面向配对系统故障发现的覆盖率感知主动评估
Coverage Aware Active Evaluation for Failure Discovery with Paired Systems
浏览论文内容
中文总结 AI 辅助
该研究针对自主系统故障发现难题，提出结合代理评估与残差建模、支持感知互信息目标的自适应方法，在三类任务中发现的故障数是基线的两倍。
中文摘要 AI 辅助
自主系统可能以罕见且多样的方式发生故障，在有限的测试预算下，真实场景中的故障发现工作十分困难。虽然可以广泛采样模拟器、低保真系统或相关策略等成本较低的代理来查找故障，但由于现实差距和系统间差距，代理故障通常无法迁移到真实系统中。因此，关键挑战在于有效利用代理系统信息，以准确预测目标系统的严重故障。我们提出一种自适应故障发现方法，将代理评估与有限的目标系统结果相结合，用于指导目标系统测试的场景选择。该方法通过使用受控制变量启发的残差建模校正代理故障信号，学习目标风险的局部预测器；为了找到既可能发生又多样的故障，我们将该预测器与支持感知互信息目标相结合，该目标倾向于现实、得到良好支持的区域，同时扩大故障模式的覆盖率。在自动驾驶、操纵和四足机器人速度跟踪任务中，我们的方法发现的故障数量是随机采样和主动学习基线的两倍，包括竞争方法遗漏的严重且多样的故障。
英文摘要
Autonomous systems can fail in rare and heterogeneous ways, making real-world failure discovery difficult under limited testing budgets. Although cheaper proxies such as simulators, lower-fidelity systems, or related policies can be sampled extensively to find failures, proxy failures often do not transfer to the real world due to sim-to-real and system-to-system gaps. The key challenge is therefore to effectively leverage proxy system information for accurate prediction of severe target system failures. We propose an adaptive failure discovery method that combines proxy evaluations with limited target system results to guide scenario selection for target system testing. Our method learns a local predictor of target risk by correcting proxy failure signals using control-variate-inspired residual modeling. To find failures that are both likely and diverse, we combine this predictor with a support-aware mutual-information objective that favors realistic, well-supported regions while expanding coverage across failure modes. Across autonomous driving, manipulation, and quadruped velocity-tracking tasks, our method discovers up to 2$\times$ as many failures as random sampling and active-learning baselines, including severe and diverse failures missed by competing methods.
发表机构
- Laboratory of Information & Decision Systems (LIDS), MIT（麻省理工学院信息与决策系统实验室（LIDS））
- NVIDIA Research（英伟达研究院）
机构由 AI 辅助整理，请以论文原文为准。
