01 A Cooperative Map Matching Algorithm Applied in Intelligent and Connected Vehicle Positioning
02 Indoor Sign-based Visual Localization Method
03 Intelligent Vehicles Localization Based on Semantic Map Representation from 3D Point Clouds
04 Companion Relationship Discovering Algorithm for Passengers in the Cruise Based on UWB Positioning
05 An Overview of Traffic Management in "Automatic+Manual" Driving Environment
06 An Image Generation Method for Automated Driving Based on Improved GAN
07 An Analysis of Injury Severities in School Bus Accidents Based on Random Parameter Logit Models
With the rapid advancement of autonomous driving technology, it has demonstrated tremendous potential in enhancing traffic efficiency and safety. However, the ethical issues it raises are becoming increasingly prominent, gradually emerging as a significant constraint to its widespread adoption. This paper aims to explore the core ethical dilemmas in the development of autonomous vehicles from the perspectives of moral philosophy and institutional governance. It focuses on three major areas: algorithmic ethics, social ethics, and legal regulation, covering key topics such as moral decision-making based on utilitarianism and deontology, mechanisms for attributing accident responsibility, and global and domestic legal responses. In terms of algorithmic ethics, utilitarian and deontological approaches, including collision algorithms and moral knobs, offer solutions for ethical conflicts. Regarding responsibility attribution, the traditional human-centered liability model is evolving into a chain-based framework encompassing all stakeholders engaged in designing, producing, and operating autonomous vehicles. As for legal regulation, current legal frameworks suffer from both applicability limitations and regulatory gaps, necessitating the construction of a legal framework that aligns with technological advancements. Future research may further deepen interdisciplinary collaboration and propose more practical solutions in areas such as ethical modeling, responsibility delineation, and institutional design, providing robust ethical support for the safe and sustainable deployment of autonomous vehicles at various levels of automation.
Amid accelerating globalization of international trade, container multimodal transport has emerged as the dominant mode of international cargo movement. Rising market diversification and technological innovations now drive transformative opportunities for container multimodal transport in China. To systematically summarize existing research, 475 Chinese and English articles (from 1st January 2000 to 10th July 2024) are retrieved from the China National Knowledge Infrastructure (CNKI) core database. Using CiteSpace visualization and literature synthesis, publication patterns, research status, key themes, and development trends are evaluated in China's container multimodal transport research. Key findings reveal four research domains: novel container designs, path optimization algorithms, green logistics systems, and digital platforms development. Critical challenges persist, including fragmented automation coverage, limited smart technology adoption, and inadequate algorithm validation in complex operational scenarios. Additional constraints involve underdeveloped green energy integration, incomplete carbon taxation frameworks, and cybersecurity risks in data-sharing platforms. Emerging trends highlight multidimensional innovation focusing on: AI-driven dynamic response systems for autonomous decision-making, adaptive algorithms for multi-scenario process optimization, blockchain-enabled smart contract solutions, and synergistic green energy-grid integration strategies, etc.
To optimize driving system's suspension structure of the inner axlebox bogie and improve service safety and reliability of the railway vehicles, a dynamics model of the inner axlebox vehicle considering driving and transmission system was established using the theories of gear dynamics and vehicle system dynamics and the multibody dynamics software SIMPACK. On the basis of the current driving system's suspension form of the bogie, three different suspension structures were proposed in this study. The proportion of traction motor mass allocated to primary unsprung and sprung under different driving system's suspension structures is analyzed. In addition, with the consideration of the internal and external excitation such as gear meshing and track random irregularity, and different driving system's suspension structures, this study investigates the dynamics characteristics such as the vibration responses of key components like traction motor, displacements of the coupling, dynamics forces at suspension points of driving system at different speeds, which revealed the effect of different driving system's suspension structures on dynamics performances of the inner axlebox bogie. The results show that the connecting rubber nodes between the gearbox and motor can limit their relative displacement and effectively protect the coupling. However, it also increases the transmission path of vibration from the wheel-rail surface to frame and driving system, leading to a significant increase in vibration levels of traction motor, frame, and other key components. In addition, reducing the number of rubber nodes between the gearbox and motor can decrease the mass of driving system allocated to the primary unsprung and the gearbox-axle joint vertical force. However, it would increase the vertical force on the motor suspension point and the gearbox rod joint. These results can provide a reference for the design of driving system's suspension structure of the inner axlebox power bogie.
In order to address critical challenges in intelligent driving systems, including insufficient dynamic interaction modeling, limited accuracy in multimodal trajectory prediction, and over-reliance on single physical metrics for collision risk quantification. A proactive collision risk assessment framework is proposed by integrating probabilistic quantification with multimodal trajectory prediction. For trajectory prediction, a hierarchical graph attention network is developed to capture dynamic environmental features through adaptive fusion of high-definition maps, lane geometries, and vehicle motion history. A sliding window-optimized decoder is introduced within the conventional two-stage prediction architecture to refine trajectory outputs. For risk assessment, a probabilistic collision quantification method is designed to calculate collision likelihood between ego and surrounding vehicles based on predicted trajectories. Results on the Argoverse dataset demonstrate state-of-the-art performance with minimum final displacement error (=0.785), average displacement error (=1.157), and miss rate (=0.126), achieving 1% and 15.1% error reduction in endpoint prediction compared to HiVT and LaneGCN respectively. simulation of urban mobility, SUMO simulations reveal 5% deviation between predicted and actual risks, with risk fluctuation amplitude reduced by 33.3% and 18.75% against time to collision (TTC) and dynamic safety index (DSI) methods. The proposed model shows enhanced stability in continuous driving scenarios (risk fluctuation=0.3) and demonstrates superior accuracy in forecasting potential collision risks through systematic integration of trajectory prediction and probabilistic analysis. These findings validate the framework's effectiveness in proactive safety warning for intelligent vehicles.
In vehicle accident detection, the imbalance between the small number of accident vehicles and the large number of normal vehicles can lead to difficulties in accurately identifying accident vehicles, increasing the risk of misclassifying them as normal vehicles. Therefore, a vehicle accident detection algorithm based on SMOTE-LSTM is proposed. To address the data imbalance between accident and normal samples, the synthetic minority over-sampling technique (SMOTE) is employed to randomly insert samples between accident data points, increasing their quantity and achieving data balance between the two categories. Furthermore, when oversampling accident data, the optimal number of neighbors is selected by comparing the detection accuracy under different neighbor counts to improve the recognition rate of accident samples while minimizing noise interference. On this basis, long short-term memory (LSTM) networks are employed to accurately capture the temporal features of data when vehicle accidents occur. Additionally, a Dropout layer is introduced to reduce overfitting and enhance the model's generalization ability, ensuring accurate accident detection. To minimize the misclassification of accident vehicles as normal, class weights are incorporated into the loss function, adjusting the weights to make the model more focused on accident sample detection. Finally, six groups of comparative experiments were conducted on a collected vehicle driving state time-series dataset. The first three groups did not use the SMOTE-LSTM-based algorithm, performing vehicle accident detection under balanced, mildly imbalanced, and moderately imbalanced conditions by increasing the number of normal samples. The latter three groups employ the SMOTE-LSTM-based algorithm to address mild, moderate, and severely imbalanced conditions. Experimental results show that, with the proposed method, the values of Precision, Recall, F1-score, G-mean, and AUC are significantly improved. Specifically, under mildly class imbalance, these five evaluation metrics increase by 56.2%, 2.5%, 38.7%, 5.8%, and 5.4%, respectively. Under moderate class imbalance, the improvements are 75%, 14.1%, 59%, 8.2%, and 7.8%. The results demonstrate that the proposed algorithm effectively addresses the class imbalance issue in vehicle accident detection, significantly enhancing all evaluation metrics. Particularly in mildly and moderately imbalanced scenarios, the algorithm effectively enhances the recognition ability of the minority class, exhibiting strong robustness and better classification performance.
Nighttime pedestrian-vehicle crashes exhibit significantly higher injury severity than daytime crashes due to visibility limitations and other factors. To accurately identify influencing factors, this study develops a hybrid model integrating a random parameters Logit model with heterogeneity in means and variances and a random forest (RF) algorithm based on SHapley Additive exPlanation (SHAP), i.e. RF-SHAP, using crash data from 2017 to 2022. The log-likelihood ratio test confirms temporal instability in the dataset, necessitating separate models for 2017—2019, 2020, 2021, and 2022 with calculated average marginal effects for significant variables. Results demonstrate that random effects exist for drinking pedestrians (2017—2019), ambulance required (2020), local street crashes (2021), and 48—56 km/h speed limits (2022), with their mean/variance influenced by traffic control and road classification. Drinking pedestrians, pedestrians aged over 45 to 60 years, driver injuries, vehicle types (pickup trucks and trucks), divided roadways, speed limits (32—40, 48—56, 64—72 km/h), weekends, and winter conditions have begun to exhibit statistically significant effects on nighttime pedestrian-vehicle crashes in recent years. In addition, the RF-SHAP algorithm quantifies heterogeneous contributions of all sub-variables within four random parameters to crash severity. Policy implications highlight three priorities: addressing pedestrian drinking behavior, enhancing nighttime crash prevention on expressways and arterial routes, and establishing appropriate speed limits while avoiding excessively high or low values.
To address the challenges in the route optimization of wind-assisted ships, namely insufficient quantification of wind energy utilization efficiency, limited accuracy in fuel consumption prediction, and lack of multi-objective coordinated optimization mechanism, this study proposes a multi-objective route optimization method integrating dynamic sail control with hybrid propulsion prediction. A dynamic sail control strategy model based on aerodynamic characteristics is developed to achieve spatial vector analysis of auxiliary thrust from sails. This model overcomes the limitations of conventional static angle-of-attack configurations by enabling real-time dynamic adjustment of sail parameters, thereby maintaining a high level of wind energy conversion efficiency. To resolve the dual constraints of poor environmental adaptability in traditional physical models and weak physical interpretability in data-driven approaches, a physics-constrained hierarchical artificial neural network architecture is constructed. This architecture establishes feature space bases using ship kinematic equations and employs attention-guided neural networks for residual learning. The proposed method preserves the underlying physical principles of energy consumption while enabling bidirectional coupling between data features and fluid dynamics equations. Validation on North Atlantic routes demonstrates that the proposed method reduces the mean absolute percentage error (MAPE) of fuel consumption prediction by 21.9% compared to purely physical models, while offering significantly enhanced inter-pretability over purely data-driven methods. Furthermore, a multi-objective optimization model incorporating both time costs and fuel consumption is established. A coordinated optimization algorithm combining non-dominated sorting genetic algorithm (NSGA-Ⅱ) and technique for order preference by similarity to ideal solution (TOPSIS) is developed, which improves the convergence rates of the non-dominated solution sets compared to standard algorithms. An empirical study conducted on the wind-assisted vessel"NEW ADEN"demonstrates that, during typical voyages in the North Atlantic, the effective operational efficiency of the sail is improved. Compared with the traditional recommended routes, the optimized route reduces voyage time by approximately 5%, fuel consumption costs and fixed costs by 9.1% and 4.95%, respectively, and total operational costs by over 7.2%. This optimization improves the economic benefits of wind-assisted ships while effectively reducing environmental pollution.
Journal of Transport Information and Safety
(Founded in 1983 bimonthly )
Former Name:Computer and Communications
Supervised by:Ministry of Education of P. R. CHINA
Sponsored by:Wuhan University of Technology
Network of Computer Application Information in Transportation
In Association With:Intelligent Transportation Committee of China Association of Artificial Intelligence
Editor-in-Chief:ZHONG Ming
Edited and Published by:Editorial Office of Transport Information and Safety
Address:No. 1178,Heping Avenue, Wuchang, Wuhan, CHINA
Postcode:430063
Tel:027-86580355
E-mail:jtjsj@vip.163.com
Website:http://www.jtxa.net/
Postal Code:38-94
Domestic Issue:
CN 42-1781/U
Publication No.:ISSN 1674-4861
- Chinese Core Journal in “Integrated Transportation” category
- Chinese Science Citation Database (CSCD)
- Core Science and Technology Journals
- Chinese Scientific and Technological Papers and Citations (CSTPCD)
- Class A of Research Center for Chinese Science Evaluation (RCCSE)
- Chinese Academic Journal Comprehensive Evaluation Database (CAJ-CED)
- Chinese Core Journals (Selection) Database
- Chinese Scientific and Technological Periodicals Database
- China National Knowledge Infrastructure (CNKI)
- Chinese Academic Journals (CAJ-CD)
- Chinese Lifelong Education Academic Research Database
- Japan Science and Technology Agency (JST)
- World Journal Clout Index Report (2020 STM)