CONTACT: CONtact-aware TACTile Learning for Robotic Disassembly

TL;DR

This paper demonstrates that tactile sensing, especially force-field representations, significantly improves robotic disassembly success in contact-rich and deformable scenarios, outperforming vision-only approaches.

Contribution

It introduces a unified learning framework comparing vision-only, tactile RGB, and tactile force field sensing, highlighting the effectiveness of structured force representations in contact-dependent tasks.

Findings

TacFF policies outperform other sensing modalities in success rates.

Tactile sensing is crucial for contact-rich and deformable disassembly tasks.

Naive fusion of tactile RGB and force field can reduce performance.

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.