EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning-Augmented MPC for Autonomous Vehicle Path Tracking via Ensemble Residual Dynamics Learning

Lu Xiong, Ming Liu, Zhihao Xie, Bo Leng, Yuanjian Zhang

Sensors · 05.01.2026 · 26 (1) · 340

DOI: 10.3390/s26010340 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 05.01.2026. Verfasst von Lu Xiong und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Automotive Studies, Tongji University, 4800 Cao'an Highway, Jiading District, Shanghai 201804, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, the Fundamental Research Funds for the Central Universities, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate vehicle dynamics modeling is essential for path tracking control, especially under sharp-curvature or rapidly changing conditions where nonlinear and time-varying behaviors introduce significant discrepancies between the nominal model and real vehicle responses, ultimately degrading the performance of traditional Model Predictive Control (MPC). To address this challenge, this paper proposes a learning-augmented MPC framework that incorporates an ensemble learning-based Data-Driven Dynamics Refinement (DDR) Model to enhance predictive accuracy and control robustness. The DDR Model complements nominal vehicle dynamics by capturing complex behaviors that are difficult to represent analytically. An ensemble of independently trained neural predictors is employed to improve generalization performance and provide stable refinement across diverse driving conditions. Furthermore, a feature-driven activation mechanism is designed to selectively apply refinement only when pronounced nonlinear behaviors arise, thereby reducing unnecessary computational burden. High-fidelity simulation studies validate the effectiveness of the proposed method. In single- and double-lane-change scenarios, the refined dynamics reduce maximum lateral deviation by approximately 6 cm and 4 cm, and decrease the maximum vehicle heading error by 0.02 rad and 0.015 rad, respectively, demonstrating significant improvements in tracking accuracy and robustness.

Schlagwörter

Stichwörter der Autor:innen

autonomous vehicleensemble learningmodel predictive controlpath tracking

Autor:innen und Institutionen

  • School of Automotive Studies, Tongji University, 4800 Cao'an Highway, Jiading District, Shanghai 201804, China.

Förderung

  • National Natural Science Foundation of China
  • the Fundamental Research Funds for the Central Universities
  • Fundamental Research Funds for the Central Universities
  • United Automotive Electronic Systems Co., Ltd.
  • SAIC Motor Corporation Limited

Zitieren

APA

Xiong, L., Liu, M., Xie, Z., Leng, B., & Zhang, Y. (2026). Learning-Augmented MPC for Autonomous Vehicle Path Tracking via Ensemble Residual Dynamics Learning. Sensors, 26(1), 340. https://doi.org/10.3390/s26010340

Vancouver

Xiong L, Liu M, Xie Z, Leng B, Zhang Y. Learning-Augmented MPC for Autonomous Vehicle Path Tracking via Ensemble Residual Dynamics Learning. Sensors. 2026;26(1):340. doi:10.3390/s26010340

BibTeX
@article{Xiong2026,
  author = {Xiong, Lu and Liu, Ming and Xie, Zhihao and Leng, Bo and Zhang, Yuanjian},
  title = {Learning-Augmented MPC for Autonomous Vehicle Path Tracking via Ensemble Residual Dynamics Learning},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {1},
  pages = {340},
  doi = {10.3390/s26010340}
}
Kostenlos starten →