EAST：通过数字孪生中的系统性故障注入进行具身人工智能安全测试
EAST: Embodied AI Safety Testing via Systematic Fault Injection in Digital Twins
Yuhao Tian · Tao Li · Ling Zhou · Dave Towey · Zhaoxin Fan · Wenjun Wu · et al.
中文摘要
具身人工智能(embodied AI)仅以任务成功率衡量安全性并不充分，因为机器人可能在完成任务时违反安全要求。现有评估偏重性能与鲁棒性，却缺少从已记录安全风险到可执行、可验证测试的系统路径。EAST(Embodied AI Safety Testing)是一种数字孪生(digital twin)框架，将文献依据的安全证据转化为涵盖感知、指令、环境、动作和时序的故障注入测试。EAST结合专家审查的安全故障分类体系与8种可执行算子，并设置适用性和有效性约束。其三阶段工作流生成测试规范、在仿真执行中验证故障是否实现，并依据模拟器状态证据独立评估安全挑战、违规、任务结果和行为特征。框架保留执行轨迹及可重放记录，支持跨实验的问题归因与复现。在同等预算下，研究在6项RoboTwin操作任务、ACT与RDT两种策略架构上，将EAST与其他测试策略进行了比较。5轮比较活动覆盖全部74个可用任务—策略—算子组合，其中63个获得有效证据，安全挑战暴露率接近Random-Legal和Rule-Based。另有82次有效EAST执行在违反安全要求的情况下完成任务，揭示了成功导向评估所掩盖的风险。结果表明，安全测试应超越任务完成指标，并做到系统化、有效性约束与可复现。
关键要点
- 01现有具身AI评估缺少从安全风险到可验证测试的系统路径
- 02EAST在数字孪生中覆盖感知、指令、环境、动作与时序故障注入
- 03三阶段流程生成规范、验证故障实现并独立评估安全结果
- 045轮活动覆盖74个可用组合，其中63个获得有效测试证据
- 0582次有效执行虽违反安全要求仍完成任务，暴露成功导向评估盲点
解读
尚无解读。
原始英文摘要
arXiv:2610.34358v1 Announce Type: cross Abstract: Task success is not a sufficient measure of safety for embodied artificial intelligence (AI), because robots may complete objectives while violating safety requirements. Existing evaluations often emphasize performance and robustness, but lack a systematic route from documented safety hazards to executable, verifiable tests. We present EAST (Embodied AI Safety Testing), a digital-twin framework that converts literature-grounded safety evidence into fault-injection tests across perception, instructions, environments, actions, and timing. EAST combines an expert-reviewed safety-fault taxonomy and eight executable operators with applicability and validity constraints. Its three-stage workflow generates test specifications, verifies fault realization during simulated execution, and independently assesses safety challenges, violations, task outcomes, and behavioral signatures using simulator-state evidence. The framework preserves execution traces and replayable records, supporting attribution and reproducibility across experiments. We evaluate EAST on six RoboTwin manipulation tasks and two policy architectures, ACT and RDT, against alternative testing strategies under matched budgets. Across five comparative campaigns, EAST targets all 74 admissible task-policy-operator combinations and obtains valid evidence for 63, while achieving safety-challenge exposure rates close to Random-Legal and Rule-Based. Moreover, 82 valid EAST executions complete their tasks despite safety violations, revealing risks concealed by success-oriented evaluation. These findings support systematic, validity-aware, reproducible safety testing beyond task-completion metrics.