[
    {
        "id": "osp-16320",
        "type": "article-journal",
        "title": "CSF: Contextual Safety Filtering for Motion Generators",
        "author": [
            {
                "family": "Yang",
                "given": "Lizhi"
            },
            {
                "family": "Hou",
                "given": "Yiling"
            },
            {
                "family": "Tang",
                "given": "Yao"
            },
            {
                "family": "Li",
                "given": "Junheng"
            },
            {
                "family": "Weng",
                "given": "Daniel"
            },
            {
                "family": "Werner",
                "given": "Blake"
            },
            {
                "family": "Ames",
                "given": "Aaron D."
            }
        ],
        "URL": "https://omanscience.com/en/articles/csf-contextual-safety-filtering-for-motion-generators",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]