Cooperative autonomous vehicle control with deep reinforcement learning in lane-free roundabouts and its adaptability to various geometries

This study investigates deep reinforcement learning (DRL) mechanisms for achieving cooperative driving control of connected autonomous vehicles (CAVs) on lane-free roads. This study investigates the effectiveness of each of the two methods proposed in our conference paper to verify whether the best...

Full description

Saved in:
Bibliographic Details
Main Authors: Reo Nakaya, Tomohiro Harada, Yukiya Miura, Kiyohiko Hattori, Johei Matsuoka
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:SICE Journal of Control, Measurement, and System Integration
Subjects:
Online Access:http://dx.doi.org/10.1080/18824889.2025.2508016
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850117976876908544
author Reo Nakaya
Tomohiro Harada
Yukiya Miura
Kiyohiko Hattori
Johei Matsuoka
author_facet Reo Nakaya
Tomohiro Harada
Yukiya Miura
Kiyohiko Hattori
Johei Matsuoka
author_sort Reo Nakaya
collection DOAJ
description This study investigates deep reinforcement learning (DRL) mechanisms for achieving cooperative driving control of connected autonomous vehicles (CAVs) on lane-free roads. This study investigates the effectiveness of each of the two methods proposed in our conference paper to verify whether the best performance is achieved when both methods are incorporated. This study also evaluates the generalization performance of training models by conducting driving tests on several test courses to see if the training models can be adapted to courses other than the training course. In addition, this study proposed improvement in the use of course direction information to enhance the generalization performance of the training models. The result shows the proposed improvement can increase the generalizability of the trained model and the efficiency of vehicle flow.
format Article
id doaj-art-4339d8ccd8544ba7a175e836ccf9dca6
institution OA Journals
issn 1884-9970
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series SICE Journal of Control, Measurement, and System Integration
spelling doaj-art-4339d8ccd8544ba7a175e836ccf9dca62025-08-20T02:35:59ZengTaylor & Francis GroupSICE Journal of Control, Measurement, and System Integration1884-99702025-12-0118110.1080/18824889.2025.25080162508016Cooperative autonomous vehicle control with deep reinforcement learning in lane-free roundabouts and its adaptability to various geometriesReo Nakaya0Tomohiro Harada1Yukiya Miura2Kiyohiko Hattori3Johei Matsuoka4Tokyo Metropolitan UniversitySaitama UniversityTokyo Metropolitan UniversityTokyo Denki UniversityTokyo University of TechnologyThis study investigates deep reinforcement learning (DRL) mechanisms for achieving cooperative driving control of connected autonomous vehicles (CAVs) on lane-free roads. This study investigates the effectiveness of each of the two methods proposed in our conference paper to verify whether the best performance is achieved when both methods are incorporated. This study also evaluates the generalization performance of training models by conducting driving tests on several test courses to see if the training models can be adapted to courses other than the training course. In addition, this study proposed improvement in the use of course direction information to enhance the generalization performance of the training models. The result shows the proposed improvement can increase the generalizability of the trained model and the efficiency of vehicle flow.http://dx.doi.org/10.1080/18824889.2025.2508016deep reinforcement learningautomated drivingcooperative controlroundaboutlane-free
spellingShingle Reo Nakaya
Tomohiro Harada
Yukiya Miura
Kiyohiko Hattori
Johei Matsuoka
Cooperative autonomous vehicle control with deep reinforcement learning in lane-free roundabouts and its adaptability to various geometries
SICE Journal of Control, Measurement, and System Integration
deep reinforcement learning
automated driving
cooperative control
roundabout
lane-free
title Cooperative autonomous vehicle control with deep reinforcement learning in lane-free roundabouts and its adaptability to various geometries
title_full Cooperative autonomous vehicle control with deep reinforcement learning in lane-free roundabouts and its adaptability to various geometries
title_fullStr Cooperative autonomous vehicle control with deep reinforcement learning in lane-free roundabouts and its adaptability to various geometries
title_full_unstemmed Cooperative autonomous vehicle control with deep reinforcement learning in lane-free roundabouts and its adaptability to various geometries
title_short Cooperative autonomous vehicle control with deep reinforcement learning in lane-free roundabouts and its adaptability to various geometries
title_sort cooperative autonomous vehicle control with deep reinforcement learning in lane free roundabouts and its adaptability to various geometries
topic deep reinforcement learning
automated driving
cooperative control
roundabout
lane-free
url http://dx.doi.org/10.1080/18824889.2025.2508016
work_keys_str_mv AT reonakaya cooperativeautonomousvehiclecontrolwithdeepreinforcementlearninginlanefreeroundaboutsanditsadaptabilitytovariousgeometries
AT tomohiroharada cooperativeautonomousvehiclecontrolwithdeepreinforcementlearninginlanefreeroundaboutsanditsadaptabilitytovariousgeometries
AT yukiyamiura cooperativeautonomousvehiclecontrolwithdeepreinforcementlearninginlanefreeroundaboutsanditsadaptabilitytovariousgeometries
AT kiyohikohattori cooperativeautonomousvehiclecontrolwithdeepreinforcementlearninginlanefreeroundaboutsanditsadaptabilitytovariousgeometries
AT joheimatsuoka cooperativeautonomousvehiclecontrolwithdeepreinforcementlearninginlanefreeroundaboutsanditsadaptabilitytovariousgeometries