IET Intelligent Transport Systems最新文献

In recent years, Vehicular Ad-hoc Network (VANET) has become an essential component of intelligent transportation systems that, along with the previous systems such as traffic condition, accident alert, automatic parking, and cruise control, use the communication of vehicle to vehicle and vehicle to the roadside unit to facilitate road transportation. Several challenges hinder efforts to improve traffic conditions and reduce traffic fatalities through VANET. A critical challenge is achieving highly accurate and reliable vehicle localization within the VANET. Additionally, the frequent unavailability of Global Positioning System (GPS), particularly in tunnels and parking lots, presents another significant obstacle. Traditional methods like Dead Reckoning offer low accuracy and reliability due to accumulating errors. Similarly, GPS positioning, map matching with mobile phone location services, and other existing solutions struggle with accuracy and economic feasibility. In this article, two Kalman filter approaches are used based on signal statistical information and the other learning-based networks, including traditional neural network, deep neural network and LSTM (long short-term memory) to locate the car. The prediction error of car position with root mean square measures. The squared error and distance prediction error are evaluated. It is shown that in terms of prediction time and processing time of vehicle localization, all the vehicle localization methods are efficient in terms of response time for localization, and Kalman filter methods, traditional neural network and deep neural network are faster than LSTM method. Also, in terms of localization error, Kalman filter works better than learning-based methods, and in learning-based methods, both deep neural network and LSTM methods perform better than traditional neural network in terms of localization error.

While existing literature has focused on modelling pedestrian movement on platforms, there is a lack of understanding of passengers' perceptions, motivations, and influential factors that shape their on-board behaviours and choices. This study developed a conceptual framework to assess passengers' post-boarding behaviours and perceptions, specifically focusing on their actions and choices inside the train carriages. The conceptual framework was tested through survey data of 429 passengers in Melbourne, Australia. The result shows that door access is the most influential factor when passengers choose where to stand or sit on board, followed by comfort, safety, privacy, and random factors. Furthermore, the study explores the relationship between the post-boarding behaviour variables and travellers’ personal and trip characteristic variables. The analysis shows that carrying large items has a more significant effect on many post-boarding behaviour variables. Gender, age group, travel frequency, waiting time, and carrying small items also play significant roles. However, variables such as travel time and frequency of group travel have lesser effects. These novel findings offer valuable insights, laying the groundwork for future modelling activities. Moreover, the understanding derived from passenger perceptions can guide transport agencies and operators in shaping strategies to improve onboard services.

Efficient control of traffic signals for vehicles and pedestrians at intersections is critical for relieving traffic congestion. Considering the unique characteristics of intersections, such as the number of roads, the presence or absence of crosswalks, road geometric shapes, and traffic demand patterns, an appropriate phase sequence and duration for traffic signals must be established at each intersection. This paper proposes a simulation-based two-stage algorithm comprising integer-constrained Adam (ICA) and tabu search (TS) to optimize the phase sequence and duration for arbitrary intersections with arbitrary traffic-demand patterns. The ICA promptly identifies a promising region in which a global optimal solution is likely to be obtained, whereas TS determines the best solution near the region. The performance of the proposed algorithm that optimizes phase durations with fixed phase sequence is evaluated against several baseline methods using 24 instances across six actual intersections. Experimental results show that the proposed algorithm reduces the average travel time by 20.2% compared with existing traffic signals within a computation time of 4 min, thus providing a near-optimal solution eight times faster than commonly used population-based metaheuristics. Furthermore, the algorithm demonstrates robust performance across heterogeneous vehicles and recommends the best phase sequence that effectively alleviates congestion in current traffic signal systems. The optimized phase sequence with best phase durations further reduces the average travel time by approximately 11.3% compared with the existing phase sequence with best phase durations at an actual intersection. To facilitate its widespread use, a free, open web-service system named “Smart Intersection for Traffic Efficiency” is developed, which enables users to optimize traffic signal systems without requiring optimization background or simulation knowledge.

The behavioural differences between autonomous vehicles (AVs) and human-driven vehicles (HDVs) can significantly impact traffic efficiency, safety, and emissions. Simulation-based impact assessments using microscopic traffic models often modify car-following (CF) and lane-changing (LC) configurations to differentiate AVs from HDVs. Typically, researchers adjust CF model parameters to replicate AV driving behaviour, but these assumptions can lead to varying conclusions on AV impacts. The scope of each study (e.g., freeways, highways, urban links, intersections) also influences the outcomes. This research conducts an impact assessment utilizing optimized AV driving behavior rather than assumptions on a city network level (Munich) using a simulation-based platform. The particle swarm optimization (PSO) algorithm is used to calibrate the base model and run simulation experiments under various penetration rates (PRs) and demand scenarios. Results show significant safety improvements throughout the network under higher PRs, while lower PRs might lead to deteriorating safety. At 100% AV PR, the total number of conflicts decreased by around 25% compared to a fully HDV environment. Considering AVs' sensing capabilities, additional safety improvements are found in almost any AV PR. However, AVs might not improve traffic efficiency; in some cases, they may slightly increase average network travel time, though this change is minimal.

Under low-light imaging conditions, visual scenes captured by intelligent waterborne transportation systems often suffer from low-intensity illumination and noise corruption. The visual quality degradation would lead to negative effects in maritime surveillance, e.g., vessel detection, positioning and tracking, etc. To restore the low-light images, we develop an effective visibility enhancement method, which contains a coarse-to-fine framework of spatially-smooth illumination estimation. In particular, the refined illumination is effectively generated by optimizing a novel structure-preserving variational model on the coarse version, estimated through the Max-RGB method. The proposed variational model has the capacity of suppressing the textural details while preserving the main structures in the refined illumination map. To further boost imaging performance, the refined illumination is adjusted through the Gamma correction to increase brightness in dark regions. We then estimate the refined reflection map by implementing the joint denoising and detail boosting strategies on the original reflection. In this work, the original reflection is yielded by dividing the input image using the refined illumination. We finally produce the enhanced image by multiplying the adjusted illumination and the refined reflection. Experiments on synthetic and realistic datasets illustrate that our method can achieve comparable results to the state-of-the-art techniques under different imaging conditions.

Aiming at the power supply scheme (PSS) of the on-board supercapacitor-powered tram, considering the cost and margin of the PSS, a two-stage method is designed to optimize the layout of the charging stations and the configuration of the supercapacitor (SC). First, the SC-powered tram model and stable cycle operation model are established, and a two-stage optimization problem model with the lowest PSS cost and the largest SC margin is established. Then, an improved dual-population differential evolution algorithm is designed, and the layout of charging stations and the configuration of SC are co-optimized in the first stage, and then the layout of charging stations is optimized again in the second stage. The simulation results show that co-optimization can obtain a lower cost of PSS, and furthermore, the layout of charging stations can be optimized again to effectively improve the margin of SC, thereby improving the matching degree between the layout of charging stations and the connection scheme of SC.

Crashes between cars and powered two-wheelers (PTWs: motorcycles, scooters, and e-bikes) are a safety concern; as a result, developing car safety systems that protect PTW riders is essential. While the pre-crash protection system automated emergency braking (AEB) has been shown to avoid and mitigate injuries for car-to-car, car-to-cyclist, and car-to-pedestrian crashes, much is still unknown about its effectiveness in car-to-PTW crashes. Further, the characteristics of the crashes that remain after the introduction of such systems in traffic are also largely unknown. This study estimates the crash avoidance and injury risk reduction performance of six different PTW-AEB algorithms that were virtually applied to reconstructed car-to-PTW pre-crash kinematics extracted from a Chinese in-depth crash database. Five of the algorithms include combinations of drivers’ and PTW riders’ comfort zone boundaries for braking and steering, while the sixth is a traditional AEB. Results show that the average safety performance of the algorithms using only the driver's comfort zone boundaries is higher than that of the traditional AEB algorithm. All algorithms resulted in similar distributions of impact speed and impact locations, which means that in-crash protection systems likely can be made less complex, not having to consider differences in AEB algorithm design among car manufacturers.

The fundamental diagram (FD) of traffic flow can effectively characterize the macroscopic characteristics of traffic flow and provide a theoretical foundation for traffic planning and control. The rapid development of connected vehicles (CVs) has led to changes in traffic flow characteristics. However, research on the FD of traffic flow involving CVs and non-connected vehicles (NCVs) is still in its early stages. Most FDs do not well characterize the motion behaviour of different vehicles, nor do they study the interaction between mixed vehicles. Therefore, in this study, the FD of mixed traffic flows (i.e. with CVs and NCVs) was constructed within a unified framework. First, the car-following behaviours of CVs and NCVs were modelled based on risk potential field theory. Subsequently, the FD of mixed traffic flows was derived based on the relationship between car-following behaviour and the macroscopic traffic flow under steady-state conditions. To validate the model, rigorous verifications were conducted via numerical experiments using the Monte Carlo method. The results indicate significant agreement between the scatter plots obtained from the experiments and the theoretical curves for different penetration rates. The proposed FD has a unified framework and a more rigorous mathematical structure.

With the development of artificial intelligence, the application of unmanned ground vehicles (UGV) in outdoor hazardous scenarios has received more attention. However, the terrains in these environments are often complex and undulating, which also pose higher challenges to the multi-UGV path planning and task assignment (MUPPTA) optimization. To efficiently improve the multi-UGV collaboration in 3D environments, a MUPPTA method is proposed based on double deep Q learning network (DDQN) and ant colony optimization (ACO) to jointly optimize the path planning and task assignment decisions of multiple UGVs. The authors first comprehensively consider the characteristics of the 3D environments, and model the MUPPTA problem as a combinatorial optimization problem. To tackle it, the original problem is decomposed into the multi-UGV path planning sub-problem and task assignment sub-problem, and solve them separately. First, the path planning sub-problem in the 3D environments is transformed into a Markov decision process (MDP) model, and a multi-UGV path planning algorithm based on DDQN (MUPP-DDQN) is proposed to obtain the optimal paths and actual path costs between tasks through extensive offline learning and training. Based on this, a multi-UGV task assignment algorithm is further proposed based on ACO (MUTA-ACO) to solve the task assignment sub-problem and achieve the optimal task assignment solution. Simulation results show that the proposed method is more cost-effective and time-saving compared to other comparison algorithms.