A Decision-Making Model for Autonomous Vehicles at Intersections Based on Hierarchical Reinforcement Learning

Xue Mei Chen; Shu Yuan Xu; Zi Jia Wang; Xue Long Zheng; Xin Tong Han; En Hao Liu

doi:10.1142/S2301385024500122

A Decision-Making Model for Autonomous Vehicles at Intersections Based on Hierarchical Reinforcement Learning

Xue Mei Chen, Shu Yuan Xu, Zi Jia Wang, Xue Long Zheng, Xin Tong Han, En Hao Liu

Advanced Research Institute of Multidisciplinary Science

Beijing Institute of Technology

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

Abstract

By aiming at addressing the left-turning problem of an autonomous vehicle considering the oncoming vehicles at an urban unsignallized intersection, a hierarchical reinforcement learning is proposed and a two-layer model is established to study behaviors of left-turning driving. Compared with the conventional decision-making models with a fixed path, the proposed multi-paths decision-making algorithm with horizontal and vertical strategies can improve the efficiency of autonomous vehicles crossing intersections while ensuring safety.

Original language	English
Pages (from-to)	641-652
Number of pages	12
Journal	Unmanned Systems
Volume	12
Issue number	4
DOIs	https://doi.org/10.1142/S2301385024500122
Publication status	Published - 1 Jul 2024

Keywords

Autonomous vehicles
decision-making model
deep deterministic policy gradient
hierarchical reinforcement learning
urban intersections

Access to Document

10.1142/S2301385024500122

Cite this

Chen, X. M., Xu, S. Y., Wang, Z. J., Zheng, X. L., Han, X. T., & Liu, E. H. (2024). A Decision-Making Model for Autonomous Vehicles at Intersections Based on Hierarchical Reinforcement Learning. Unmanned Systems, 12(4), 641-652. https://doi.org/10.1142/S2301385024500122

@article{147f69aa043f4b27a67150748491c81b,

title = "A Decision-Making Model for Autonomous Vehicles at Intersections Based on Hierarchical Reinforcement Learning",

abstract = "By aiming at addressing the left-turning problem of an autonomous vehicle considering the oncoming vehicles at an urban unsignallized intersection, a hierarchical reinforcement learning is proposed and a two-layer model is established to study behaviors of left-turning driving. Compared with the conventional decision-making models with a fixed path, the proposed multi-paths decision-making algorithm with horizontal and vertical strategies can improve the efficiency of autonomous vehicles crossing intersections while ensuring safety.",

keywords = "Autonomous vehicles, decision-making model, deep deterministic policy gradient, hierarchical reinforcement learning, urban intersections",

author = "Chen, {Xue Mei} and Xu, {Shu Yuan} and Wang, {Zi Jia} and Zheng, {Xue Long} and Han, {Xin Tong} and Liu, {En Hao}",

note = "Publisher Copyright: #c World Scientific Publishing Company.",

year = "2024",

month = jul,

day = "1",

doi = "10.1142/S2301385024500122",

language = "English",

volume = "12",

pages = "641--652",

journal = "Unmanned Systems",

issn = "2301-3850",

publisher = "World Scientific",

number = "4",

}

TY - JOUR

T1 - A Decision-Making Model for Autonomous Vehicles at Intersections Based on Hierarchical Reinforcement Learning

AU - Chen, Xue Mei

AU - Xu, Shu Yuan

AU - Wang, Zi Jia

AU - Zheng, Xue Long

AU - Han, Xin Tong

AU - Liu, En Hao

N1 - Publisher Copyright: #c World Scientific Publishing Company.

PY - 2024/7/1

Y1 - 2024/7/1

N2 - By aiming at addressing the left-turning problem of an autonomous vehicle considering the oncoming vehicles at an urban unsignallized intersection, a hierarchical reinforcement learning is proposed and a two-layer model is established to study behaviors of left-turning driving. Compared with the conventional decision-making models with a fixed path, the proposed multi-paths decision-making algorithm with horizontal and vertical strategies can improve the efficiency of autonomous vehicles crossing intersections while ensuring safety.

AB - By aiming at addressing the left-turning problem of an autonomous vehicle considering the oncoming vehicles at an urban unsignallized intersection, a hierarchical reinforcement learning is proposed and a two-layer model is established to study behaviors of left-turning driving. Compared with the conventional decision-making models with a fixed path, the proposed multi-paths decision-making algorithm with horizontal and vertical strategies can improve the efficiency of autonomous vehicles crossing intersections while ensuring safety.

KW - Autonomous vehicles

KW - decision-making model

KW - deep deterministic policy gradient

KW - hierarchical reinforcement learning

KW - urban intersections

UR - http://www.scopus.com/inward/record.url?scp=85147511674&partnerID=8YFLogxK

U2 - 10.1142/S2301385024500122

DO - 10.1142/S2301385024500122

M3 - Article

AN - SCOPUS:85147511674

SN - 2301-3850

VL - 12

SP - 641

EP - 652

JO - Unmanned Systems

JF - Unmanned Systems

IS - 4

ER -

A Decision-Making Model for Autonomous Vehicles at Intersections Based on Hierarchical Reinforcement Learning

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this