CSF: Contextual Safety Filtering for Motion Generators
We introduce contextual safety filtering (CSF), a training-free filter that grounds natural-language safety rules in safe and unsafe reference trajectories produced by the generator.
ProofPaper ↗
Key points
- Text-conditioned motion generators produce trackable whole-body motion, but they have no notion of scene-dependent safety: the same action may target an object or a person.
- For each active rule, safe and unsafe reference trajectories define an affine safety value that a safe reference tracking CBF-QP enforces.
- Across four pretrained generators with different architectures, CSF activates the intended rules in all explicit and scene-triggered unsafe cases and reduces the danger-event rate by up to 90%, while preserving 88-100% of benign motions.
- We demonstrate the complete system on a real-world Unitree G1, where it successfully prevents unsafe motions in a variety of scenarios, including interactions with humans and objects.
Sources (1)
- [1]CSF: Contextual Safety Filtering for Motion GeneratorsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 05:59 PM
We introduce contextual safety filtering (CSF), a training-free filter that grounds natural-language safety rules in safe and unsafe reference trajectories produced by the generator.
Text-conditioned motion generators produce trackable whole-body motion, but they have no notion of scene-dependent safety: the same action may target an object or a person.
Extractive summary: sentences quoted from the sources.