Can AI Perceive Physical Danger and Intervene?
This addresses safety challenges for AI systems interacting in the physical world, such as robots or assistive agents, to prevent physical harm, though it is incremental in building on existing foundation models.
The paper tackles the problem of assessing and improving AI's ability to perceive physical danger and intervene in embodied interactions, by developing a scalable safety benchmark based on real-world injury narratives and analyzing foundation models, resulting in state-of-the-art performance in constraint satisfaction evaluations.
When AI interacts with the physical world -- as a robot or an assistive agent -- new safety challenges emerge beyond those of purely ``digital AI". In such interactions, the potential for physical harm is direct and immediate. How well do state-of-the-art foundation models understand common-sense facts about physical safety, e.g. that a box may be too heavy to lift, or that a hot cup of coffee should not be handed to a child? In this paper, our contributions are three-fold: first, we develop a highly scalable approach to continuous physical safety benchmarking of Embodied AI systems, grounded in real-world injury narratives and operational safety constraints. To probe multi-modal safety understanding, we turn these narratives and constraints into photorealistic images and videos capturing transitions from safe to unsafe states, using advanced generative models. Secondly, we comprehensively analyze the ability of major foundation models to perceive risks, reason about safety, and trigger interventions; this yields multi-faceted insights into their deployment readiness for safety-critical agentic applications. Finally, we develop a post-training paradigm to teach models to explicitly reason about embodiment-specific safety constraints provided through system instructions. The resulting models generate thinking traces that make safety reasoning interpretable and transparent, achieving state of the art performance in constraint satisfaction evaluations. The benchmark will be released at https://asimov-benchmark.github.io/v2