Smart multi-agent traffic coordinator for autonomous vehicles at intersections

Lamouik, Imad; Yahyaouy, Ali; Sabri, My Abdelouahed

doi:10.1109/atsip.2017.8075564

Cited by 17 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Perronnet et al [178] deployed a sequence-based strategy for AVs that was resilient to communication latency and could ensure safe crossing of the vehicles with minimum delay. Lamouik et al [218] employed a multi-agent coordination system using deep neural networks and reinforced learning (RL) in an autonomous environment. The proposed system offered safe a rapid intersection passing.…”

Section: Safety and Efficiencymentioning

confidence: 99%

A Comprehensive Survey on Cooperative Intersection Management for Heterogeneous Connected Vehicles

Gholamhosseinian

Seitz

2022

IEEE Access

View full text Add to dashboard Cite

Nowadays, with the advancement of technology, world is trending toward high mobility and dynamics. In this context, intersection management (IM) as one of the most crucial elements of the transportation sector demands high attention. Today, road entities including infrastructures, vulnerable road users (VRUs) such as motorcycles, moped, scooters, pedestrians, bicycles, and other types of vehicles such as trucks, buses, cars, emergency vehicles, and railway vehicles like trains or trams are able to communicate cooperatively using vehicle-to-everything (V2X) communications and provide traffic safety, efficiency, infotainment and ecological improvements. In this paper, we take into account different types of intersections in terms of signalized, semi-autonomous (hybrid) and autonomous intersections and conduct a comprehensive survey on various intersection management methods for heterogeneous connected vehicles (CVs). We consider heterogeneous classes of vehicles such as road and rail vehicles as well as VRUs including bicycles, scooters and motorcycles. All kinds of intersection goals, modeling, coordination architectures, scheduling policies are thoroughly discussed. Signalized and semi-autonomous intersections are assessed with respect to these parameters. We especially focus on autonomous intersection management (AIM) and categorize this section based on four major goals involving safety, efficiency, infotainment and environment. Each intersection goal provides an in-depth investigation on the corresponding literature from the aforementioned perspectives. Moreover, robustness and resiliency of IM are explored from diverse points of view encompassing sensors, information management and sharing, planning universal scheme, heterogeneous collaboration, vehicle classification, quality measurement, external factors, intersection types, localization faults, communication anomalies and channel optimization, synchronization, vehicle dynamics and model mismatch, model uncertainties, recovery, security and privacy.INDEX TERMS Vehicular ad-hoc networks (VANETs), intersection management (IM), vehicle-tovehicle (V2V), vehicle-to-infrastructure (V2I), trajectory planning (TP), spatio-temporal (ST), connected autonomous vehicles (CAVs), vulnerable road users (VRUs), connected vehicles (CVs), autonomous vehicle (AVs). II. INTERSECTION MANAGEMENT (IM) FUNDAMENTALS A. ARCHITECTURE ALTERNATIVESASHKAN GHOLAMHOSSEINIAN (Graduate Student Member, IEEE) received the bachelor's degree in computer engineering-software in Iran, the M.Sc. degree in computer network engineering from Halmstad University, Sweden, and the Post master's degree in communications for intelligent transport systems from Eurecom, France. He is currently pursuing the Ph.D. degree in electrical engineering and information technology with the Communication Networks Group, Technische Universität Ilmenau, Germany. His research interests include vehicular networks, intelligent transport systems, computer networks, and wireless and mobile networks and communications. JOCHEN...

show abstract

Section: Safety and Efficiencymentioning

confidence: 99%

A Comprehensive Survey on Cooperative Intersection Management for Heterogeneous Connected Vehicles

Gholamhosseinian

Seitz

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…It is one of the widely used deep reinforcement learning (DRL) algorithms. This algorithm also has a very wide range of applications in the field of intelligent transportation [19][20][21][22]. Li et al [19] use DQN pairs to take the sampled traffic state as input and the maximum intersection throughput as output.…”

Section: Related Workmentioning

confidence: 99%

Coordinated Control of Distributed Traffic Signal Based on Multiagent Cooperative Game

Zhang

Jin

Fang

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In the adaptive traffic signal control (ATSC), reinforcement learning (RL) is a frontier research hotspot, combined with deep neural networks to further enhance its learning ability. The distributed multiagent RL (MARL) can avoid this kind of problem by observing some areas of each local RL in the complex plane traffic area. However, due to the limited communication capabilities between each agent, the environment becomes partially visible. This paper proposes multiagent reinforcement learning based on cooperative game (CG-MARL) to design the intersection as an agent structure. The method considers not only the communication and coordination between agents but also the game between agents. Each agent observes its own area to learn the RL strategy and value function, then concentrates the Q function from different agents through a hybrid network, and finally forms its own final Q function in the entire large-scale transportation network. The results show that the proposed method is superior to the traditional control method.

show abstract

“…Compared to traffic-light systems and existing methods, the proposed method reduces communication latency and evacuation time, with guaranteed safety. Similarly, Lamouik et al [67] developed a smart multiagent traffic coordinator to provide safe and fast intersection crossing. The proposed method is based on reinforced learning (RL) and deep neural networks designed to learn and estimate the best action for each vehicle.…”

Section: Efficiency and Safetymentioning

confidence: 99%

“…As shown in Table B-3 in Appendix B, rule-based (e.g., [53], [56], and [57]), optimization (e.g., [55], [60], and [65]), hybrid (e.g., [61], [63], and [68]), and machine learning (e.g., [67], [76], [84], and [91]) methods have been developed to improve intersection efficiency while considering safety. Researchers claimed that four of the optimization methods are suitable for real-time or online implementation ( [70], [71], [84], and [92]).…”

Section: Efficiency and Safetymentioning

confidence: 99%

Intelligent Intersection Management Systems Considering Autonomous Vehicles: A Systematic Literature Review

Namazi

2019

IEEE Access

128

View full text Add to dashboard Cite

Over the past several decades, the development of technologies and the production of autonomous vehicles have enhanced the need for intelligent intersection management systems. Subsequently, growing interest in studying the traffic management of autonomous vehicles at intersections has been evident, which indicates a critical need to conduct a systematic literature review on this topic. This paper offers a systematic review of the proposed methodologies for intelligent intersection management systems and presents the remaining research gaps and possible future research approaches. We consider both pure autonomous vehicle traffic and mixed traffic at four-way signalized and unsignalized intersection(s). We searched for articles published from 2008 to 2019, and identified 105 primary studies. We applied the thematic analysis method to analyze the extracted data, which led to the identification of four main classes of methodologies, namely rule-based, optimization, hybrid, and machine learning methods. We also compared how well the methods satisfy their goals, namely efficiency, safety, ecology, and passenger comfort. This analysis allowed us to determine the primary challenges of the presented methodologies and propose new approaches in this area.INDEX TERMS Autonomous vehicle, intelligent intersection management system, mixed traffic, vehicleto-infrastructure (V2I) communication, vehicle-to-vehicle (V2V) communication.

show abstract

Smart multi-agent traffic coordinator for autonomous vehicles at intersections

Cited by 17 publications

References 10 publications

A Comprehensive Survey on Cooperative Intersection Management for Heterogeneous Connected Vehicles

A Comprehensive Survey on Cooperative Intersection Management for Heterogeneous Connected Vehicles

Coordinated Control of Distributed Traffic Signal Based on Multiagent Cooperative Game

Intelligent Intersection Management Systems Considering Autonomous Vehicles: A Systematic Literature Review

Contact Info

Product

Resources

About