3 papers
cs.RO2026
SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models
Jialiang Fan, Weizhe Xu, Oleg Sokolsky +3
Vision-language-action (VLA) benchmarks measure whether a policy completes a requested manipulation task, but binary success can hide safety violations along the trajectory: a poli…
cs.RO2026
SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systems
Jialiang Fan, Weizhe Xu, Mengyu Liu +3
Safety-critical task planning in robotic systems remains challenging: classical planners suffer from poor scalability, Reinforcement Learning (RL)-based methods generalize poorly,…
cs.LG2026
Demonstration-Guided Observation Attacks on Black-Box Safe Reinforcement Learning Controllers for Robotic Systems
Jialiang Fan, Shixiong Jiang, Mengyu Liu +1
Safe reinforcement learning (Safe RL) learns robotic controllers that optimize task rewards under safety constraints, yet observation perturbations can induce safety violations. Ex…