arXiv：cs.LG· Lizhi Yang, Yiling Hou, Yao Tang, Junheng Li, Daniel Weng, Blake Werner, Aaron D. Ames·· 3 小时前
CSF：面向动作生成器的上下文安全过滤
CSF: Contextual Safety Filtering for Motion Generators
AI 导读
研究提出上下文安全过滤（CSF），一种无需训练、将自然语言安全规则锚定到生成器所产安全/不安全参考轨迹的过滤器，通过安全参考跟踪 CBF-QP 执行仿射安全值。
正文
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.
| Comments: | 8 pages, 6 figures, website at this https URL |
| Subjects: | Robotics (cs.RO); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.12467 [cs.RO] |
| (or arXiv:2610.12467v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.12467 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lizhi Yang [view email]
[v1]
Thu, 8 Oct 2026 17:59:50 UTC (14,205 KB)
来源：arXiv：cs.LG · arxiv.org