Automatic Tuning of MPC for Autonomous Vehicle using Bayesian Optimization

Autor:	Strozecki, Wojciech, Oufroukh, Naima Ait, Kebbati, Yassine, Ichalal, Dalil, Mammar, Said
Přispěvatelé:	Informatique, BioInformatique, Systèmes Complexes (IBISC), Université d'Évry-Val-d'Essonne (UEVE)-Université Paris-Saclay
Rok vydání:	2021
Předmět:	Lateral control Autonomous driving Model predictive control Bayesian optimization [SPI.AUTO]Engineering Sciences [physics]/Automatic
Zdroj:	18th IEEE International Conference on Networking, Sensing and Control (ICNSC 2021) 18th IEEE International Conference on Networking, Sensing and Control (ICNSC 2021), Dec 2021, Xiamen, China. pp.1-6, ⟨10.1109/ICNSC52481.2021.9702240⟩
DOI:	10.1109/icnsc52481.2021.9702240
Popis:	International audience; The purpose of this paper is to develop an automated tuning procedure for autonomous vehicle lateral control. A low effort and high level method of automated Model Predictive Control tuning based on Bayesian Optimization is proposed. Except from reducing the workload and making the process less tedious, the method yields optimal gains in a sense defined by a user. The solution is implemented and verified in simulation on a driving scenario. The vehicle is able to perform lane keeping maneuvers under varying vehicle velocity.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be4cc821b1cab8ab2df8ac1accf2eb9c https://doi.org/10.1109/icnsc52481.2021.9702240 Zobrazit plný text záznamu