SOURCE-LINKED INTELLIGENCE

SafeStage: Evaluating Safety Before, During, and After Vision-Language-Conditioned Robot Manipulation

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Vision-language-conditioned robot policies integrate perception, language understanding, and control for general-purpose manipulation. However, existing evaluations often focus on task success, isolated physical constraints, semantic refusal, or realized physical damage, providing limited insight into where safety fails during closed-loop manipulation. We introduce SafeStage, a lifecycle-structured benchmark for evaluating manipulation safety before, during, and after task execution. SafeStage contains 97 purpose-built risk scenarios organized into three stages. Initial-State Hazards captures

Read original source ↗ Open in workspace

recordType

paper

region

Global