Year: 2024
Type: article
Abstract: —Urban traffic congestion represents a critical chal-lenge for modern cities, significantly impacting mobility, envi-ronmental sustainability, and quality of urban life. This com-prehensive survey explores the transformative potential of ad-vanced technologies—particularly deep reinforcement learning (DRL), artificial intelligence (AI), and Vehicle-to- Everything (V2X) communication—in revolutionizing traffic management systems. We critically examine emerging approaches that move beyond traditional fixed-timing signals, highlighting innovative methodologies including deep reinforcement models , computer vision techniques like YOLOv4, and intelligent traffic coordina-tion strategies. The survey synthesizes current research trends, evaluating technological capabilities in real-time traffic opti- mization, emergency vehicle prioritization, and predictive traffic management. By analyzing both technological achievements and existing limitations, we provide a strategic roadmap for future research, emphasizing the need for more adaptive, data-driven, and intelligent urban traffic solutions that can effectively address the complex dynamics of modern transportation networks. Index Terms—Smart Traffic Management, Deep Reinforce-ment Learning, Artificial Intelligence, Computer Vision, Vehicle-to-Everything Communication, Urban Mobility, Intelligent Transportation Systems
DOI: 10.55041/ijsrem41556
Authors: Noyal Reji, Philips Jose, Sanjayramprasad V S, Aju Joseph, Alpha Mathew
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4407564518