Physics-Driven Hybrid Framework for Vehicle State Estimation Using Residual Learning and Adaptive UKF
Applied Sciences · 26.04.2026 · 16 (9) · 4230
DOI: 10.3390/app16094230 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 26.04.2026. Verfasst von Peng Zhou und 5 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Education Department of Heilongjiang Province.
Abstract (Originalsprache)
Accurate estimation of vehicle sideslip angle and lateral velocity is essential for the stability control of Advanced Driver Assistance Systems (ADASs). Traditional physics-based observers often exhibit dynamic response distortions under stability-limit conditions due to unmodeled tire relaxation effects, while data-driven methods lack physical interpretability. This paper proposes a Physics-Driven Hybrid Estimation Framework (PD-HEF) to bridge this gap. First, a nonlinear nominal model is constructed as a physical skeleton, and dynamic residual equations are derived to define learning targets. Second, a Spatio-Temporal Feature Coupled Residual Network is designed to capture time-domain phase lag and compensate for spatial nonlinear deviations. Furthermore, a hybrid unscented Kalman filter is developed to inject predicted residuals into the sigma-point evolution. A Dual-Layer Adaptive Mechanism is also introduced to regulate trust weights based on innovation statistics. Joint simulations demonstrate that the proposed framework reduces the root mean square error by over 60% compared to traditional observers while satisfying real-time constraints.
Förderung
- Education Department of Heilongjiang Province
Zitieren
APA
Zhou, P., Zhou, Y., Sun, X., Li, Z., Liu, M., & Han, P. (2026). Physics-Driven Hybrid Framework for Vehicle State Estimation Using Residual Learning and Adaptive UKF. Applied Sciences, 16(9), 4230. https://doi.org/10.3390/app16094230
Vancouver
Zhou P, Zhou Y, Sun X, Li Z, Liu M, Han P. Physics-Driven Hybrid Framework for Vehicle State Estimation Using Residual Learning and Adaptive UKF. Applied Sciences. 2026;16(9):4230. doi:10.3390/app16094230
BibTeX
@article{Zhou2026,
author = {Zhou, Peng and Zhou, Yanbin and Sun, Xi and Li, Ziming and Liu, Mingpu and Han, Ping},
title = {Physics-Driven Hybrid Framework for Vehicle State Estimation Using Residual Learning and Adaptive UKF},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {9},
pages = {4230},
doi = {10.3390/app16094230}
}
EUVIMED