Goal-conditioned locomotion in sim: recovery policy survives stairs and slopes
burny_tech · x · 2026-11-12
surenat's team is testing goal-conditioned locomotion in simulation: give the robot a goal and let it figure out how to get there, yielding results between locomotion, navigation, and parkour. The harder problem is real-world recovery — falls on stairs, slopes, edges, and odd orientations still require the policy to get the robot back on its feet — and their recovery policy is holding up surprisingly well so far.
More from Embodied
- AI agents drive through GTA 6's Vice City with an army in tow — MicahBerkley · 2026-11-12
- Claude designed a humanoid robot overnight: 698 parts, 33 actuators, self-iterated balance — Distinct-Question-16 · 2026-11-12
- Meta Releases XRStereo: ~18k-Sequence Synthetic Stereo Dataset on Hugging Face — _akhaliq · 2026-11-12
- Liquid AI lays out roadmap to put AI on half the world's devices via model-hardware co-design — JosephJacks_ · 2026-11-12
- Wayve unveils Learned Safety Envelope: end-to-end trained live risk prediction for AI driving — alexgkendall · 2026-11-12
- Pro-0 trains dexterous robot hands from human demos with zero on-robot data — chris_j_paxton · 2026-11-12