safety security
The Same Motion Became Unsafe When a Person Entered the Scene
Contextual safety filtering grounds language rules in paired safe and unsafe trajectories without retraining the motion generator.
Summary
Contextual safety filtering grounds language rules in paired safe and unsafe trajectories without retraining the motion generator.
A text-conditioned motion generator may produce the same movement near an object or near a person without understanding why the second context changes its risk. Contextual Safety Filtering turns active natural-language rules into safe and unsafe reference trajectories, then enforces an affine safety value through a control-barrier optimization layer. Across four pretrained generators, the filter activated the intended rule in every explicit and scene-triggered unsafe case, cut danger events by as much as 90%, and preserved 88% to 100% of benign motions. A Unitree G1 demonstration extended the test to real hardware. The findings remain limited to the tested rules and scenarios.
Why it matters
Contextual safety filtering grounds language rules in paired safe and unsafe trajectories without retraining the motion generator.
Limits and context
- The findings remain limited to the tested rules and scenarios.
Key claims
Contextual safety filtering grounds language rules in paired safe and unsafe trajectories without retraining the motion generator.
Qualification: The findings remain limited to the tested rules and scenarios.
Evidence: source-2026-10-10-005
Sources
- arXiv preprint 2610.12467, original v1arXiv / submitting research authors · primary research
Corrections
No corrections have been recorded for this story.