Localization failure is a significant challenge faced by urban autonomous driving applications. To ensure vehicle safety in the event of localization failure, a functional degradation strategy is proposed from the perspective of the autonomous driving system. The strategy introduces a hierarchical four-stage degradation framework, enabling dynamic switching between localization-based path tracking, dead reckoning (DR)-based tracking, lane-keeping control, and manual takeover according to localization status, DR duration and lane lines quality. Specific degradation strategies are designed for typical urban scenarios—including straight and curved roads, intersections, and on-ramp scenarios. Hardware-in-the-loop (HIL) experiments demonstrate that the functional degradation strategy effectively addresses localization failures in real urban scenarios.
BurtonSHabliILawtonT, et al. Mind the gaps: assuring the safety of autonomous systems from an engineering, ethical, and legal perspective. Artif Intell2020; 279: 103201.
2.
WangYWangJCaoL, et al. A comprehensive failure analysis method for a fusion localization system: a case study on vector high-definition map and vision matching. IEEE Veh Technol Mag2025; 20(2): 123–136.
3.
ISO/PAS 21448:2019. Safety of the intended functionality.
4.
QuddusMAOchiengWYNolandRB.Current map-matching algorithms for transport applications: state-of-the-art and future research directions. Transp Res Part C Emerg Technol2007; 15(5): 312–328.
5.
ChiangKWTsaiGJChuHJ, et al. Performance enhancement of INS/GNSS/refreshed-SLAM integration for acceptable lane-level navigation accuracy. IEEE Trans Veh Technol2020; 69(3): 2463–2476.
6.
CaiHHuZHuangG, et al. Integration of GPS, monocular vision, and high-definition (HD) map for accurate vehicle localization. Sensors2018; 18(10): 3270.
7.
RoessleBGruenwedelS. Vehicle localization in six degrees of freedom for augmented reality. In: 2020 IEEE intelligent vehicles symposium (IV), Las Vegas, NV, USA, 19 October–13 November 2020, pp.1853–1858. New York: IEEE.
8.
XiaoZYangDWenT, et al. Monocular localization with vector HD map (MLVHM): a low-cost method for commercial IVs. Sensors2020; 20(7): 1870.
9.
WenTXiaoZWijayaB, et al. High precision vehicle localization based on tightly-coupled visual odometry and vector HD map. In: 2020 IEEE intelligent vehicles symposium (IV), Las Vegas, NV, USA, 19 October–13 November 2020, pp.672–679. New York: IEEE.
10.
ZhangZZhaoJHuangC, et al. Learning visual semantic map-matching for loosely multi-sensor fusion localization of autonomous vehicles. IEEE Trans Intell Veh2022; 8(1): 358–367.
11.
CuiDXueJDuS, et al. Real-time global localization of intelligent road vehicles in lane-level via lane marking detection and shape registration. In: 2014IEEE/RSJ international conference on intelligent robots and systems, Chicago, IL, USA, 14–18 September 2014, pp.4958–4964. New York: IEEE.
12.
RohdeJJatzkowskiIMielenzH, et al. Vehicle pose estimation in cluttered urban environments using multilayer adaptive Monte Carlo localization. In: Proceedings of the international conference on information fusion, Heidelberg, Germany, 5–8 July 2016, pp.1774–1779. New York: IEEE.
13.
HuangZQiaoSHanN, et al. Survey on vehicle map matching techniques. CAAI Trans Intell Technol2021; 6(1): 55–71.
14.
WangYLuoYLuJ, et al. An underground parking lot mask for the long-term visual localization of intelligent vehicles. IEEE Intell Transp Syst Mag2022; 15(4): 22–34.
15.
ReidTGRHoutsSECammarataR, et al. Localization requirements for autonomous vehicles. SAE Int J Connected Autom Veh2019; 2(3): 173–190.
16.
ShenYXiaCJianZ, et al. An integrated localization system with fault detection, isolation and recovery for autonomous vehicles. In: 2021 IEEE international intelligent transportation systems conference (ITSC), Indianapolis, IN, USA, 19–22 September 2021, pp.84–91. New York: IEEE.
17.
MoriDSugiuraHHattoriY.Adaptive sensor fault detection and isolation using unscented Kalman filter for vehicle positioning. In: 2019 IEEE intelligent transportation systems conference (ITSC), Auckland, New Zealand, 27–30 October 2019, pp.1298–1304. New York: IEEE.
18.
SeoKLeeJLeeJ, et al. Fail-safe process of vehicle localization for reliability improvement of LV3 autonomous driving. Int J Automot Technol2021; 22: 529–535.
19.
CaoLHeYLuoY, et al. Layered SOTIF analysis and 3σ-criterion-based adaptive EKF for LiDAR-based multi-sensor fusion localization system on foggy days. Remote Sens2023; 15(12): 3047.
20.
CaoLLuoYWangY, et al. Degradation state detection and local map optimization for enhancing the SOTIF of map-matching-based fusion localization system. Meas Sci Technol2023; 35(3): 036303.
21.
VianaKZubizarretaADiezM.A reconfigurable framework for vehicle localization in urban areas. Sensors2022; 22(7): 2595.
22.
HasanSGirsSUhlemannE.Characterization of transient communication outages into states to enable autonomous fault tolerance in vehicle platooning. IEEE Open J Intell Transp Syst2023; 4: 101–129.
23.
HasanS.Fail-operational and fail-safe vehicle platooning in the presence of transient communication errors. Report, Mälardalen University, Sweden, March2022.
24.
RenLXiZ.Bias-learning-based model predictive controller design for reliable path tracking of autonomous vehicles under model and environmental uncertainty. J Mech Des2022; 144(9): 091706.
25.
RahmanMHGulzarMMHaqueTS, et al. Trajectory planning and tracking control in autonomous driving system: leveraging machine learning and advanced control algorithms. Eng Sci Technol Int J2025; 64: 101950.
