发表机构
University of Houston（休斯顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对动态环境中预测误差导致的安全风险，提出CERT-Replan框架，利用校准屏障风险作为重规划信号，通过时域级风险监视选择低风险替代方案，显著降低碰撞率并减少安全过滤器干预。
AI 中文摘要
在动态环境中进行安全导航要求机器人在障碍物预测误差不确定、非平稳且可能引发罕见但安全关键的失败的情况下进行规划。现有的基于控制屏障函数的安全过滤器可以拒绝立即不安全的控制，但它们很少指导当前有限时域规划模式本身何时因预测不确定性演变而变得不安全。我们提出了共形事件触发风险认证重规划（CERT-Replan），这是一个利用校准的屏障风险作为重规划早期预警信号的框架。CERT-Replan在线校准按时间索引的障碍物预测残差，并利用由此产生的不确定性半径来评估动态障碍物的安全裕度。一步安全过滤器保护下一个应用的控制，而时域级风险监视器评估当前MPC滚动过程中预测的屏障违反损失的上尾CVaR。当该风险超过分配的预算时，CERT-Replan拒绝当前的规划模式并选择较低风险的替代方案，例如不同的速度曲线、走廊或同伦类，而不是反复修正相同的标称计划。在一个非平稳基准测试中，与仅使用安全过滤器的基线相比，CERT-Replan实现了83.3%的碰撞减少，相对于简单重规划触发器减少了77.8%，同时将平均安全过滤器干预减少了32.4%。使用Trajectron++，CERT-Replan实现了96%的无碰撞运行。硬件实验和板载运行时分析证明了计算可行性。
英文摘要
Safe navigation in dynamic environments requires robots to plan under obstacle predictions whose errors are uncertain, non-stationary, and can induce rare but safety-critical failures. Existing control-barrier-function safety filters can reject immediately unsafe controls, but they provide little guidance on when the current finite-horizon planning mode itself is becoming unsafe as prediction uncertainty evolves. We propose Conformal Event-Triggered Risk-Certified Replanning (\emph{CERT-Replan}), a framework that uses calibrated barrier risk as an early-warning signal for replanning. CERT-Replan calibrates horizon-indexed obstacle-prediction residuals online and uses the resulting uncertainty radii to evaluate dynamic-obstacle safety margins. A one-step safety filter protects the next applied control, while a horizon-level risk monitor evaluates the upper-tail CVaR of predicted barrier-violation losses along the current MPC rollout. When this risk exceeds an allocated budget, CERT-Replan rejects the current planning mode and selects a lower-risk alternative, such as a different speed profile, corridor, or homotopy class, rather than repeatedly correcting the same nominal plan. In a non-stationary benchmark, CERT-Replan achieves an \(83.3\%\) collision reduction relative to the safety-filter-only baseline \textcolor{black}{and a \(77.8\%\) reduction relative to simple replanning triggers}, while reducing average safety-filter intervention by \(32.4\%\). \textcolor{black}{With Trajectron++, CERT-Replan achieves \(96\%\) collision-free operation. Hardware experiments and onboard runtime profiling demonstrate computational feasibility.}
Commentsfor associated mpeg file, see https://nail-uh.github.io/corl2026.github.io/
