军事知识服务平台
自动驾驶车辆功能韧性研究:横向控制与定位案例
Functionality Resilience of Autonomous Vehicles:Case Studies of Lateral Control and Positioning
摘要 针对自动驾驶车辆在复杂动态环境中因内部子系统耦合、外部环境变化和多交通参与者交互等不确定性而面临关键功能退化、运行安全难以保障的问题,提出以功能为中心的韧性框架及其表征、量化和增强方法.将功能韧性形式化为由不利事件 A、功能 F 和不确定性U 组成的三元组(A,F,U);基于性能曲线Q(t)的几何特性,从全局和局部2个维度评估功能韧性,全局维度以韧性损失 RL 量化不利事件作用期间的功能损失,局部维度以性能曲线的局部几何特征刻画系统的吸收与恢复特性;归纳出以降低认知不确定性、优化功能性水平和引入性能反馈为核心的功能韧性增强原则.车辆横向控制案例针对纯跟踪控制器在急弯工况下的功能退化问题,设计融合实时车速与路径曲率的自适应预瞄距离计算方法,并引入横向误差的比例-积分-滑动平均微分反馈构成闭环校正;实车试验与仿真测试表明,所提策略在2个连续急弯处的韧性损失 RL 分别由63.93降至49.50、由61.50降至45.58,性能下降 L1 的绝对值分别由6.73减小至5.15、由5.83减小至3.94,恢复速度 k2 分别由0.530提升至0.683、由0.565提升至0.864.车辆定位案例构建位置"预测-校正"网络,以全球导航卫星系统(global navigation satellite system,GNSS)定位误差为监督信息训练校正网络,提升GNSS信号中断时组合导航系统的定位功能韧性;3处GNSS信号中断场景下,预测-校正策略的定位功能韧性均优于航迹推算与"p-Dp"架构,第2处中断场景的韧性损失 RL 由航迹推算的420.13降至141.41.结果表明,(A,F,U)框架能够有效表征、量化和增强自动驾驶车辆的功能韧性,降低认知不确定性与优化功能性水平是提升功能韧性的有效途径.
Abstract:
Autonomous vehicles(AVs)face functionality degradation and safety risks in complex dynamic environ-ments.Such risks arise from uncertainties,including the coupling of internal subsystems,changes in the external en-vironment,and interactions among multiple traffic participants.To address this problem,a functionality-centered re-silience framework together with its characterization,quantification,and enhancement methods is proposed.Func-tionality resilience is formalized as a triplet(A,F,U)consisting of an adverse event(A),a functionality(F),and uncertainty(U).Based on the geometric characteristics of the performance curve Q(t),functionality resilience is evaluated from both global and local dimensions.The global resilience loss RL quantifies the functionality loss during adverse events,while the local geometric features of the performance curve characterize the absorption and recovery behavior of the system.Resilience enhancement principles centered on reducing epistemic uncertainty,op-timizing the functionality level,and introducing performance feedback are summarized.In the vehicle lateral con-trol case,the functionality degradation of a pure pursuit controller in sharp-curve scenarios is addressed.An adap-tive look-ahead distance method that fuses real-time vehicle speed and path curvature is designed,and a closed-loop correction consisting of proportional-integral-moving-average-derivative feedback of the lateral error is introduced.Vehicle tests and simulation experiments show that,for the proposed strategy,the resilience loss RL at two succes-sive sharp curves decreases from 63.93 to 49.50 and from 61.50 to 45.58.The absolute value of the performance drop L1 decreases from 6.73 to 5.15 and from 5.83 to 3.94.The recovery speed k2 increases from 0.530 to 0.683 and from 0.565 to 0.864.In the vehicle positioning case,a position"prediction-correction"network is developed.Global navigation satellite system(GNSS)positioning errors are used as supervisory information to train the correc-tion network,thereby improving the positioning functionality resilience of the integrated navigation system during GNSS outages.Under three GNSS outage scenarios,the positioning functionality resilience of the prediction-correc-tion strategy is superior to that of dead reckoning and the"p-Dp"architecture.The resilience loss RL at the sec-ond outage decreases from 420.13 for dead reckoning to 141.41.The results indicate that the(A,F,U)frame-work can effectively characterize,quantify,and enhance the functionality resilience of AVs.Reducing epistemic un-certainty and optimizing the functionality level are effective ways to improve functionality resilience.
刊 名 交通信息与安全 ISTICPKU
年,卷(期): 2026, 44(4)
分类号: U495
机标分类号: TN967.1 P228.4 U491
在线出版日期: 2026年11月6日
基金项目: 52372426:国家自然科学基金2025yjrc0012:安徽理工大学高层次引进人才科研启动基金JTX202604:安徽省交通信息与安全重点实验室开放课题,