HDMI open-sourced: whole-body robot interaction skills learned from human videos
chris_j_paxton · x · 2026-09-08
Elijah Galahad open-sourced HDMI, a general framework for learning whole-body robot interaction skills directly from human videos — no manual reward engineering or task-specific pipelines required.
- Demonstrated 67 door traversals in the real world across 6 real tasks, plus 14 simulated tasks
- HDMI extends MimicLite from robot-only motion tracking to paired robot-object interaction tracking
- The rewritten release adds a new Mjlab backend and single-object multi-motion support
- The GitHub README includes full uv + MjLab setup and reproduction commands, with W&B and HuggingFace credentials configuration
More from Embodied
- Musk touts CyberCab ride experience, hopes service comes to Europe soon — elonmusk · 2026-09-08
- Opendoor founder Eric Wu's NavigateAI builds hands-free AI copilots for construction workers — saranormous · 2026-09-08
- GPT-6 'Astra' learns to control a real robot arm and paint the Golden Gate Bridge — alexeyguzey · 2026-09-08
- US police fear Meta smart glasses could be used to secretly record them — bookofjoe · 2026-09-08
- GPT-6 Astra vs MediaPipe for hand pose: SOTA reasoning, 3 min per frame — chris_j_paxton · 2026-09-08
- After 10+ Kindles, this reader says the Xteink x3 is the most portable yet — 6 books in 23 days — Technovangelist · 2026-09-08