TransTac: Visuo-Tactile Modality Transition via Ultraviolet-Encoded Transparent Elastomers
2026-06-03 • Robotics
Robotics
AI summaryⓘ
The authors developed TransTac, a new type of touch sensor that is see-through and uses ultraviolet (UV) light to detect touch shapes with a camera. Unlike usual tactile sensors that block sight, their device combines touch sensing and visual input in one small tool using special UV markers inside a clear gel. They made a smart method to find these markers accurately even when the surface is pressed or bent, improving the sensor's reliability. Tests showed TransTac recognizes touch patterns better than older opaque sensors and works well with regular images, and it costs about $70 to build. The authors also showed how their device helps fix problems with regular depth cameras when objects are very close.
Vision-based tactile sensorsTransparent elastomerUltraviolet (UV) markersDelaunay stereo matchingStereo triangulationRGB-D camerasTactile image recognitionCross-modal alignmentSparse triangulationVisuo-tactile integration
Authors
Lingyue Yang, Bin Fang
Abstract
Vision-based tactile sensors (VBTS) recover high-resolution contact geometry but typically rely on opaque elastomer layers that prevent visual transparency, while RGB-D cameras provide global depth perception yet degrade significantly at close range. To address this limitation, we present TransTac, a transparent ultraviolet (UV)-encoded binocular VBTS that integrates visual observation and marker-based tactile reconstruction within a single compact device. The system employs a transparent elastomer embedded with UV-reflective markers and a prior-guided Delaunay stereo matching algorithm for robust sparse triangulation. To reliably detect densely distributed semitransparent markers, we develop a lightweight detector that enables stable localization under contact and deformation. The proposed prior-guided Delaunay matching improves correspondence robustness by approximately 21% compared with global assignment baselines while maintaining high reconstruction accuracy. In semantic evaluation, TransTac achieves up to 83.3% zero-shot recognition accuracy on tactile images, exceeding opaque tactile baselines by approximately 50 percentage points. Embedding analysis further reveals substantially stronger cross-modal alignment with natural images, with class-center similarity increasing from around 0.2 to over 0.77. Controlled near-distance experiments quantify the degradation of RGB-D depth reliability and demonstrate extended geometric coverage enabled by visuo-tactile integration. Finally, a compact prototype is implemented with an approximate hardware cost of $70.