Galbot's PASSAGE: humanoid traversal framework hits 98.67% success
chris_j_paxton · x · 2026-10-13
Galbot introduces PASSAGE, a framework combining environmental perception, whole-body motion planning, and closed-loop control, letting humanoid robots autonomously plan and execute flexible traversal motions based on their surroundings. Trained on 100 hours of human data across 1,500 scenes, it achieves 98.67% success on the Clutter Scene Traversal benchmark. Researcher Chris Paxton calls it very cool work.
More from Embodied
- GeneralistAI expands GEN-1.5 access, betting on a brain for billions of robots — E0M · 2026-10-13
- Agent Buddy: an open-source ESP32 desk device that watches your coding agents — DanWahlin · 2026-10-13
- Microduck Fight: a 25cm servo-duck fighting game where two neural policies duke it out — huggingface · 2026-10-13
- Foxglove founder: billions of autonomous machines are coming, and infra is the bottleneck — Sethwinterroth · 2026-10-13
- Ex-Boston Dynamics strategy chief's startup unveils Hugo, an interactive furry robot for theme parks — CyberRobooo · 2026-10-13
- 7 AI models flew a drone via phone MCP: Claude refused, Codex one-shotted it — Basic-Let6828 · 2026-10-13