UCLA's Visible Touch turns touch into image overlays, boosting VLA robot success by up to 30pp
Scobleizer · x · 2026-11-10
UCLA researchers presented Visible Touch as a CoRL 2026 Spotlight: instead of adding specialized tactile hardware or encoders, it renders contact feedback as image-space overlays on the policy's RGB observations, so any image-conditioned policy — including pretrained VLAs — can use touch with zero architectural changes.
Results:
- +15.7pp for BC-Transformer on LIBERO (2-view)
- +25.3pp for miniVLA fine-tuning on LIBERO
- +30.3pp for π₀.₅ on four real-world manipulation tasks
- Paired with an open-source magnetic contact sensor built from off-the-shelf parts for under $50
Scobleizer frames it as evidence that robots don't need expensive touch sensors — cameras plus smart encoding suffice — and that CoRL research quality has jumped markedly this year, one reason investors are pouring money into robotics.
More from Embodied
- Beff Jezos wants hands-free AR glasses for navigation after traveling in Japan — beffjezos · 2026-11-10
- NVIDIA DLSS 5 Wins CES 2027 Best of Innovation Award for 3D-Guided Neural Rendering — ctnzr · 2026-11-10
- China's brain-reading device hits 94% mind-typing accuracy in day-long use — yogthos · 2026-11-10
- Brown PhD candidate Rahul Sajnani seeks robotics world-model research roles, advisor endorses — drsrinathsridha · 2026-11-10
- HuGo: Berkeley Team's LLM-Designed Humanoid Whole-Body Policy Paper Spotlit at CoRL 2026 — m_wulfmeier · 2026-11-10
- UniWALM: one diffusion video backbone for planning, memory and manipulation — drsrinathsridha · 2026-11-10