Multi-Agent Deep Reinforcement Learning to Manage Connected Autonomous Vehicles at Tomorrow's Intersections

In recent years, the growing development of Connected Autonomous Vehicles (CAV), Intelligent Transport Systems (ITS), and 5G communication networks have led to the advent of Autonomous Intersection Management (AIM) systems. AIMs present a new paradigm for CAV control in future cities, taking control...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on vehicular technology 2022-07, Vol.71 (7), p.7033-7043
Main Authors: Antonio, Guillen-Perez, Maria-Dolores, Cano
Format: Article
Language:English
Subjects:
Algorithms
Autonomous intersection management
Autonomous vehicles
Communication networks
Complexity theory
connected autonomous vehicles
Control algorithms
Deep learning
deep reinforcement learning
Heuristic algorithms
intelligent transport systems
Intelligent transportation systems
intersection traffic management
Intersections
Machine learning
multi-agent deep reinforcement learning
Multiagent systems
Reinforcement learning
Traffic congestion
Traffic control
Traffic flow
Traffic signals
Training
Travel time
Urban areas
Vehicle dynamics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, the growing development of Connected Autonomous Vehicles (CAV), Intelligent Transport Systems (ITS), and 5G communication networks have led to the advent of Autonomous Intersection Management (AIM) systems. AIMs present a new paradigm for CAV control in future cities, taking control of CAVs in scenarios where cooperation is necessary and allowing safe and efficient traffic flows, eliminating traffic signals. So far, the development of AIM algorithms has been based on basic control algorithms, without the ability to adapt or keep learning new situations. To solve this, in this paper we present a new advanced AIM approach based on end-to-end Multi-Agent Deep Reinforcement Learning (MADRL) and trained using Curriculum through Self-Play , called advanced Reinforced AIM ( adv. RAIM). adv. RAIM enables the control of CAVs at intersections in a collaborative way, autonomously learning complex real-life traffic dynamics. In addition, adv .RAIM provides a new way to build smarter AIMs capable of proactively controlling CAVs in other highly complex scenarios. Results show remarkable improvements when compared to traffic light control techniques (reducing travel time by 59% or reducing time lost due to congestion by 95%), as well as outperforming other recently proposed AIMs (reducing waiting time by 56%), highlighting the advantages of using MADRL.
ISSN:0018-9545
1939-9359
DOI:10.1109/TVT.2022.3169907