Testing the walking policy of open-source humanoid Asimov in simulation
freelerobot · x · 2026-10-29
Menlo Research's Asimov, one of the most developer-friendly open-source humanoids, learned to walk via reinforcement learning earlier this year. A new article tests its walking policy in simulation, showing the progress made by late August.
More from Embodied
- Zero-HLM trains humanoid loco-manipulation with zero real robot data, lifting success 23% to 69% — siyuanhuang95 · 2026-10-29
- Matrix-3 humanoid debuts at Wuzhen World Internet Conference, built for service work — CyberRobooo · 2026-10-29
- China's ultra-realistic androids blur the line between human and machine — LexiLove · 2026-10-29
- Unreleased Mac Studio with M5 Ultra spotted in Apple Store: 512GB memory, $29,999 — nikitabier · 2026-10-29
- Robotics figure Fowe lands in Bay Area for Berkeley robotics symposium BARS — Fowe · 2026-10-29
- DIY metal upper-body exoskeleton rigs for robot teleoperation revealed by two builders — mattfreed · 2026-10-29