CSF: Contextual Safety Filtering for Motion Generators

Lizhi Yang, Yiling Hou, Yao Tang, Junheng Li, Daniel Weng, Blake Werner, Aaron D. Ames · N/A · 2026

Summary

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.

Abstract Summary

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.

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.
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.

Method

Consider a text-conditioned generator that samples a motion for prompt $c$ in a scene with semantically rich entities; its parameters remain frozen during filtering. We declare unsafe behaviors in natural language and, at inference time, correct only motions that violate a scene-active rule while passing all other motions through without retraining or auxiliary models.

Experiments

We apply CSF without retraining to four pretrained generators through the output-estimate interface of Definition 1 : Kimodo-G1 [ 1 ] (DDIM diffusion), ECHO [ 2 ] (diffusion with DPM-Solver sampling [ 49 ] ), MotionHiFlow [ 3 ] (flow matching in a VAE latent), and ARDY [ 4 ] (windowed autoregressive generation over hybrid tokens).

Table I lists each adapter’s output space, tracking strength $\gamma$, and root-channel handling.

Experiments — CSF: Contextual Safety Filtering for Motion Generators — Fig. 2 : During generation, rules and scene context select the constraints enforced by a safe-reference tracking CBF-QP inside the frozen generator. During execution, a context change preserves the executed motion and redirects the remaining reference before a whole-body controller tracks it on Unitree G1.

Sources and Demonstrations

Figures are reproduced from Yang et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.