aiqbench analysis
This research advances robotic manipulation by demonstrating that structured force-field representations outperform vision-only or simple multimodal fusion in contact-rich disassembly tasks. The study highlights the critical necessity of tactile sensing for handling deformable objects and tight-tolerance scenarios where geometric alignment alone is insufficient.
CONTACT: CONtact-aware TACTile Learning for Robotic Disassembly
arXiv:2603.08560v2 Announce Type: replace Abstract: Robotic disassembly involves contact-rich interactions in which successful manipulation depends not only on geometric alignment but also on force-dependent state transitions. While vision-based policies perform well in structured settings, their reliability often degrades in tight-tolerance, contact-dominated, or deformable scenarios. In this work, we systematically investigate the role of tactile sensing in robotic disassembly through both simulation and real-world experiments. We construct five rigid-body disassembly tasks in simulation with increasing geometric constraints and extraction difficulty. We further design five real-world tasks, including three rigid and two deformable scenarios, to evaluate contact-dependent manipulation. Within a unified learning framework, we compare three sensing configurations: Vision Only, Vision + tactile RGB (TacRGB), and Vision + tactile force field (TacFF). Across both simulation and real-world experiments, TacFF-based policies consistently achieve the highest success rates, with particularly notable gains in contact-dependent and deformable settings. Notably, naive fusion of TacRGB and TacFF underperforms either modality alone, indicating that simple concatenation can dilute task-relevant force information. Our results show that tactile sensing plays a critical, task-dependent role in robotic disassembly, with structured force-field representations being particularly effective in contact-dominated scenarios.
Abstract:Robotic disassembly involves contact-rich interactions in which successful manipulation depends not only on geometric alignment but also on force-dependent state transitions. While vision-based policies perform well in structured settings, their reliability often degrades in tight-tolerance, contact-dominated, or deformable scenarios. In this work, we systematically investigate the role of tactile sensing in robotic disassembly through both simulation and real-world experiments. We construct five rigid-body disassembly tasks in simulation with increasing geometric constraints and extraction difficulty. We further design five real-world tasks, including three rigid and two deformable scenarios, to evaluate contact-dependent manipulation. Within a unified learning framework, we compare three sensing configurations: Vision Only, Vision + tactile RGB (TacRGB), and Vision + tactile force field (TacFF). Across both simulation and real-world experiments, TacFF-based policies consistently achieve the highest success rates, with particularly notable gains in contact-dependent and deformable settings. Notably, naive fusion of TacRGB and TacFF underperforms either modality alone, indicating that simple concatenation can dilute task-relevant force information. Our results show that tactile sensing plays a critical, task-dependent role in robotic disassembly, with structured force-field representations being particularly effective in contact-dominated scenarios.
Accepted to IROS 2026. Project page: this https URL
Robotics (cs.RO)
arXiv:2603.08560 [cs.RO]
(or arXiv:2603.08560v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2603.08560 Focus to learn more arXiv-issued DOI via DataCite
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 · 282 words
Related coverage
TacVLA: Contact-Aware Tactile Fusion for Robust Vision-Language-Action Manipulation
arXiv · Sep 2, 2026
Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning
arXiv · Jun 12, 2026
Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning
arXiv · Jun 11, 2026
RATE: Risk-Aware Tactile Encoding for Contact-rich Robotic Manipulation
arXiv · Oct 5, 2026