arXiv:2606.25371eess.SYcs.AI2026-06

为自适应控制器设计了可证明恢复时限的证书,避免误触发安全保护。

Conformal Recovery-Deadline Certificates for Runtime Assurance of Adapting Controllers

  • 用分拆式保形方法给出恢复时间的有限样本上界,允许延迟切换
  • 在航天器与倒立摆系统中验证,能准确区分有恢复能力与无能力的控制器
  • 适合需自主恢复但又必须保障安全的实时控制系统,如自动驾驶

运行时保证(RTA)通过在监控条件被违反时从先进控制器切换到经验证的安全控制器来保护关键系统。标准的锁存规则在控制器发散时是正确的,但在具备在线自适应能力的控制器上会引发病态行为。这类控制器在有限的恢复暂态期间本就不安全:它必须激励被控对象以识别故障,才能修正问题;而锁存防护会在该暂态期间误触发,压制本可恢复的控制器。本文提出一种共形恢复时限证书,这是一种分拆式保形、分布无关、有限样本的上界,用于估计自适应控制器的恢复时间,允许延迟降级并提供覆盖率保障,且由硬性临界极限处的经验证监控器作为后备。该证书能区分具备恢复能力与不具备恢复能力的控制器,在保持恢复器自主性的同时捕获发散控制器。其构造将自主性(由统计覆盖率控制)与安全性(由经验证后备控制)分离,体现可靠性不对称设计。我们证明了边际覆盖率(一种已知故障分布偏移下的加权扩展)和组条件蒙德里安覆盖率。在两个无关的Simplex测试平台——六自由度航天器姿态控制器和力矩控制倒立摆上均实现并验证了三种覆盖类型。两者均表现出相同的抑制病理与相同治愈效果,表明该证书是领域通用机制而非单一系统技巧。

原文摘要 · Abstract (English)

Runtime assurance (RTA) protects a safety-critical system by switching from an advanced controller to a verified safe controller when a monitored condition is violated. The standard latching rule, which trips on the first breach of the safe set and then coasts, is correct for a diverging controller but pathological for a capable online-adapting one. Such a controller is unsafe by design during a bounded recovery transient. It must excite the plant to identify the fault before it can correct it, so a latching shield trips on that transient and suppresses a controller that would have recovered. We introduce the conformal recovery-deadline certificate, a split-conformal, distribution-free, finite-sample upper bound on the adapting controller's recovery time that licenses delayed fallback with a coverage guarantee, backstopped by a verified monitor at a hard critical limit. The certified deadline discriminates capable from incapable controllers, keeping the recoverer autonomous while catching the diverger. The construction separates autonomy, governed by statistical coverage, from safety, governed by the verified backstop, as an instance of reliability-asymmetric design. We prove marginal coverage, a weighted extension that restores coverage under a known fault-distribution shift, and group-conditional Mondrian coverage. We demonstrate all three on two unrelated Simplex testbeds: a 6-DOF spacecraft attitude controller and a torque-controlled inverted pendulum. Both show the same suppression pathology and the same cure, making the certificate a domain-general mechanism rather than a single-system trick.

控制安全自适应控制运行时保证保形预测

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。