Light-Loco-Parkour shows humanoid robots zero-shot navigating complex terrain on onboard compute
chris_j_paxton · x · 2026-09-16
Light Origins' Light-Loco-Parkour demonstrates a humanoid robot policy that decides when to walk, vault, or climb across complex terrain using only onboard sensing and compute. Unlike methods relying on large motion corpora, it trains with sparse seeds and no sub-task labels, learning when to deploy its locomotion skills. The team discussed details on Episode 104 of RoboPapers.
Related event: Light Origins Shows Zero-Shot Humanoid Parkour on Rough Terrain(2 posts)→
More from Embodied
- Anthropic previews Model Hardware Standard to let AI agents run lab instruments — ivan_bezdomny · 2026-09-16
- World's first 10,000-unit-scale humanoid robot factory starts production — yogthos · 2026-09-16
- First M5 Ultra Geekbench leak: 52,516 multi-core, ~35% faster than M3 Ultra — jedisct1 · 2026-09-16
- Fei-Fei Li's World Labs is hiring robot learning researchers to scale world models — YunzhuLiYZ · 2026-09-16
- Figure CEO Brett Adcock Shows Off New F.03 Humanoid Robot at Dreamforce — adcock_brett · 2026-09-16
- Berseth: Self-driving shows cost cuts aren't enough — real-time closed-loop control is the hard part — GlenBerseth · 2026-09-16