TacGB adds shear sensing to tactile sensors for better robot touch
TacGooseBumps (TacGB): Retrofitting Normal-Only Tactile Sensors with Shear Encoding for Learning Contact-Rich Manipulation
Robotics
Summary
Robots often struggle to tell the difference between similar touches that need different actions, especially when sliding or sideways forces happen. Cameras and normal tactile sensors usually miss these sideways, or shear, forces. The authors created TacGooseBumps (TacGB), a simple dome-shaped film that changes the pressure pattern on existing sensors when touched from the side. This helps robots learn tasks better without needing complicated new hardware. In tests, TacGB helped robots insert connectors more successfully, handle fragile objects more gently, and draw more smoothly.
What this means in practice
- •For robotics engineers: Improve robot grasping and insertion tasks by adding TacGB to existing tactile sensors without new electronics.
- •For manufacturing automation teams: Enhance precision and speed in automated assembly lines by detecting subtle contact states with TacGB retrofitted sensors.
Authors
Wenjie Li, Binyu Yang, Yuxin Chen, Ambrose Wang, Masayoshi Tomizuka
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.