HKUST(GZ) lab lands 3 CoRL 2026 papers, unveils terrain-adaptive robot motion model
Scobleizer · x · 2026-09-06
HKUST(GZ)'s Junwei Liang lab announced 3 papers accepted at CoRL 2026:
- Perceptive Behavior Foundation Model: adapts human motion priors to robot-centric terrain. A single policy takes arbitrary flat-ground human-motion references (one-leg backflips, stair dances, obstacle crossings) and uses onboard vision to resolve footholds, swing clearance, and contact timing, without changing the raw kinematic command interface. Terrain-Conformal References (TCRS) supervise training offline, and a zero-initialized residual vision pathway applies corrections only where terrain demands. Live demo runs in-browser via MuJoCo WASM + ONNX Runtime.
- MeshMimic: geometry-aware humanoid motion learning through 3D scene reconstruction.
- Look Before You Move: agent-interface-aligned supervision for open-world mobile manipulation; code and models coming soon.
More from Embodied
- Asimov humanoid robot Day 345: testing full-body teleoperation — freelerobot · 2026-09-06
- First-time Tesla Cybercab robotaxi rider loves the experience, says whurley — whurley · 2026-09-06
- Polymarket Puts Only 22% Odds on Tesla Launching California Robotaxis by Year-End — Polymarket · 2026-09-06
- Paraplegic user rates Tesla CyberCab 10/10 in viral accessibility review — elonmusk · 2026-09-06
- Musk signals Tesla could turn Cybercab tech into a consumer AI-driven car lineup — elonmusk · 2026-09-06
- Roboticist: Next Frontier Is Truly Leveraging AI Models for Manipulation, Not Agent Wrappers — chris_j_paxton · 2026-09-06