arXiv Open Access 2025

Learning-based model predictive control with moving horizon state estimation for autonomous racing

Yassine Kebbati Andreas Rauh Naima Ait-Oufroukh Dalil Ichalal Vincent Vigneron

Lihat Sumber

Abstrak

This paper addresses autonomous racing by introducing a real-time nonlinear model predictive controller (NMPC) coupled with a moving horizon estimator (MHE). The racing problem is solved by an NMPC-based off-line trajectory planner that computes the best trajectory while considering the physical limits of the vehicle and circuit constraints. The developed controller is further enhanced with a learning extension based on Gaussian process regression that improves model predictions. The proposed control, estimation, and planning schemes are evaluated on two different race tracks. Code can be found here: https://github.com/yassinekebbati/GP_Learning-based_MPC_with_MHE

Topik & Kata Kunci

math.OC

Penulis (5)

Yassine Kebbati

Andreas Rauh

Naima Ait-Oufroukh

Dalil Ichalal

Vincent Vigneron

Format Sitasi

APA MLA BibTeX

Kebbati, Y., Rauh, A., Ait-Oufroukh, N., Ichalal, D., Vigneron, V. (2025). Learning-based model predictive control with moving horizon state estimation for autonomous racing. https://arxiv.org/abs/2510.05366

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓