Abstract
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. Existing safeguards either inspect the prompt, require labeled motion data, or enforce geometric constraints; therefore, they do not directly account for how scene context changes a motion's meaning. 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. 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.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Yang, L., Hou, Y., Tang, Y., Li, J., Weng, D., Werner, B., & Ames, A. D. (2026). CSF: Contextual Safety Filtering for Motion Generators. https://omanscience.com/en/articles/csf-contextual-safety-filtering-for-motion-generators
MLA 9
Yang, Lizhi, et al. "CSF: Contextual Safety Filtering for Motion Generators." https://omanscience.com/en/articles/csf-contextual-safety-filtering-for-motion-generators.
Chicago (author–date)
Yang, Lizhi, Yiling Hou, Yao Tang, Junheng Li, Daniel Weng, Blake Werner, and Aaron D. Ames. 2026. "CSF: Contextual Safety Filtering for Motion Generators." https://omanscience.com/en/articles/csf-contextual-safety-filtering-for-motion-generators.
Harvard
Yang, L., Hou, Y., Tang, Y., Li, J., Weng, D., Werner, B. and Ames, A. D. (2026) 'CSF: Contextual Safety Filtering for Motion Generators', Available at: https://omanscience.com/en/articles/csf-contextual-safety-filtering-for-motion-generators.
Vancouver
Yang L, Hou Y, Tang Y, Li J, Weng D, Werner B, et al. CSF: Contextual Safety Filtering for Motion Generators. https://omanscience.com/en/articles/csf-contextual-safety-filtering-for-motion-generators
IEEE
L. Yang, Y. Hou, Y. Tang, J. Li, D. Weng, B. Werner, and A. D. Ames, "CSF: Contextual Safety Filtering for Motion Generators," https://omanscience.com/en/articles/csf-contextual-safety-filtering-for-motion-generators.