Article

Reasoning driving VLAs have a perception-action binding gap: they can perceive danger but do not brake

The paper points out that reasoning-augmented vision-language-action (VLA) driving models can perceive and reason about safety-critical hazards, yet cannot translate that evidence into safe actions, which the authors call a perception-action binding gap. Using matched simulated counterfactuals and logged replay, the study finds that in-path hazards are indeed encoded in the visual representation, but longitudinal planning is dominated mainly by ego-speed history and responds only weakly to hazard distance and the model's own reasoning trace.

Part of the event: Driving VLA can perceive danger but fails to brake, study proposes training-free fix

This page provides a summary and source link only.