ETH's AME-2 legged locomotion paper accepted at TRO, training code open-sourced
ChongZzZhang · x · 2026-10-06
Chong Zhang of ETH Zurich announced that AME-2 — "Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding" (Zhang, Klemm, Yang, Hutter) — is officially accepted at IEEE Transactions on Robotics.
The team open-sourced leggedrobotics/ame2minimal, an official reimplementation for G1 training built on IsaacLab 2.3.2 and rslrl, installable via Docker container. The author notes the codebase was mostly vibe-coded and recommends onboarding with a coding agent.
More from Embodied
- Robotics researcher slams microfactory demo as 'too perfect' sim missing real-world contact dynamics — ChongZzZhang · 2026-10-06
- YC robot data startup wins customers in a commoditized market by out-supplying rivals — paigeinsf · 2026-10-06
- Flashing Telink firmware via Flipper Zero to hack Tuya Zigbee devices — ngxson · 2026-10-06
- Norway to propose temporary ban on AI glasses in some public places — talkingatoms · 2026-10-06
- DIY ESP32-S3 pocket voice assistant with e-paper display and Hermes agent routing — K8s-monk · 2026-10-06
- Jobs Called Touchscreen Macs 'Terrible' — 16 Years Later, Apple May Ship One — Kiteaton · 2026-10-06