Skip to main content

Accidental harm

Embodied AI: Emerging Risks and Opportunities for Policy Action

Perlo et al. (2025)

Sub-category
Risk Domain

AI systems that fail to perform reliably or effectively under varying conditions, exposing them to errors and failures that can have significant consequences, especially in critical applications or areas that require moral reasoning.

"Automation in sectors ranging from manufacturing to healthcare has and will increasingly put humans into close contact with EAI systems [7]. This interaction increases the risk of accidental physical harm. Though accidental harm has been a longstanding issue in industrial robotics, increased AI capabilities could exacerbate this risk; several recent reports document an increase in industrial injuries following the introduction of AI-controlled robots [66–68]."(p. 4)

Supporting Evidence (1)

1.
"AI’s potential to cause accidental, physical harm could be caused by misspecified goals, lack of semantic understanding, misaligned behavior, physical hardware malfunctions, or other unanticipated behaviors [44, 69, 70]. For example, a humanoid EAI might not correctly reason that placing a full glass of milk on a tilted table is perilous and likely to lead to a dangerous broken glass [71], or a swarm of EAI systems might get caught in a physical logjam and run over humans by mistake while trying to unstick themselves [72]."(p. 4)

Other risks from Perlo et al. (2025) (12)