aiqbench analysis
This research addresses a critical gap in Vision-Language-Action (VLA) models by integrating tactile perception to improve performance on contact-rich robotic manipulation tasks. The authors introduce OmniVTLA, which utilizes a dual-path encoder and the new ObjTac dataset to unify diverse sensor inputs into semantically aligned representations. Real-world testing confirms that this approach significantly boosts success rates for both grippers and dexterous hands while optimizing task trajectories.
OmniVTLA: Vision-Tactile-Language-Action Models with Semantic-Aligned Tactile Sensing
arXiv:2508.08706v3 Announce Type: replace Abstract: Recent vision-language-action (VLA) models build upon vision-language foundations, and have achieved promising results and exhibit the possibility of task generalization in robot manipulation. However, due to the heterogeneity of tactile sensors and the difficulty of acquiring tactile data, current VLA models significantly overlook the importance of tactile perception and fail in contact-rich tasks. To address this issue, this paper proposes OmniVTLA, a novel architecture involving tactile sensing. Specifically, our contributions are threefold. First, our OmniVTLA features a dual-path tactile encoder framework. This framework enhances tactile perception across diverse vision-based and force-based tactile sensors by using a pretrained vision transformer (ViT) and a semantically-aligned tactile ViT (SA-ViT). Second, we introduce ObjTac, a comprehensive force-based tactile dataset capturing textual, visual, and tactile information for 56 objects across 10 categories. With 135K tri-modal samples, ObjTac supplements existing visuo-tactile datasets. Third, leveraging this dataset, we train a semantically-aligned tactile encoder to learn a unified tactile representation, serving as a better initialization for OmniVTLA. Real-world experiments demonstrate substantial improvements over state-of-the-art VLA baselines, achieving 96.9% success rates with grippers, (21.9% higher over baseline) and 100% success rates with dexterous hands (6.2% higher over baseline) in pick-and-place tasks. Besides, OmniVTLA significantly reduces task completion time and generates smoother trajectories through tactile sensing compared to existing VLA. Our ObjTac dataset can be found at https://readerek.github.io/Objtac.github.io
Abstract:Recent vision-language-action (VLA) models build upon vision-language foundations, and have achieved promising results and exhibit the possibility of task generalization in robot manipulation. However, due to the heterogeneity of tactile sensors and the difficulty of acquiring tactile data, current VLA models significantly overlook the importance of tactile perception and fail in contact-rich tasks. To address this issue, this paper proposes OmniVTLA, a novel architecture involving tactile sensing. Specifically, our contributions are threefold. First, our OmniVTLA features a dual-path tactile encoder framework. This framework enhances tactile perception across diverse vision-based and force-based tactile sensors by using a pretrained vision transformer (ViT) and a semantically-aligned tactile ViT (SA-ViT). Second, we introduce ObjTac, a comprehensive force-based tactile dataset capturing textual, visual, and tactile information for 56 objects across 10 categories. With 135K tri-modal samples, ObjTac supplements existing visuo-tactile datasets. Third, leveraging this dataset, we train a semantically-aligned tactile encoder to learn a unified tactile representation, serving as a better initialization for OmniVTLA. Real-world experiments demonstrate substantial improvements over state-of-the-art VLA baselines, achieving 96.9% success rates with grippers, (21.9% higher over baseline) and 100% success rates with dexterous hands (6.2% higher over baseline) in pick-and-place tasks. Besides, OmniVTLA significantly reduces task completion time and generates smoother trajectories through tactile sensing compared to existing VLA. Our ObjTac dataset can be found at this https URL
Accepted by IEEE Robotics and Automation Letters (RA-L). ObjTac dataset: this https URL
Robotics (cs.RO)
arXiv:2508.08706 [cs.RO]
(or arXiv:2508.08706v3 [cs.RO] for this version)
Full text under the publisher's open licence · 243 words
Related coverage
{\tau}: Learning Touch-Augmented Vision-Language-Action Models from Future Visual Supervision
arXiv · Jul 28, 2026
$N_0$-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens
arXiv · Jul 28, 2026
HapTile: A Haptic-Informed Vision-Tactile-Language-Action Dataset for Contact-Rich Imitation Learning
arXiv · Jun 4, 2026
Touvigation: Embodied Adaptive Object Acquisition for Blind and Low-Vision Users in Unfamiliar Indoor Environments
arXiv · Sep 22, 2026