Combining obstacle stepping with fall response to create reactive human-like robots
The Galbot team introduces PASSAGE, a framework that integrates environmental perception, whole-body motion planning, and closed-loop control to enable humanoid robots to autonomously navigate complex environments. Trained on 100 hours of human data across 1,500 scenes, it achieves 98.67% success on the Clutter Scene Traversal benchmark, showcasing advancements in reactive human-like locomotion.
Source: Chris Paxton — X Robotics · Read original article ↗
Article text · Original source · English
Combine stepping over obstacles with reaction to falls and we'll have really good, reactive humanlike robots
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported duration
100 hours
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
Built on 100 hours of human data across 1,500 scenes, it achieves 98.67% success on the Clutter Scene Traversal benchmark.
Open source S4
Perceiving the environment, understanding spatial constraints, and coordinating whole-body motion are essential for humanoid robots to integrate into human society—and remain major challenges in robotics. To address this, the Galbot team introduces PASSAGE, a framework that combines environmental perception, whole-body motion planning, and closed-loop control, enabling humanoid robots to autonomously plan and execute flexible traversal motions based on their surroundings. Built on 100 hours of human data across 1,500 scenes, it achieves 98.67% success on the Clutter Scene Traversal benchmark. #PASSAGE #Galbot #embodiedAI #humanoidrobotView the quoted post on X
Source：Chris Paxton · x.com