TacClaw-Infinity: Large-Scale Vision-Tactile-Language-Action Dataset for Dexterous Manipulation
CyberRobooo · x · 2026-11-09
TacClaw-Infinity is a large-scale Vision-Tactile-Language-Action dataset for dexterous manipulation, released with paper, project page, GitHub, Hugging Face, and ModelScope downloads.
Motivation: humanoid robots stocking shelves must handle soft plastic bags, rigid cartons and slippery bottles—beyond visual recognition, robots need to regulate grip force, detect slipping, and adapt to changing contact conditions. Vision tells robots what they pick up; tactile feedback tells them how contact is going.
Related event: TacClaw-Infinity: Massive Tactile Dataset Lifts Robot Grasping(2 posts)→
More from Embodied
- Guava distills GPT-5.4 into a 4B robot agent with just 2,000 simulated trajectories — jbhuang0604 · 2026-11-09
- Dex-One2Many learns dexterous manipulation from one human video, 95%+ success across 4 hands — jbhuang0604 · 2026-11-09
- Fly-by-Code: coding agents pilot drones via active visual and physical feedback loops — jbhuang0604 · 2026-11-09
- μ0 world model learns robot physics from video only, beats π0 by 5 points on RoboCasa365 — jbhuang0604 · 2026-11-09
- NVIDIA unveils GR00T 2 open-world robot action model, hitting 95% success with 5 demos — CyberRobooo · 2026-11-09
- CoRL keynote to explore open-source data and hardware for robotics — micoolcho · 2026-11-09