Search

Traveling vehicles participate in emphasizing the global warming problem due to the gases produced by them. The exponential increase in the number of daily traveling vehicles has exaggerated the world pollution problem threatening the life on the planet. This encourages several environmental organizations to look for designing green vehicles. Moreover, several countries have forced green driving rules and technologies. Road intersections are considered high fuel consumption areas over the road network. This is due to the required power to stop moving vehicles and restart stopped vehicles at these intersections. This work introduces an efficient traffic light scheduling algorithm (SmartLight) that controls the competing traffic flows at the road intersections. It is designed to reduce the total consumed fuel of vehicles and thus it reduces their produced gases. The topology of the road intersection, the context of the competing traffic flows, and the real-time traffic characteristics of each flow are mainly considered to schedule the phases of each located traffic light. The phases of the traffic light cycle are primly set to allow emergency vehicles to pass through the intersection without stopping. Then, the traffic flow that contains heavy vehicles or has the highest weight among the competing traffic flows is assigned the highest priority to pass through the signalized intersection. Finally, the average waiting delay time of each flow on the signalized intersection should not exceed a pre-determined threshold to guarantee fair sharing of the signalized intersection. The scheduling time of each phase is set based on the lengths of platoons of vehicles that are scheduled during that phase from different un-conflicted traffic flows. An experimental study has evaluated the performance of the proposed algorithm (SmartLight) compared to previous traffic light scheduling algorithms in terms of total fuel consumption, gas emission, the average queuing delay time of vehicles, and the throughput of the road intersection. [ABSTRACT FROM AUTHOR]

Emergency vehicles (EMVs) play a crucial role in responding to time-critical calls such as medical emergencies and fire outbreaks in urban areas. Existing methods for EMV dispatch typically optimize routes based on historical traffic-flow data and design traffic signal pre-emption accordingly; however, we still lack a systematic methodology to address the coupling between EMV routing and traffic signal control. In this paper, we propose EMVLight, a decentralized reinforcement learning (RL) framework for joint dynamic EMV routing and traffic signal pre-emption. We adopt the multi-agent advantage actor–critic method with policy sharing and spatial discounted factor. This framework addresses the coupling between EMV navigation and traffic signal control via an innovative design of multi-class RL agents and a novel pressure-based reward function. The proposed methodology enables EMVLight to learn network-level cooperative traffic signal phasing strategies that not only reduce EMV travel time but also shortens the travel time of non-EMVs. Simulation-based experiments indicate that EMVLight enables up to a 42.6% reduction in EMV travel time as well as an 23.5% shorter average travel time compared with existing approaches. • Propose a multi-agent reinforcement learning framework for traffic signal control. • Simultaneously solve emergency vehicle (EMV) routing and congestion alleviation. • Formulate a model to capture the establishment of emergency lane for EMV passage. • Empower the actor-critic method with policy sharing and spatially adjusted reward. • Conduct comprehensive experiments on both synthetic and real-world maps. • Reduce 42.6% of EMV travel time and 23.5% average trip time. [ABSTRACT FROM AUTHOR]

To estimate travel times through road networks, in this study, we assume a stochastic demand and formulate a stochastic network equilibrium model whose travel times, flows, and demands are stochastic. This model enables us to examine network reliability under stochastic circumstances and to evaluate the effect of providing traffic information on travel times. For traffic information, we focus on travel time information and propose methods to evaluate the effect of providing that information. To examine the feasibility and validity of the proposed model and methods, we apply them to a simple network and the real road network of Kanazawa, Japan. The results indicate that providing ambulance drivers in Kanazawa with travel time information leads to an average reduction in travel time of approximately three minutes. [ABSTRACT FROM AUTHOR]