Empirical Comparison of Heuristic Optimisation Methods for Automated Car Setup

Berna Kiraz; Shahriar Asta; Ender Özcan; Muhammet Köle; A. Sima Etaner-Uyar

doi:10.1007/978-3-031-16832-1_1

Empirical Comparison of Heuristic Optimisation Methods for Automated Car Setup

Berna Kiraz^*, Shahriar Asta, Ender Özcan, Muhammet Köle, A. Sima Etaner-Uyar

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

Tuning a race car to improve its performance by adopting an effective setup is crucial and an extremely challenging task. The Open Racing Car Simulator, referred to as TORCS, is a well-known simulator in which a race car requires a configuration of twenty two real-valued parameters for an optimal setup. In this study, various modern (meta)heuristic techniques, such as, evolutionary algorithms, swarm intelligence algorithm and selection hyper-heuristics, are evaluated using TORCS to solve the car setup optimisation problem across a range of tracks. An in-depth performance comparison and analysis of those techniques on the car setup optimisation problem are provided with a discussion on their strengths and weaknesses. The empirical results indicate the success of Covariance Matrix Adaptation Evolutionary Strategy for the car setup optimisation problem.

Original language	English
Title of host publication	Studies in Computational Intelligence
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	1-18
Number of pages	18
DOIs	https://doi.org/10.1007/978-3-031-16832-1_1
Publication status	Published - 2023
Externally published	Yes

Publication series

Name	Studies in Computational Intelligence
Volume	1069
ISSN (Print)	1860-949X
ISSN (Electronic)	1860-9503

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

Evolutionary computation
Heuristic algorithms
Particle swarm optimization
Simulation

Access to Document

10.1007/978-3-031-16832-1_1

Cite this

@inbook{2d9dc381a0214787bc3f4bbe29a8c123,

title = "Empirical Comparison of Heuristic Optimisation Methods for Automated Car Setup",

abstract = "Tuning a race car to improve its performance by adopting an effective setup is crucial and an extremely challenging task. The Open Racing Car Simulator, referred to as TORCS, is a well-known simulator in which a race car requires a configuration of twenty two real-valued parameters for an optimal setup. In this study, various modern (meta)heuristic techniques, such as, evolutionary algorithms, swarm intelligence algorithm and selection hyper-heuristics, are evaluated using TORCS to solve the car setup optimisation problem across a range of tracks. An in-depth performance comparison and analysis of those techniques on the car setup optimisation problem are provided with a discussion on their strengths and weaknesses. The empirical results indicate the success of Covariance Matrix Adaptation Evolutionary Strategy for the car setup optimisation problem.",

keywords = "Evolutionary computation, Heuristic algorithms, Particle swarm optimization, Simulation",

author = "Berna Kiraz and Shahriar Asta and Ender {\"O}zcan and Muhammet K{\"o}le and Etaner-Uyar, \{A. Sima\}",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.",

year = "2023",

doi = "10.1007/978-3-031-16832-1\_1",

language = "English",

series = "Studies in Computational Intelligence",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "1--18",

booktitle = "Studies in Computational Intelligence",

address = "Germany",

}

Empirical Comparison of Heuristic Optimisation Methods for Automated Car Setup. / Kiraz, Berna; Asta, Shahriar; Özcan, Ender et al.
Studies in Computational Intelligence. Springer Science and Business Media Deutschland GmbH, 2023. p. 1-18 (Studies in Computational Intelligence; Vol. 1069).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

TY - CHAP

T1 - Empirical Comparison of Heuristic Optimisation Methods for Automated Car Setup

AU - Kiraz, Berna

AU - Asta, Shahriar

AU - Özcan, Ender

AU - Köle, Muhammet

AU - Etaner-Uyar, A. Sima

PY - 2023

Y1 - 2023

N2 - Tuning a race car to improve its performance by adopting an effective setup is crucial and an extremely challenging task. The Open Racing Car Simulator, referred to as TORCS, is a well-known simulator in which a race car requires a configuration of twenty two real-valued parameters for an optimal setup. In this study, various modern (meta)heuristic techniques, such as, evolutionary algorithms, swarm intelligence algorithm and selection hyper-heuristics, are evaluated using TORCS to solve the car setup optimisation problem across a range of tracks. An in-depth performance comparison and analysis of those techniques on the car setup optimisation problem are provided with a discussion on their strengths and weaknesses. The empirical results indicate the success of Covariance Matrix Adaptation Evolutionary Strategy for the car setup optimisation problem.

AB - Tuning a race car to improve its performance by adopting an effective setup is crucial and an extremely challenging task. The Open Racing Car Simulator, referred to as TORCS, is a well-known simulator in which a race car requires a configuration of twenty two real-valued parameters for an optimal setup. In this study, various modern (meta)heuristic techniques, such as, evolutionary algorithms, swarm intelligence algorithm and selection hyper-heuristics, are evaluated using TORCS to solve the car setup optimisation problem across a range of tracks. An in-depth performance comparison and analysis of those techniques on the car setup optimisation problem are provided with a discussion on their strengths and weaknesses. The empirical results indicate the success of Covariance Matrix Adaptation Evolutionary Strategy for the car setup optimisation problem.

KW - Evolutionary computation

KW - Heuristic algorithms

KW - Particle swarm optimization

KW - Simulation

UR - https://www.scopus.com/pages/publications/85143777389

U2 - 10.1007/978-3-031-16832-1_1

DO - 10.1007/978-3-031-16832-1_1

M3 - Chapter

AN - SCOPUS:85143777389

T3 - Studies in Computational Intelligence

SP - 1

EP - 18

BT - Studies in Computational Intelligence

PB - Springer Science and Business Media Deutschland GmbH

ER -