Ant's open-source LingBot-Touch tactile foundation model lifts success rates 14-26 pts
aigclink · x · 2026-11-10
Ant Group open-sourced LingBot-Touch, a tactile foundation model giving robots a sense of "touch" beyond vision, with tactile experience reusable across sensors, dexterous hands, models, and tasks.
Key details:
- Pretrained on nearly 5,000 hours of real tactile data covering magnetic, visuotactile, and piezoresistive sensing
- Sensor-specific encoders map different tactile layouts into a unified fingertip coordinate space
- A shared model learns contact position, force, and temporal dynamics, outputting unified tactile tokens
Results: average task success rate improves 14-26 percentage points over no-tactile baselines. Demo images span Baoding ball rotation, pen spinning, nut assembly, plate spinning, blind grasping, and ball balancing across Sharpa and XHand hands.
Significance: instead of re-collecting data and retraining for each new hand or sensor, this builds a cross-hardware general tactile representation.
Related event: Ant's Robbyant Open-Sources LingBot-Touch Tactile Foundation Model(30 posts)→
More from Embodied
- Long-horizon mobile manipulation called the standout demo at CoRL — JasonMa2020 · 2026-11-11
- UCLA's TRIMI turns the data glove itself into the robot hand — DennisHongRobot · 2026-11-11
- Supersplat XR update: Quest 3 streamed scenes jump from 9.7 to 30+ fps, Vision Pro gets WebGPU — willeastcott · 2026-11-11
- Cartwheel releases three open motion-tracking policies for humanoid robots on Hugging Face — andrew_n_carr · 2026-11-11
- Claude Fable 5.2 designs a humanoid robot overnight with CAD, sim and reel — davidpattersonx · 2026-11-11
- Russ Tedrake's CoRL talk: deploy robots early, train on intervention data to scale — DominiqueCAPaul · 2026-11-11