Intelligent 3-Way Priority-Driven Traffic Light Control System for Emergency Vehicles

The problem of traffic congestion is a significant phenomenon that has had a substantial impact on the transportation system within the country. This phenomenon has given rise to numerous intricacies, particularly in instances where emergency situations occur at traffic light intersections that are consistently congested with a high volume of vehicles. This implementation of a traffic light controller system is designed with the intention of addressing this problem. The purpose of the system was to facilitate the operation of a 3-way traffic control light and provide priority to emergency vehicles using a Radio Frequency Identification (RFID) sensor and Reduced Instruction Set Computing (RISC) Architecture Based Microcontroller. This research work involved designing a system to mitigate the occurrence of accidents commonly observed at traffic light intersections, where vehicles often need to maneuver in order to make way for emergency vehicles following a designated route. The research effectively achieved the analysis, simulation and implementation of wireless communication devices for traffic light control. The implemented prototype utilizes RFID transmission, operates in conjunction with the sequential mode of traffic lights to alter the traffic light sequence accordingly and reverts the traffic lights back to their normal sequence after the emergency vehicle has passed the traffic lights.

Deep Reinforcement Learning for Addressing Disruptions in Traffic Light Control

This paper investigates the use of multi-agent deep Q-network(MADQN)to address the curse of dimensionality issue occurred in the traditional multi-agent reinforcement learning(MARL)approach.The proposed MADQN is applied to traffic light controllers at multiple intersections with busy traffic and traffic disruptions,particularly rainfall.MADQN is based on deep Q-network(DQN),which is an integration of the traditional reinforcement learning(RL)and the newly emerging deep learning(DL)approaches.MADQN enables traffic light controllers to learn,exchange knowledge with neighboring agents,and select optimal joint actions in a collaborative manner.A case study based on a real traffic network is conducted as part of a sustainable urban city project in the Sunway City of Kuala Lumpur in Malaysia.Investigation is also performed using a grid traffic network(GTN)to understand that the proposed scheme is effective in a traditional traffic network.Our proposed scheme is evaluated using two simulation tools,namely Matlab and Simulation of Urban Mobility(SUMO).Our proposed scheme has shown that the cumulative delay of vehicles can be reduced by up to 30%in the simulations.

Optimal traffic light control method for a single intersecti on basedon hybrid systems

A single intersection of two phases is selected as a model to put forward a new optimal time-planning scheme for traffic light based on the model of hybrid automata for single intersection. A method of optimization is proposed for hybrid systems, and the average queue length over all queues is used as an objective function to find an optimal switching scheme for traffic light. It is illustrated that traffic light control for single intersection is a typical hybrid system, and the optimal planning-time scheme can be obtained using the optimal hybrid systems control based on the two stages method.

Mathematical Modeling,Field Calibration and Numerical Simulation of Low-Speed Mixed Traffic Flow in Cities

Ｗｉｔｈｔｈｅｒａｐｉｄｄｅｖｅｌｏｐｍｅｎｔｏｆｔｒａｎｓｐｏｒｔａｔｉｏｎａｎｄａｕｔｏｍｏｂｉｌｅｉｎｄｕｓｔｒｙ，ｔｈｅｃｏｎｆｌｉｃｔｂｅｔｗｅｅｎｍｏｔｏｒｍａｎｕｆａｃｔｕｒｅａｎｄｈｉｇｈｗａｙｃｏｎｓｔｒｕｃｔｉｏｎｂｅｃｏｍｅｓｓ...

Optimizing urban traffic control using a rational agent

This paper is devoted to developing and evaluating a set of technologies with the objective of designing a methodology for the implementation of sophisticated traffic lights by means of rational agents. These devices would be capable of optimizing the behavior of a junction with multiple traffic signals, reaching a higher level of autonomy without losing reliability, accuracy, or efficiency in the offered services. In particular, each rational agent in a traffic signal will be able to analyze the requirements and constraints of the road, in order to know its level of demand. With such information, the rational agent will adapt its light cycles with the view of accomplishing more fluid traffic patterns and minimizing the pollutant environmental emissions produced by vehicles while they are stopped at a red light, through using a case-based reasoning(CBR) adaptation. This paper also integrates a microscopic simulator developed to run a set of tests in order to compare the presented methodology with traditional traffic control methods. Two study cases are shown to demonstrate the efficiency of the introduced approach, increasing vehicular mobility and reducing harmful activity for the environment. For instance, in the first scenario, taking into account the studied traffic volumes, our approach increases mobility by 23% and reduces emissions by 35%. When the roads are managed by sophisticated traffic lights, a better level of service and considerable environmental benefits are achieved, demonstrating the utility of the presented approach.