · 16 iun. 2026