Transforming quadruped robot runs on real hardware: per-pose RL policies in Isaac switched on morph
_Stocko_ · x · 2026-10-16
Japanese developer fusnail demonstrates transformation plus walking on a real quadruped robot. Each pose is trained separately with reinforcement learning in Isaac; inference runs on ATOMS3R, and separate walking policies for each post-transform pose are implemented and switched at morph time.
More from Embodied
- Fake Apple listing for dual-screen 'iPhone Duo' jokes it's the best phone for watching your AI agents — AIFlow_ML · 2026-10-16
- Inside Auki's Hong Kong office: a fake grocery store powering robotics data collection — LoganGrasby · 2026-10-16
- Physicist calls compressed-air car a scam: one charge would take a week of compressor time — rickasaurus · 2026-10-16
- Robot gives thumbs-up from inside an upside-down car: 'peak tech moment' — NicoVerderosa · 2026-10-16
- NVIDIA launches RTX Spark for local AI on Windows PCs — ostrisai · 2026-10-16
- Foldable iPhone Duo reportedly sells out launch-day inventory, some deliveries slip to 2027 — Polymarket · 2026-10-16