$α$-Potential Games for Decentralized Control of Connected and Automated Vehicles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Di, Xuan, Hu, Anran, Wang, Zhexin, Zhang, Yufei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909946414628864
author Di, Xuan
Hu, Anran
Wang, Zhexin
Zhang, Yufei
author_facet Di, Xuan
Hu, Anran
Wang, Zhexin
Zhang, Yufei
contents Designing scalable and safe control strategies for large populations of connected and automated vehicles (CAVs) requires accounting for strategic interactions among heterogeneous agents under decentralized information. While dynamic games provide a natural modeling framework, computing Nash equilibria (NEs) in large-scale settings remains challenging, and existing mean-field game approximations rely on restrictive assumptions that fail to capture collision avoidance and heterogeneous behaviors. This paper proposes an $α$-potential game framework for decentralized CAV control. We show that computing $α$-NE reduces to solving a decentralized control problem, and derive tight bounds of the parameter $α$ based on interaction intensity and asymmetry. We further develop scalable policy gradient algorithms for computing $α$-NEs using decentralized neural-network policies. Numerical experiments demonstrate that the proposed framework accommodates diverse traffic flow models and effectively captures collision avoidance, obstacle avoidance, and agent heterogeneity.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05712
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle $α$-Potential Games for Decentralized Control of Connected and Automated Vehicles
Di, Xuan
Hu, Anran
Wang, Zhexin
Zhang, Yufei
Optimization and Control
Computer Science and Game Theory
Multiagent Systems
Designing scalable and safe control strategies for large populations of connected and automated vehicles (CAVs) requires accounting for strategic interactions among heterogeneous agents under decentralized information. While dynamic games provide a natural modeling framework, computing Nash equilibria (NEs) in large-scale settings remains challenging, and existing mean-field game approximations rely on restrictive assumptions that fail to capture collision avoidance and heterogeneous behaviors. This paper proposes an $α$-potential game framework for decentralized CAV control. We show that computing $α$-NE reduces to solving a decentralized control problem, and derive tight bounds of the parameter $α$ based on interaction intensity and asymmetry. We further develop scalable policy gradient algorithms for computing $α$-NEs using decentralized neural-network policies. Numerical experiments demonstrate that the proposed framework accommodates diverse traffic flow models and effectively captures collision avoidance, obstacle avoidance, and agent heterogeneity.
title $α$-Potential Games for Decentralized Control of Connected and Automated Vehicles
topic Optimization and Control
Computer Science and Game Theory
Multiagent Systems
url https://arxiv.org/abs/2512.05712