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
The approach aims to uncover the relationship between dynamic traffic parameters and traffic conflict incidents and it further supports proactive safety control. The highD database is utilized to create sample data in 3-minute intervals, extracting 23 features related to traffic flow and road section characteristics. Based on the post encroachment time(PET)indicator, different thresholds are set to classify the severity of conflicts during car-following and lane-changing scenarios. The random forest regression(RFR)method is used to select the most critical features, while feature matrix to gray image(FM2GI)technology converts the sample data into grayscale images to enable 2D convolution to extract image features. Three encoder-decoder models, convolutional neural networks (CNN), C-RFR, and C-SVR are compared with baseline models (back propagation neural network (BPNN), RFR, and support vector regression(SVR). The results indicated that: based on two key features(the number of vehicles entering and exiting the road section)and five effective features(average headway, time occupancy, average driving speed of passenger cars, lane change rate, and variance of exit speeds), the CNN, C-RFR, and C-SVR models within the encoder-decoder framework outperformed the baseline models. Specifically, root mean squared error(RMSE)reduced by 12. 6%, 31. 6%, and 18. 5%, respectively, enabling real-time prediction of traffic conflicts. Among them, CNN exhibited the lowest prediction error and demonstrated strong robustness in predicting traffic conflicts of varying severities, along with low sensitivity to two key parameters. The CNN, C-RFR, and C-SVR models, utilizing FM2GI technology and 2D convolution encoding, expand the deep learning framework for traffic conflict prediction modeling, and achieve reliable predictions for multiple severities of highway traffic conflicts in basic road segments.
The study focuses on a model for identifying critical road links based on path redundancy in road networks. Path redundancy enhances efficiency for daily travel and provides crucial alternative routes during emergency situations. This model comprehensively considers time-varying factors in the road system, including origin-destination (OD) demand, OD pair, and road congestion. By analyzing time-varying factors for each period, the path redundancy of the road network is calculated. Furthermore, combining the weights of each period with their corresponding path redundancy yields the expected value of path redundancy, facilitating accurate identification of critical links. To address the computational challenge of solving for large-scale path redundancy, a reconstruction of the urban road network structure is performed, enabling the use of maximum flow and minimum cost flow algorithms, which have polynomial time complexity, for iterative solutions. The effectiveness and applicability of the model and algorithm are verified through practical application in the Pinglu Canal bridge reconstruction project. Results reveal the impact of the bridge group's removal and reconstruction on the redundancy of the road network in Qinzhou. Changes in OD pair path redundancy are highlighted, providing a basis for refined traffic management measures before and after construction. In terms of computational efficiency, the proposed algorithm shows a significant advantage over Gurobi. The computation time improves by 17.90 times, demonstrating its suitability for large-scale urban road networks. This paper can be targeted to enhance the resilience of key road sections, thereby contributing to the construction of a more resilient urban road transport system.
Aiming at the problem that the fixed-point detection method cannot effectively monitor the formation and evolution of the mobile bottleneck, a real-time detection method of the mobile bottleneck on the expressway based on intelligent networked vehicles is studied. A wavelet analysis-based method is proposed to reduce the errors of trajectories collected by intelligent connected vehicles (ICVs). And then the key points that represent the change of traffic states are identified based on the relationship between the vehicle trajectories and the traffic states. Considering that multiple traffic congestions may simultaneously occur on a road segment, an algorithm is proposed to classify the key points based on the space-time characteristics of traffic shockwaves. Finally, the traffic shockwave speed is calculated, and moving bottlenecks are identified and evaluated. Based on SUMO simulation platform, experiments are carried out on the detection effect of mobile bottleneck location, propagation speed and queuing delay under the proportion of various intelligent vehicles in Hujia freeway. The results show that when the penetration rate of ICVs is less than 10%, the accuracy of traffic wave speed estimation improves by an average of 20% after trajectory denoising. When the penetration rate exceeds 3%, the estimation error of the moving bottleneck propagation speed is below 0.42 m/s. When the penetration rate reaches 7%, the estimated position of the moving bottleneck has a deviation mostly within 10 m, with a maximum of 25 m. The proposed method can detect the presence of freeway bottlenecks which occur randomly and evaluate their severity in real-time.
Car following and lane changing are important research directions in traffic flow theory, and the factors involved in lane changing behavior are more complex than following. The current analysis of lane-changing characteristics based on foreign public trajectory datasets can hardly cover the lane-changing behavior characteristics in line with Chinese drivers, and at the same time, most of the domestic and foreign dataset collection sources are concentrated on highways, which does not consider the influence of different road types on the characteristics of lane-changing behavior. In order to study the characteristics of vehicle lane-changing behavior on typical urban roads in China, an unmanned aerial vehicle(UAV)was used to photograph the traffic flow on the straight section of the urban expressway in Wuhan, to obtain the natural driving data in line with the characteristics of urban roads and drivers in China, and to perform lane-changing identification and parameter extraction on the dataset. The video captured by the UAV contains 8 609 small vehicles, and based on whether the lane number where the vehicle is located changes and the number of changes as the recognition standard for lane-changing vehicles, a total of 6 897 vehicle trajectory data are extracted from the following vehicles(no change in the lane number where the vehicle is located), and 1 712 single lane-changing vehicle trajectory data are extracted(the lane number where the vehicle is located changes only once). Based on the extracted trajectory data of the following vehicles, obtain the average speed of the road traffic flow and the average distance between the following vehicles, so as to analyze the real-time operation state of the traffic flow; based on the extracted trajectory data of the single lane-changing vehicles, adopt a fixed time window as the basis for judging the starting and ending points of the lane-changing, and on this basis, obtain the longitudinal displacement of the vehicle changing the lane and the distance between it and the neighbor vehicles when the lane-changing is started, and the safety of lane-changing behavior is analyzed by combining with the real-time operation state of the traffic flow. The safety analysis of lane-changing behavior is carried out by combining the real-time operation status of traffic flow. Through the distribution fitting and statistical analysis of the obtained traffic parameters of following and lane changing, the results show that the average value of road traffic speed is 19.257 1 m/s, the average value of vehicle following distance is 45.910 7 m, the average value of vehicle longitudinal displacement is 115.515 m, and the distribution of the distance between the vehicle and peripheral cars at the time of lane changing is in line with the lognormal distribution. Among them, the average value of the lane change vehicle time distance from the vehicle in front of the target lane is significantly higher than the average value of the vehicle time distance from the vehicle in front of the initial lane. It is also found that some drivers still choose to change lanes when the distance from the rear vehicle in the target lane is small, which reflects the aggressive driving of some drivers. This study can provide a reference for analyzing the characteristics of lane-changing on urban expressways in China and developing a lane-changing behavior model suitable for Chinese traffic characteristics.
The runway and taxiway scheduling of large hub airports has not yet formed a cascade operation mode, leading to the inability to achieve coordinated planning and reasonable scheduling of cross-domain and heterogeneous flight flows under limited capacity of airports. This paper studies a bi-layer coordinated optimization scheduling method of runway and taxiway for arriving and departing flights in the airfield area. In the runway scheduling stage, a joint arriving and departing scheduling model of multi runways considering the cost of runway changing is proposed, which quantifies and minimizes the cost of unimpeded taxiing time for flights that change runways, and suppresses the extra taxiing time generated as far as possible while ensuring the minimum cumulative delays on runways. In the taxiway scheduling stage, a surface taxiing scheduling model is developed by minimizing the deviation between the total cumulative taxiing time of flights and the expected departure time of runway scheduling, which is used to plan the timing and sorting of arriving and departing flights at each metering point. Finally, a closed-loop mechanism of feedback-revision is adopted to prevent the mismatch in bi-layer coordinated optimization scheduling. Simulation and verification are conducted by taking Shuangliu International Airport and Tianfu International Airport in Chengdu as scenarios. The results show that runway delay time of single aircraft is reduced by 16.9 s and the cumulative flight taxiing time is reduced by 14.27% on average after the first iteration comparing to the first-come-first-served strategy, and that a matching scheduling plan can be found within 1.35 iterations on average if the closed-loop mechanism of feedback-revision is adopted. Meanwhile, the performance of 3 different types of bi-layer coordinated optimization scheduling strategies is analyzed. The method proposed in this paper is helpful to promote the technology system of comprehensive coordinated management for arrival, departure and surface, and to the formation of refined control capabilities of the airfield traffic flows with a digitally-drive core.
Since Chinese government proposes the strategies of peak carbon emissions and carbon neutral, the greening level of transportation system gets huge attentions. As a part of the road transportation system, the studies about greening level for infrastructures of road transportation is rare. To this end, this paper proposes a hybrid method of factor analysis and best-worst scaling to identify and weight the corresponding evaluation indexes. This method considers the correlation between evaluation indexes and evaluation object to avoid the subjective bias caused in the index selection. Specifically, 11 evaluation indexes are selected from the literature. A survey is conducted to collect opinions of experts that from industry, academic community and government toward these indexes. Next, factor analysis technique is adopted to explore the relationship between these indexes and green level of road transportation infrastructures based on the experts' rating information, which finds that the indexes of reliability and importance are less relevant, and other indexes can be constructed into a single factor called Index Relevance. Further, an improved best-worst scaling method is proposed combing the factor analysis technique to calculate index weights. The validity of the proposed method is verified by comparing to the traditional best-worst scaling method. Next, the improved method is adopted to calculate the weights of these evaluation indexes based on the factor Index Relevance and best-worst choice data. The evaluation indexes in top 3/4 of weights in sequence are (based on the results of 95% quantile of factor score): energy self-consistency (1.000), clean energy (0.702), refuse disposal (0.651), air pollution (0.589), intelligence (0.332), material use (0.324), virescence (0.303), and land use (0.277). The proposed method can contribute to the selection and weight calculation of greening-level indexes for infrastructures of road transportation and also contribute to the development of corresponding evaluation system.
Since China proposed the"carbon peak and carbon neutrality"goals in September 2020, green transformation and development in road transportation have become pressing. Utilizing clean energy along freeways to create self-consistent micro-network systems and integrating transportation with energy are vital for reducing carbon emissions and achieving clean energy usage in transportation. This paper focuses on independent transportation micro-networks in remote western regions of China, where are featured by abundant solar and water resources but limited access to the main power grid. It proposes a photovoltaic complementary system framework based on small hydropower and establishes a planning model for a self-consistent micro-network system for road transportation. Moreover, the paper proposes a control and operation strategy for the complementary system, with small hydropower as the main source and photovoltaics as an auxiliary source. By optimizing the system economy and stability of power supply, the particle swarm optimization (PSO) algorithm is used to solve typical cases and conduct a comparative analysis of different schemes, resulting in a recommended planning scheme for a self-consistent micro-network system of road transportation. The research results indicate that: under the complementary scheme, the stable power supply rate can reach 99.64%; the overall annual cost is reduced by 430 500 CNY and the power shortage rate is reduced by 2.5% comparing to a single photovoltaic power supply scheme; the overall annual cost increases by only 15 300 CNY but the system's power shortage rate is reduced by 1.59% comparing to a single small hydropower station supply scheme. These results validate the effectiveness of the proposed planning model for the complementary and self-consistent micro-network system and provide a reference for subsequent engineering practices.
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)