Future Of Transportation Systems Research Articles

A novel hybrid Coyote–Particle Swarm Optimization Algorithm for three-dimensional constrained trajectory planning of Unmanned Aerial Vehicle

Unmanned Aerial Vehicles (UAVs) have been considered the future of transportation systems. However, mostly the reported optimizers struggle to estimate the flyable trajectories within acceptable accuracy and time bound under various constraints, particularly in a complex 3D environment. Therefore, this work proposes a novel hybrid optimizer (HCPSOA) by combining the Particle Swarm Optimization (PSO) and Coyote Optimization Algorithm (COA). Further, the chaotic logistic map and dynamic weight adjustments have been incorporated to enhance the exploration–exploitation capabilities. After validating the promising performance of HCPSOA against popular metaheuristics (COA, PSO, Improved COA, Glowworm Swarm Optimization, and Hybrid Fireworks PSO) for several benchmark functions, the proposed HCPSOA has been employed to estimate the flyable path by formulating a novel cost function and smoothened by cubic B-spline curve. The simulated results reveal that the HCPSOA provide a non-colliding path with up to 10.00% lesser average cost for the considered real world scenario (map 3), which confirms its supremacy for the estimation of the safe and flyable relative to other compared algorithms.

Electric Vehicle Charging Station Based on Photovoltaic Energy with or without the Support of a Fuel Cell–Electrolyzer Unit

The transport sector generates more than 35% of total CO2 emissions. Electric vehicles are the future of transportation systems, and the demand for electric vehicles has grown considerably in the last few years due to government support. Companies worldwide are investing heavily in electric car charging stations based on renewable energy. This research study presents a complete design (including an appropriate energy management strategy) for a photovoltaic energy-based electric vehicle charging station (EVCS) with or without the support of a fuel cell and electrolyzer system. The parameters considered for designing the necessary capacity of the battery pack to support the required load are relative to the location-specific solar radiation (using RETScreen® Clean Energy Management Software, Version 9.0, Government of Canada, Toronto, Canada), the efficiency of the solar panel, the used strategy, etc. The battery capacity in the EVCS design based on a power-following strategy is about 20 times smaller than that resulting in the reference design. Additionally, the cost for an EVCS design based on a power-following strategy is almost half that resulting in the reference design. An analysis of the power-following strategy was carried out according to three EVCS operating scenarios.

Exit transit control at objects of traffic attraction as a mobility service

The modern development of transport and road engineering is aimed at the design of transport systems. The sustainable development of territories cannot be imagined without the appropriate transport information content, which includes the services of intelligent transport systems. Management of transport demand and mobility based on a service approach is the future of transport systems, affecting the quality of society development. A conscious perspective of intelligent transport systems (ITS) projects is the development of mobility services. One of them is providing road users with information that encourages them to take a certain action, resulting in a spatial or temporal redirection of traffic flows. A specialized ITS subsystem that controls traffic near objects of traffic attraction by informing about the place of comfortable waiting for the exit and the time of comfortable departure from this object is understood as a system of motivational control of exit transit. The system under consideration is formed in order to prevent a decrease in the capacity of the road in the area of operation of this object and is not intended to reduce the total intensity of the traffic flow at the exit from the object. It provides only a temporary redistribution of exit flows of road users from the object of traffic attraction and the coordination of the moments of these exits in accordance with the current (and predicted) load level of the main highway. Delays of vehicles and the value of unsatisfied demand are taken as performance indicators.

Vision-Based Autonomous Vehicle Systems Based on Deep Learning: A Systematic Literature Review

In the past decade, autonomous vehicle systems (AVS) have advanced at an exponential rate, particularly due to improvements in artificial intelligence, which have had a significant impact on social as well as road safety and the future of transportation systems. However, the AVS is still far away from mass production because of the high cost of sensor fusion and a lack of combination of top-tier solutions to tackle uncertainty on roads. To reduce sensor dependency and to increase manufacturing along with enhancing research, deep learning-based approaches could be the best alternative for developing practical AVS. With this vision, in this systematic review paper, we broadly discussed the literature of deep learning for AVS from the past decade for real-life implementation in core fields. The systematic review on AVS implementing deep learning is categorized into several modules that cover activities including perception analysis (vehicle detection, traffic signs and light identification, pedestrian detection, lane and curve detection, road object localization, traffic scene analysis), decision making, end-to-end controlling and prediction, path and motion planning and augmented reality-based HUD, analyzing research works from 2011 to 2021 that focus on RGB camera vision. The literature is also analyzed for final representative outcomes as visualization in augmented reality-based head-up display (AR-HUD) with categories such as early warning, road markings for improved navigation and enhanced safety with overlapping on vehicles and pedestrians in extreme visual conditions to reduce collisions. The contribution of the literature review includes detailed analysis of current state-of-the-art deep learning methods that only rely on RGB camera vision rather than complex sensor fusion. It is expected to offer a pathway for the rapid development of cost-efficient and more secure practical autonomous vehicle systems.

Detection and Isolation of False Data Injection Attack in Intelligent Transportation System via Robust State Observer

As the future of transportation systems, the intelligent transportation system is a promising technology to improve the increasingly serious traffic problems. However, the integration of cyber-physical systems makes them vulnerable to new cyber–physical attacks. To ensure the security of intelligent transportation systems, a novel robust state observer-based detection and isolation method against false data injection attacks is developed. Based on the constructed dynamic model of intelligent vehicle networking, the covert characteristic of a false data injection attack is analyzed. Then, a novel state residuals-based detection criterion is developed by using a real-time observed state. To shorten the detection time, an adaptive detection threshold is designed to replace the existing computed threshold. In addition, robust state observer banks are established to isolate multiple injected attacks. Finally, simulation results on the vehicle networking system demonstrate the effectiveness of the developed detection and isolation method against false data injection attacks.

Comparing Localization Performance of IEEE 802.11p and LTE-V V2I Communications.

The future of transportation systems is going towards autonomous and assisted driving, aiming to reach full automation. There is huge focus on communication technologies expected to offer vehicular application services, of which most are location-based services. This paper provides a study on localization accuracy limits using vehicle-to-infrastructure communication channels provided by IEEE 802.11p and LTE-V, considering two different vehicular network designs. Real data measurements obtained on our highway testbed are used to model and simulate propagation channels, the position of base stations, and the route followed by the vehicle. Cramer–Rao lower bound, geometric dilution of precision, and least square error for time difference of arrival localization technique are investigated. Based on our analyses and findings, LTE-V outperforms IEEE 802.11p. However, it is apparent that providing larger signal bandwidth dedicated to localization, with network sites positioned at both sides of the highway, and considering the geometry between vehicle and network sites, improve vehicle localization accuracy.

Predict or prophesy? Issues and trade-offs in modelling long-term transport infrastructure demand and capacity

Effective planning and investment for transport infrastructure systems is seen as key for economic development in both advanced and developing economies. However, planning for such strategic transport investments is fraught with difficulties, due to their high costs and public profile, long asset life, and uncertainty over future transport demand patterns and technologies. Given that only a finite quantity of funding is available for transport investment, it is important that this funding is spent in the right places and on the right schemes in order to ensure that the best return is obtained from limited public resources. There is therefore a need for a model which is capable of assessing network demand and performance in a wide range of possible futures, in order that robust decisions can be taken with regard to which schemes are given the go ahead. This paper discusses a range of issues associated with the development of a strategic national transport model for Great Britain as part of a wider interdependent infrastructure systems modelling framework (NISMOD). It considers the compromises which have to be made in order to develop a model which can examine a wide range of potential futures in a reasonable timescale, outlines how such futures can be captured in the model, and finally assesses the continued role of planners and policy-makers in determining both how the model is applied and how the future of transport systems might play out in reality. While the paper is based on a case study example from Great Britain, most of the general issues discussed are of relevance to transport and infrastructure policy making in almost any national or international context.

Wired at Birth: Childhood, Technology Engagement, and Travel Behavior

The ongoing demographic transition from baby boomers to millennials and technology-fueled evolution of transportation bring to the fore key trends that will determine how the future of transportation systems will unfold. This paper examines the implications of such trends on travel behavior by quantifying the impacts of a technologically engaged childhood—generally attributed to millennials—and an increased use of technology during travel on travel behavior now and in the future. Results indicate that individuals who grew up with a stronger childhood technology experience are more likely to be technologically engaged as adults, have stronger pro-environmental attitudes, lower car dependence, and stronger interest in autonomous vehicles. The results also support a simultaneous relationship between technology use during travel and car dependence, which posits that individuals with lower car dependence (or availability) are more likely to use technology during travel. Emanating results put forward potential benefits of policy starting at the childhood level. The implications of this work will only gain importance as the interplay between technology and travel deepens and as a larger share of the adult population become “digital natives.”

The future of transportation systems

The future of transportation systems