aiqbench analysis
HapTile addresses a critical gap in current Vision-Language-Action datasets by integrating synchronized fingertip tactile feedback and haptic-informed teleoperation, moving beyond vision-only paradigms for contact-rich manipulation tasks. This dataset provides a reproducible benchmark for training policies that leverage physical interaction sensing to improve demonstration quality and stability in everyday robotic skills. The inclusion of language-conditioned action trajectories alongside visuotactile observations offers a robust foundation for advancing imitation learning in complex, tactile-dependent environments.
HapTile: A Haptic-Informed Vision-Tactile-Language-Action Dataset for Contact-Rich Imitation Learning
arXiv:2606.04825v1 Announce Type: new Abstract: Despite the importance of tactile sensing for reliable manipulation, most existing Vision-Language-Action (VLA) datasets remain vision-only, and those that do incorporate tactile information typically lack the joint combination of task diversity, language conditioning, and action trajectories. Furthermore, existing teleoperation pipelines rarely provide haptic feedback to the operator, despite its established role in demonstration quality and manipulation stability. In this work, we present HapTile, a contact-grounded visuotactile manipulation dataset that advances beyond vision-only trajectory datasets by embedding physical interaction sensing at two levels: fingertip tactile feedback at the robot end-effector, and haptic-informed demonstrations at the teleoperator side. The data collection platform integrates haptic feedback directly into the teleoperation controller, enabling the operator to perceive contact interactions in real time. It is built around a standard and reproducible robotic system equipped with custom-designed fingertip tactile sensors. The dataset comprises everyday manipulation tasks spanning a broad range of contact-rich skills, including pick-and-place, folding, pressing, stacking, and other routine activities. Each task is paired with language instructions that condition the policy on the manipulation objective, together with synchronized visuotactile observations and action trajectories. In addition, we provide a benchmarking study on contact-rich policy learning using two baseline models to evaluate the effectiveness of the proposed contact-grounded dataset. The dataset and additional details are available on our website: haptile-dataset.github.io.
Abstract:Despite the importance of tactile sensing for reliable manipulation, most existing Vision-Language-Action (VLA) datasets remain vision-only, and those that do incorporate tactile information typically lack the joint combination of task diversity, language conditioning, and action trajectories. Furthermore, existing teleoperation pipelines rarely provide haptic feedback to the operator, despite its established role in demonstration quality and manipulation stability. In this work, we present HapTile, a contact-grounded visuotactile manipulation dataset that advances beyond vision-only trajectory datasets by embedding physical interaction sensing at two levels: fingertip tactile feedback at the robot end-effector, and haptic-informed demonstrations at the teleoperator side. The data collection platform integrates haptic feedback directly into the teleoperation controller, enabling the operator to perceive contact interactions in real time. It is built around a standard and reproducible robotic system equipped with custom-designed fingertip tactile sensors. The dataset comprises everyday manipulation tasks spanning a broad range of contact-rich skills, including pick-and-place, folding, pressing, stacking, and other routine activities. Each task is paired with language instructions that condition the policy on the manipulation objective, together with synchronized visuotactile observations and action trajectories. In addition, we provide a benchmarking study on contact-rich policy learning using two baseline models to evaluate the effectiveness of the proposed contact-grounded dataset. The dataset and additional details are available on our website: this http URL.
Robotics (cs.RO)
arXiv:2606.04825 [cs.RO]
(or arXiv:2606.04825v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.04825 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 · 309 words
Related coverage
OmniVTLA: Vision-Tactile-Language-Action Models with Semantic-Aligned Tactile Sensing
arXiv · Jun 16, 2026
{\tau}: Learning Touch-Augmented Vision-Language-Action Models from Future Visual Supervision
arXiv · Jul 28, 2026
STAR: Sparse Tactile Representation Learning in Vision-Tactile-Language-Action Models for Dexterous Manipulation
arXiv · Sep 14, 2026
XRoboToolKit-T: Teleoperation with High Stability and Precision with Tactile Sensing for Contact-rich Manipulation
arXiv · Sep 16, 2026