Crossing an urban traffic intersection is one of the most dangerous activities of a blind or visually impaired person's travel. Building on past work by the authors on the issue of proper alignment with the crosswalk, this paper addresses the complementary issue of knowing when it is time to cross. We describe a prototype portable system that alerts the user in real time once the Walk light is ...

This paper proposes the Intersection Simulation System which can dynamically manage the real-time traffic flow for each section from the intersections by referring to the traffic information database. This system consists of the hierarchical 3 layers. The lower layer is the physical layer where the traffic information is acquired on an actual road. The middle layer, which is the core of this sy...

We propose a light controlled intersection model based on a constant speed continuous Petri net. The Model is innovative, firstly, by the free space modeling together with the opposite direction of the vehicular flow, secondly by the continuous Petri net use only leading to a smaller state space. For this purpose, we show a new method for conflict resolution in a Petri net based on the maximal ...

Red-light running problem has been recognized as a significant safety problem in Indonesia as well as throughout the world. This is a frequent and highly dangerous driving act. Reducing this risk behavior depends on understanding its prevalence, as well as the drivers involved. However, it should also improve the infrastructure system in order to be an intelligent system. In this study, modelin...

The use of a Model Predictive Controller (MPC) in an urban traffic network allows for controlling the infrastructure and errors its operations. In this research, novel, stable predictive controller is proposed state-space dynamics are used to estimate number vehicles at isolated intersection length queue. This novel control strategy based on type light duration green-light phase aims achieve op...

The rapid development of autonomous vehicles spurred a careful investigation of the potential benefits of allautonomous transportation networks. Most studies conclude that autonomous systems can enable drastic improvements in performance. A widely studied concept is all-autonomous, collision-free intersections, where vehicles arriving in a traffic intersection with no traffic light adjust their...

Safely crossing an intersection requires that drivers actively control their approach to the intersection with respect to characteristics of the flow of incoming traffic. To further our understanding of the perceptual-motor processes involved in this demanding manoeuvre, we designed a driving simulator experiment in which 13 participants actively negotiated intersections by passing through a ga...

The following terms are used when discussing traffic signal coordination: Phase – a predetermined set of traffic signal movements that operate concurrently. Cycle time – the total time taken to run once through all phases for an intersection. Offset – For coordinated traffic signals the beginning or end of the green period on the coordinated approach of each intersection is set to occur a given...

Traditional traffic control systems based on traffic light have achieved a great success in reducing the average delay of vehicles or in improving the traffic capacity. The main idea of these systems is based on the optimization of the cycle time, the phase sequence, and the phase duration. The right-of-ways are assigned to vehicles of one or several movements for a specific time. With the emer...

Recent advances in combining deep neural network architectures with reinforcement learning techniques have shown promising potential results in solving complex control problems with high dimensional state and action spaces. Inspired by these successes, in this paper, we build two kinds of reinforcement learning algorithms: deep policy-gradient and value-function based agents which can predict t...