双重应力：安全约束模型预测控制导航的运行时安全监测
Dual Stress: Runtime Safety Monitoring for Safety-Constrained MPC Navigation
- American University of Beirut (AUB)（贝鲁特美国大学）
- New York University Abu Dhabi (NYUAD)（纽约大学阿布扎比分校）
- New York University（纽约大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出基于MPC约束优化的Karush-Kuhn-Tucker乘子的双重应力信号，将其与15个几何检测器对比，发现其漏检碰撞的补充预警能力显著，结合后可提升制动可行碰撞的预警占比。
AI中文摘要：
自主导航的运行时危险监测器通常基于几何量构建：预测的安全距离、碰撞时间及所需减速度。通过显式约束保障安全的模型预测控制器（MPC），在每个控制步骤的计算中会产生一个此类监测器忽略的辅助信息通道：其约束优化的Karush-Kuhn-Tucker乘子，该乘子用于衡量为维持对每个障碍物的安全所付出的边际控制 effort。本文评估这些乘子的水平加权和（即双重应力信号）是否可作为同一状态已支持的几何警告的补充危险监测器。我们将其与15个几何检测器组成的电池（已调整至匹配的虚警预算）进行对比，实验在物理模拟器生成的预注册保留交叉场景中开展。应力警报可有效标记出几何电池整体漏检的碰撞数量，是几何电池漏检量的4.7倍（85次对18次）；结合两者后，在制动仍可行的碰撞中，四分之三可被预警，而仅几何电池的预警占比不足一半。
英文摘要：
Runtime hazard monitors for autonomous naviga- tion are conventionally built from geometric quantities: predicted clearance, time to collision, and required deceleration. A model-predictive controller that enforces safety through explicit con- straints computes, as a by-product of every control step, a second information channel that such monitors ignore: the Karush-Kuhn-Tucker multipliers of its constrained optimization, which measure the marginal control effort spent to maintain safety against each obstacle. This paper evaluates whether a horizon-weighted sum of those multipliers, a dual stress signal, provides a hazard monitor complementary to the geometric warnings the same state already supports. We compare it against a battery of fifteen geometric detectors tuned to a matched false-alarm budget, on preregistered held-out crossing scenarios driven through a physics simulator. The stress alarm actionably flags 4.7 times as many collisions missed by the entire geometric battery as the geometric battery flags in return (85 versus 18); combined, the two channels warn of three quarters of the collisions for which braking remained feasible, against under half for the geometric battery alone.
