ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models
ForesightSafety-VLA:视觉-语言-动作模型的统一诊断安全基准
机构 * Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所类脑认知智能实验室) ; Beijing Key Laboratory of Safe AI and Superalignment(北京市安全人工智能与超级对齐重点实验室) ; Beijing Institute of AI Safety and Governance(北京人工智能安全与治理研究所) ; Gaoling School of AI, Renmin University of China(中国人民大学高瓴人工智能学院) ; University of Chinese Academy of Sciences (UCAS)(中国科学院大学)
专题命中 VLA模型 :VLA(title,title_cn);vision-language-action(title,abstract);action model(title);分类 cs.RO
AI总结 提出ForesightSafety-VLA基准,通过13类安全分类和三维变量控制,诊断VLA模型在物理交互、指令和感知侧的安全风险,并引入累积安全成本和风险暴露时间等过程级指标。
Comments 8 pages, 5 figures, 4 tables. Submitted to IROS 2026