Skip to content
aiqbench takeAI Products

aiqbench analysis

This study establishes cluttered dexterous grasping as a critical benchmark for robotics, demonstrating that combining vision with tactile wrench and taxel feedback significantly outperforms visual-only approaches in real-world scenarios. The findings reveal a widening "vision-interaction gap," proving that interaction sensing is essential for early contact rejection and stable manipulation when occlusions obscure visual geometry. This work advances the field by quantifying exactly when learned policies must integrate physical interaction signals to succeed in complex environments.
Source coveringarXiv
What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

When Does Touch Matter? Charting the Vision-Interaction Gap in Cluttered Dexterous Grasping

arXiv2 min read

arXiv:2609.24068v1 Announce Type: new Abstract: Dexterous grasping in clutter poses a basic sensing question: when do tactile measurements and external wrench estimates improve on visual geometry? Occlusion and contact can obscure grasp quality, motivating a controlled evaluation of these interaction signals. We present a controlled real-world study over five tabletop scene conditions on a dexterous system that combines vision, per-finger and wrist wrench estimates, and distributed fingertip taxels. With demonstrations, visual observations, action space, and compliant control fixed, we compare vision-only, wrench, taxel, and combined policies plus representation and fusion baselines. The combined policy succeeds in 24/25 trials versus 14/25 for vision only, and 15/15 versus 6/15 across the three confined conditions. Ablations show that wrench and taxel feedback are complementary. Behavioral comparisons show that interaction feedback enables earlier rejection of inadequate contacts, regrasping before lift, and more stable grasps. To our knowledge, this is the first real-world study to combine and separately evaluate these interaction modalities for target-oriented dexterous grasping in clutter. These results chart a widening vision-interaction gap and position cluttered dexterous grasping as a benchmark for determining when the learned policy needs interaction sensing. Project website: https://interaction-dex-grasp.github.io/

Title:When Does Touch Matter? Charting the Vision-Interaction Gap in Cluttered Dexterous Grasping

Abstract:Dexterous grasping in clutter poses a basic sensing question: when do tactile measurements and external wrench estimates improve on visual geometry? Occlusion and contact can obscure grasp quality, motivating a controlled evaluation of these interaction signals. We present a controlled real-world study over five tabletop scene conditions on a dexterous system that combines vision, per-finger and wrist wrench estimates, and distributed fingertip taxels. With demonstrations, visual observations, action space, and compliant control fixed, we compare vision-only, wrench, taxel, and combined policies plus representation and fusion baselines. The combined policy succeeds in 24/25 trials versus 14/25 for vision only, and 15/15 versus 6/15 across the three confined conditions. Ablations show that wrench and taxel feedback are complementary. Behavioral comparisons show that interaction feedback enables earlier rejection of inadequate contacts, regrasping before lift, and more stable grasps. To our knowledge, this is the first real-world study to combine and separately evaluate these interaction modalities for target-oriented dexterous grasping in clutter. These results chart a widening vision-interaction gap and position cluttered dexterous grasping as a benchmark for determining when the learned policy needs interaction sensing. Project website: this https URL

9 pages, 7 figures, 2 tables. Project website: this https URL

Robotics (cs.RO)

arXiv:2609.24068 [cs.RO]

(or arXiv:2609.24068v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2609.24068 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 · 303 words

Related coverage