TacGooseBumps (TacGB): Retrofitting Normal-Only Tactile Sensors with Shear Encoding for Learning Contact-Rich Manipulation

2026-09-27

AI Summary

This study addresses the limitation of normal tactile sensors, which lack tangential information and thus struggle to distinguish similar physical states during contact-rich manipulation. To overcome this, we propose a shear-encoding mechanism based on a passive dome membrane that mechanically transduces tangential loads into pattern variations in pressure maps. This design requires no additional electronic components, hardware modifications, or force reconstruction. By integrating end-to-end pressure map processing with imitation learning strategies, the approach achieves effective tactile enhancement. We demonstrate that non-metric shear signals are sufficient to improve robot learning performance. In insertion tasks, the success rate increases by 36%, yielding more efficient and gentler manipulation. These results indicate significant improvements in complex operations that rely heavily on tangential interactions.

Abstract

Contact-rich policies often fail because distinct physical states look alike yet require different actions. Cameras may not reveal whether a connector is aligned or fully seated, while many normal-only tactile sensors can miss the tangential interactions perpendicular to the grasping direction that distinguish these states. We ask whether a learning policy needs calibrated shear measurements, or only a repeatable observation that separates shear-dependent contact states. We introduce TacGooseBumps (TacGB), a passive domed film that mechanically encodes tangential loading as pattern changes in an existing sensor's pressure map. Tangential loading tilts each dome and redistributes pressure across its footprint; an end-to-end policy consumes the resulting maps without added electronics, force reconstruction, or taxel-level dome alignment. Across four imitation-learning tasks and two data-collection pipelines, TacGB improves goal attainment, efficiency, and contact quality: insertion success increases by up to 36 percentage points, and successful insertions are completed faster, while fragile-object placement becomes gentler and drawing becomes more continuous and straight. Signal, stage-wise, failure-mode, and trajectory analyses link these gains to contact regimes in which task-relevant tangential interactions are poorly resolved by vision and normal pressure alone. Together, these results show that shear need not be measured metrically to benefit robot learning; it can instead be mechanically encoded without changing the underlying tactile sensor or the policy's pressure-map input format.

Problem

• tactile sensing
• shear encoding
• contact-rich manipulation
• normal-only sensors
• imitation learning

Innovation

• Tactile sensing
• Shear encoding
• Contact-rich manipulation
• Imitation learning
• Passive mechanical retrofit