IET Intelligent Transport Systems最新文献

The optimization of the total passenger travel time and total train energy consumption are critical factors in metro operation optimization. However, deriving an optimal train operation plan that incorporates both passenger travel time and total train energy consumption is a complex task because it should consider numerous variables representing the operational status of the urban railway, such as the number of boarding and alighting passengers, number of on-board passengers in each train, and entire train operation status along the line. Moreover, owing to the fluctuating nature of passenger demand, which can change rapidly over time, its optimization becomes challenging. To address this challenge, this study develops a recurrent neural network-based real-time metro operation optimization model trained using data representing the moments when the trains departed from the stations. These data are derived and reconstructed from various simulated operation plans while searching for optimal daily metro timetable. Consequently, the proposed model derives the real-time optimal operation strategies for trains departing from the next station within an average of 0.18 s. The result of metro operation simulations using proposed optimal operation strategies reveals a 7–14% improvement in efficiency compared to the current train operation strategies.

This paper considers the real-time spatio-temporal electric vehicle charging navigation problem in a dynamic environment by utilizing a shortest path-based reinforcement learning approach. In a data sharing system including transportation network, an electric vehicle (EV) and EV charging stations (EVCSs), it is aimed to determine the most convenient EVCS and the optimal path for reducing the travel, charging and waiting costs. To estimate the waiting times at EVCSs, Gaussian process regression algorithm is integrated using a real-time dataset comprising of state-of-charge and arrival-departure times of EVs. The optimization problem is modelled as a Markov decision process with unknown transition probability to overcome the uncertainties arising from time-varying variables. A recently proposed on-policy actor–critic method, phasic policy gradient (PPG) which extends the proximal policy optimization algorithm with an auxiliary optimization phase to improve training by distilling features from the critic to the actor network, is used to make EVCS decisions on the network where EV travels through the optimal path from origin node to EVCS by considering dynamic traffic conditions, unit value of EV owner and time-of-use charging price. Three case studies are carried out for 24 nodes Sioux-Falls benchmark network. It is shown that phasic policy gradient achieves an average of 9% better reward compared to proximal policy optimization and the total time decreases by 7–10% when EV owner cost is considered.

In accordance with the current European railway regulations and particularly the two directives relating to the interoperability (Directive (EU) 2016/797) and safety (Directive (EU) 2016/798) of the railway system, this literature review proposes to classify artificial intelligence (AI) applications by distinguishing the structural elements (Infrastructure, Energy, Control-Command-Signalling and Rolling Stock) and the functional elements (Operation and Traffic Management, Maintenance and Telematics Applications) of the European railway system. Several “classic” AI techniques are implemented, including machine learning (supervised, semi-supervised, unsupervised), deep learning such as artificial neural networks (ANN), natural language processing (NLP), case-based reasoning (CBR), etc. However, the inadequacy of these approaches to capitalize, share and reuse the knowledge involved has oriented research towards the development of new approaches based on ontologies and knowledge graphs. This study shows that the stages of data acquisition, modeling, processing and interpretation pose a crucial problem in rail transport. In addition, with complex models described as “black boxes”, it is difficult to understand how the internal reasoning mechanisms of the AI system impact the solution and predictions. The new explainable AI (XAI) approach can possibly provide an element of response to this problem.

This paper proposes a longitudinal controller for the mixed vehicle platoon in the presence of driver response time-delay and communication time-delay based on the pinning consensus of heterogeneous multi-agent system. Firstly, an adaptive pinning consensus control protocol and derive sufficient conditions for the heterogeneous non-linear multi-agent system are designed to achieve pinning consistency. Then, the heterogeneous characteristics of the vehicle are described based on the car-following model, then the mixed vehicle platoon system model is constructed and a mixed vehicle platoon controller based on heterogeneous multi-agent pinning consensus is proposed. Besides, the driver response time-delay and communication time-delay are introduced into the model, and a controller based on time-delay heterogeneous multi-agent pinning consensus is designed. Finally, the effectiveness of the proposed controller is verified by numerical simulations, and the effect of number of connected autonomous vehicle, different types of vehicle order, driver response time-delay, communication time-delay and the parameter of the controller on stability of mixed vehicle platoon is also quantitatively demonstrated.

The rapid and uncontrolled urbanization of cities in developing countries has engendered a plethora of urban mobility issues, including traffic congestion, accidents, and air pollution. To address these challenges, contemporary urban mobility trends are incorporating innovative technologies and sustainable governance practices. This article investigates how urban managers can leverage the opportunities presented by cost-effective technologies and the management of urban data to enhance urban mobility in developing countries. Within this discourse, an RSU-based approach is proposed that employs motorbike taxis for inter-vehicular communication, given their status as the most widely used form of public transportation. This approach substantially diminishes investment costs and reinforces the sustainability of urban mobility. Through the implementation of this solution, a noteworthy reduction is anticipated in the emission of gases such as CO2, and NOx, known contributors to climate change and various respiratory diseases. To validate the efficacy of the proposed solution, four distinct scenarios are scrutinized in a case study centered on the city of Douala in Cameroon, utilizing tools such as OMNET++, SUMO, Veins, and INET. The proposed framework offers significant benefits in terms of environmental sustainability and operational efficiency. It enables a 10% reduction in CO2 emissions, a 15% reduction in NOx emissions, an 11% drop in fuel consumption, and a 15% reduction in waiting time in traffic jams. The envisaged solution aims to aid urban managers in their decision-making processes, specifically in advancing sustainable urban mobility. Through the adoption of this approach, cities in developing countries can mitigate challenges associated with urban mobility and enhance the overall well-being of their residents.

Boosting the rail freight modal share is an ambitious target in Europe and North America. Yards, where freight trains are arranged, can be crucial in realizing this target by reliable dispatching to the network. This paper predicts freight train departures by developing a simulation-assisted machine learning model with two concepts: general (adding all predictors at once) and step-wise (adding predictors as they become available in sub-yard operations) for hump yards with the conventional layout to provide a generalized model for European and North American contexts. The developed model is a decision tree algorithm, validated via 10-fold cross-validation. The model's performance on three data sets—a real-world European yard, a baseline simulation, and an ultimate randomness simulation for a comparable North American yard—shows a respective $�R^2$ of 0.90, 0.87, and 0.70. Step-wise inclusion of the predictors results differently for the real-world and simulation data. The global feature importance highlights maximum planned length, departure weekday, the number of arriving trains, and minimum arrival deviation as key predictors for the real-world data. For the simulation data, the most significant predictors are departure yard predictors, the number of arriving trains, and the maximum hump duration. Additionally, utilization rates—except for the receiving yard—enhance the predictions.

Multispectral pedestrian detection with visible light and infrared images is robust to changes in lighting conditions and therefore is of great importance to numerous applications that require all-day environmental perception. This paper proposes a novel method named FCE-RCNN, which integrates saliency detection as a sub-task and utilizes global information for enhanced feature representation. The approach enhances thermal inputs by incorporating gradients at the raw-data level before feature extraction. Utilizing a dual-stream backbone, a global semantic information extraction module is introduced that combines pooling with horizontal–vertical attention mechanisms, capturing high-quality global semantic information for lower-level feature enrichment and guidance. Additionally, the pedestrian locality enhancement module is designed to enhance spatial locality information of pedestrians through saliency detection. Furthermore, to alleviate the challenges posed by positional shifts between cross-spectral features, deformable convolution is innovatively employed. Experimental results on the KAIST dataset demonstrate that FCE-RCNN significantly improves nighttime detection, achieving a log-average miss rate of 6.92%, outperforming the new method ICAFusion by 0.93%. These results underscore the effectiveness of FCE-RCNN, and the method also maintains competitive inference speed, making it suitable for real-time applications.

Advances in real-time basic safety message (BSM) data from sensor-equipped vehicles have created new opportunities for driving risk assessments. This paper presents a machine learning approach using BSM data to provide fine-grained risk assessments, focusing on safety-critical events (SCEs) related to driving profiles, vehicle states, and road conditions. This approach formulates a bi-level risk indicator: one level measures the observable frequency of SCEs, while the other estimates their likelihood. The coarse level calculates risk scores by classifying driving profiles as normal or risky based on SCE frequency. The fine level refines these scores by comparing normal and risky profiles using key features from a feature learning model. This combined system accounts for recent driving behaviours and road/weather conditions within a vehicle-to-everything (V2X) environment, addressing high data dimensionality and imbalance. A comprehensive case study using 1 year of data from pilot V2X infrastructure in Tampa, Florida, demonstrates the efficacy of this approach, showing practical applications of the SCE-based risk indicator and combinatorial feature learning while also highlighting the real-world utility of the assessment method in providing a detailed and actionable view of driving risk based on V2X information.

The analysis of people's daily activities has played a crucial role in various applications, such as urban geography, activity prediction, and homogeneous population detection. However, limited studies have explored changes in the residents’ activity patterns in a particular region across various periods. To explore the changes, a methodological framework of sequence visualization analysis based on machine learning that extracts the activity patterns across various periods using sequence analysis, visualizes the activity patterns by calculating the frequency of different activities at time points and categorizes them through graphical similarity, and then compares the activity patterns in terms of activity and demographic characteristics is proposed. Empirical testing on the New York Metropolitan data of the National Household Travel Survey (NHTS) is conducted for 2001, 2009, and 2017. The findings reveal significant intra-similarities, inter-differences, and distinct changes in activity patterns across three periods for different social populations in the New York Metropolitan. From the perspective of information analysis, this work is anticipated to enhance the understanding of travel needs for diverse social populations in a particular region, thereby facilitating targeted policy adjustments for the departments concerned.

Intelligent Transportation Systems (ITS) are crucial for developing fully automated vehicles. While significant progress has been made with advanced driver assistance systems and automation technology, challenges remain, such as improving traffic information, enhancing planning and control systems, and developing better decision-making capabilities. Despite these hurdles, the potential benefits of ITS are so many that its challenges have attracted substantial industrial investment and research groups interested in the automated driving field. In this work, a methodology based on state space search for planning knowledge integration is proposed. The main goal of the proposal is to provide a planning system with the necessary information to perform properly any task related to lateral and longitudinal control, path following, trajectory generation, arbitration and behavior execution by localizing the vehicle with respect to a high-level road plan. To this end, this research compares cutting-edge methods for rapidly finding the K nearest neighbor in relatively high dimensional road plans constructed from the traffic information stored in a high definition map. During the experimentation phase, promising real-time results have been obtained for fast KNN algorithms, leading to a robust tree index-based methodology for decision making in self-driving vehicles combining path planning, trajectory tracking, trajectory creation, knowledge aggregation and precise vehicle control.