Intelligent Urban Traffic Management Using Artificial Intelligence and Machine Learning Methods and Algorithms: Challenges and Opportunities

Machine Learning based Distributed Traffic Signal Control

Multi-Agent Autonomous Control Framework for Intelligent Transportation Infrastructure

A Multi-Agent Autonomous Control Framework that integrates Multi-Agent Systems (MAS), Artificial Intelligence (AI), Deep Reinforcement Learning (DRL), Graph Neural Networks (GNN), Internet of Things (IoT), Vehicle-to-Everything (V2X) communication, and edge-cloud computing is proposed.

Artificial Intelligence Models for Smart Traffic Management and Road Safety

An overview of the most prominent types of AI models employed in smart traffic control and road safety, such as supervised and unsupervised machine learning, deep learning, computer vision, and reinforcement learning, and their applications for traffic flow prediction, adaptive traffic signal control, vehicle and pedestrian detection, accident prediction, driver behaviour monitoring, and prioritisation of emergency vehicles are discussed.

Real-Time Intelligent Traffic Congestion Prediction and Management using Machine Learning

Optimizing Traffic Flow in Sri Lanka Using Reinforcement Learning-Based Traffic Light Control Approach

Traffic congestion in urban areas has become a significant challenge, particularly in developing countries such as Sri Lanka, where conventional fixed-time traffic signal systems are unable to adapt to dynamic traffic conditions. This research aimed to develop an adaptive traffic signal control system using reinforcement learning to improve traffic flow efficiency.The study primarily focuses on an Advantage Actor-Critic (A2C) reinforcement learning agent for adaptive traffic signal control. The A2C model was trained to optimize traffic flow by utilizing key state inputs such as vehicle waiting time, queue length, and rainfall conditions. Real-time traffic data required for these inputs were obtained using a YOLO-based vehicle detection model, which provided vehicle counts and queue length information. The system was trained and evaluated using a combination of real-world traffic data and simulated environments in the SUMO platform.The results showed that the proposed approach reduced vehicle waiting time and queue length compared to traditional fixed-time control methods. The reinforcement learning agent demonstrated the ability to learn improved signal timing strategies through interaction with the environment.Overall, the findings indicate that reinforcement learning-based adaptive traffic control can enhance traffic efficiency and provide a promising solution for managing congestion in complex urban environments.

Design management for smart urban traffic: an IoV-Based multi-agent AI framework for adaptive signal control

This study develops an adaptive multi-agent traffic-management framework that responds to real-time urban traffic conditions using Internet of Vehicles (IoV) traffic-state information and artificial intelligence. Remote-sensing information is discussed as a contextual extension of the broader framework rather than as an experimentally validated input in the present evaluation. A Sustainable Multi-Agent Traffic Management Strategy (SMATMS) is implemented using a Galactic Swarm Optimized Deep Q-Network (GSO-DQN). The empirical evaluation uses traffic-state variables available in the Urban Traffic Light Control Dataset and considers two- and six-intersection multi-agent reinforcement-learning scenarios. GSO is positioned as an outer optimization layer that supports exploration of learning/control parameter configurations, while DQN performs sequential signal-control decisions. The reported aggregate comparisons show favorable observed mean performance for GSO-DQN relative to MADDPG and MARDDPG in reward, delay, queue length, travel time, and pedestrian waiting across the two evaluated scenarios. Because the archived results are aggregate summaries rather than a repeated-seed inferential dataset, the revised manuscript treats these differences descriptively and does not claim formal statistical significance. The framework provides an adaptive AI-based approach for coordinated traffic-signal control and supports traffic-efficiency-related sustainability objectives in the evaluated multi-intersection settings. Claims concerning metropolitan-scale scalability, direct emission reduction, and operational remote-sensing fusion are explicitly limited and identified as priorities for future validation.