提出运行时框架，提前识别自动驾驶任务失效指令
Mission-Level Runtime Assurance Framework for Autonomous Driving
- 在执行前检测任务级故障，如漏过检查点或进入禁入区
- 实验显示可成功拒绝不可行指令，任务成功率显著提升
- 适合关注自动驾驶长期安全的开发者与研究者
本文研究高阶驾驶指令失效时自动驾驶系统的运行时安全性。不同于传统仅关注车辆即时安全的方法，该框架在指令执行前同时评估驾驶安全性和任务完成可行性。通过扩展highway-env，引入跳过必经检查点、进入受限区域及生成无法完成任务的路径等任务级故障场景。设计运行时监控系统，在执行前检测并拒绝不安全或任务不可行的指令。对比采用公开Simplex-Drive框架的改进版Simplex-Drive基线（含学习驱动控制、安全降级控制和控制器切换），实验表明平台级运行时安全无法检测任务级规划错误，而本文框架能有效拒绝对任务不可行的指令，在随机故障条件下提升任务成功率。
原文摘要 · Abstract (English)
This paper studies runtime safety for autonomous driving when high-level driving commands become faulty or unreliable. Unlike conventional runtime-safety approaches that mainly focus on immediate vehicle safety, the proposed framework evaluates both driving safety and whether the vehicle can still successfully complete its mission before a command is executed. The framework extends highway-env with mission-level fault scenarios such as skipping required checkpoints, entering restricted areas, and generating future routes that can no longer complete the mission successfully. A runtime monitoring system is introduced to detect and reject unsafe or mission-infeasible commands before execution. For comparison, an adapted Simplex-Drive runtime-safety baseline with learning-based driving control, safety fallback control, and runtime controller switching is implemented using the public Simplex-Drive framework. Experimental results show that platform-level runtime safety alone cannot detect mission-level planning faults, while the proposed framework successfully rejects mission-infeasible commands and improves mission success under randomized fault conditions.
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。