RLA-DDTC: A Reinforcement Learning Agent-based approach for Decision-making for Dynamic Traffic Control in C-ITS systems

Abstract

The Cooperative Intelligent Transport System (C-ITS) aims to address traffic efficiency, road safety, and environmental sustain-ability by facilitating communication among autonomous entities with complex behaviors. Traffic congestion is a significant issue in modern urban areas, influenced by factors like accidents, road works, weather and peak hours, leading to wasted time, fuel, and increased pollution. To address these challenges, multi-agent systems have proven effective in managing dynamic traffic in C-ITS environments. In this paper, we propose a novel Reinforcement Learning Agent (RLA) method for decision-making in C-ITS systems to optimize traffic flow and control. Our method utilizes the Q-learning algorithm, enabling effective problem-solving. We conducted experiments to demonstrate the versatility and effectiveness of our approach in complex C-ITS environments. Our method surpasses traditional metrics like mean travel time and mean speed, validated through comparisons with Actor-Critic methods and against the Original Traffic Trace (OTT). This research contributes to advancing decision-making capabilities within C-ITS systems by leveraging RLA for traffic optimization and efficiency.