Taking a vacant parking lot in crowded metropolitan areas is a major problem especially with the huge number of vehicles. In this study, the authors provide a vision-based system for real-time management of parking spaces in the case of outdoor parking. Different real-world challenges may face these systems such as weather conditions, luminance variation, perspective distortion and inter-spaces occlusion. In this study, they propose a decisional module based on a tracking approach that determines in real time the state of the parking lots and localises the vacant parking spaces according to several extracted attributes. This decision is based on local characteristics of the parking spaces as well as the performed vehicles’ events.

This study presents a novel approach to the road traffic prediction using single multilayer perceptrons and their ensemble. Networks were trained on the basis of real-world data from the intelligent transportation system Wroclaw. This system is installed in one of the largest cities in Poland. First, a number of neural networks were created, each of which was concurrently able to predict the state of traffic on a number of major intersections located in different parts of the city. Then the multilayer perceptrons were made, which predict the numbers of vehicles passing through selected intersections using the information about previous situations at other intersections. Furthermore, an ensemble method, which combine output values of multiple neural networks, were applied. In the worst case, mean absolute percentage error did not exceed 12.6%, even in cases when traffic prediction was based only on information from other intersections.

The most common mode for en-route public traveller information is dynamic message signs (DMSs). Despite their effectiveness, they are costly and limited in the amount of information they can deliver. The wide availability of smart mobile devices and communication technologies offers possibilities to provide traveller information not only through in-vehicle devices without incurring huge infrastructure costs, but also in a more flexible manner to selected individuals and at specific locations without geographical constraints. This study proposed the concept of virtual DMSs (VDMSs) to improve public traveller information provision. In order to evaluate the effectiveness of such systems, the study first prototyped a smartphone-based VDMS application and conducted a focused group user experience survey, which revealed a positive attitude towards VDMS in terms of both usefulness and satisfaction. Second, a driving simulator study was conducted to analyse two other critical aspects of VDMS, message comprehension and driver distraction. Results revealed that VDMS generally performs better than DMS across different amounts of information provision and under different driving conditions regardless of driver age. It is recommended that transportation agencies give full consideration to VDMS as a future strategy for delivering public traffic information in a connected vehicle environment.

In railway planning, the timetabling step needs, as input, the train running times, which are calculated from a train dynamic model. Usually, this model determines the most energy-efficient train trajectory for a predefined time. However, this time may not correspond to the timetable-makers’ needs. They should have the choice among a set of solutions, more or less energy-consuming. This study proposes a method capable of producing a set of alternative running times with the associated mechanical energy required. To this end, the authors’ contribution is to set up an efficient evolutionary multi-objective algorithm builds a set of well-spread and diversified solutions which approximate a Pareto front. The solutions are all compromises between running time and energy-consumption, the two minimisation objectives concurrently optimised. Given that an evolutionary algorithm is strongly dependent on the initialisation phase, the efficiency of the algorithm is improved through a specific and original mechanism connecting multiple initialisations in cascade in order to accelerate the convergence towards the best solutions. A set of results obtained on randomly-generated instances is analysed and discussed.

In this study, the authors refine a route-planning algorithm, in order to improve the route planning strategy in urban areas under traffic congestion. Considering the Oil Consumption Weight (OCW) and route planning methods, they propose an OCW-Dijkstra algorithm. In the algorithm, the parameters concerning the vehicle and driving environment, such as distance, speed, driving time, idling time, travel flow, driving oil consumption and idling oil consumption, are used for producing the OCW with weighted calculation in each section of the journey. In the execution of the algorithm, an adjacency matrix of the OCW is first generated by loading segment description, regional routing and the point information in an urban map. After the initial point and the destination point are selected, the optimal route is planned and generated automatically. In addition, the algorithm has self-learning methods, which can update the parameters and the OCW in real time. From the results of simulating experiments and the comparison with exhaustive algorithm, they find that the OCW-Dijkstra algorithm performs more effectively and robustly, which consequently saves driving time, as well as decreases oil consumption.

Platoon formation of highway vehicles has the potential to significantly enhance road safety, improve highway utility, and increase traffic efficiency. However, various uncertainties and disturbances that are present in real-world driving conditions make the implementation of vehicular platoon a challenging problem. This study presents an H-infinity control method for a platoon of heterogeneous vehicles with uncertain vehicle dynamics and uniform communication delay. The requirements of string stability, robustness and tracking performance are systematically measured by the H-infinity norm, and explicitly satisfied by casting into the linear fractional transformation format. A delay-dependent linear matrix inequality is derived to numerically solve the distributed controllers for each vehicle. The performances of the controlled platoon are theoretically analysed by using a delay-dependent Lyapunov function which includes a linear quadratic function of states during the delay period. Simulations with a platoon of heterogeneous vehicles are conducted to demonstrate the effectiveness of the proposed method under random parameters and external disturbances.