Article
Computer Science, Information Systems
Yuming Wu, Lei Zhang, Ren Lou, Xinghua Li
Summary: The increasing number of vehicles has made traffic safety more complicated. Autonomous vehicles (AVs) have the potential to greatly reduce accidents. This study proposes a lane changing maneuver recognition model based on physical data and machine learning, achieving good results.
Article
Engineering, Industrial
Bekir Bartin, Kaan Ozbay, Chuan Xu
Summary: This paper presents the calibration and development process of safety performance function for undivided two-lane urban and suburban arterial segments in New Jersey. Various statistical models were generated and compared using likelihood ratio test, AIC, BIC, Vuong test, and rootograms. The results showed that the negative binomial and hurdle models exhibited better performance in terms of absolute residuals and absolute Pearson residual statistics.
Article
Green & Sustainable Science & Technology
Penghui Zhao, Jianxiao Ma, Chubo Xu, Chuwei Zhao, Zifan Ni
Summary: This study investigates the impact of left hard shoulders on the safety of vehicles traveling on multi-lane highways. By constructing a simulation model and analyzing conflict characteristics, it is found that setting left hard shoulders can significantly reduce traffic conflicts and improve safety levels on multi-lane freeways. The study also highlights the effectiveness of left hard shoulders in improving safety on one-way five-lane highways. The findings can help develop specifications for installing hard shoulders and enhance the safety of multi-lane highways.
Article
Engineering, Civil
Michael Williams, Anurag Pande, Marcial Lamera, Aleksandar Bauranov, Carole Voulgaris
Summary: This paper provides an observational before/after evaluation of the safety effects of edge-lane road (ELR) installations in the United States. The study finds that 8 out of 11 ELR sites experienced a reduction in crash experience, with a -44% overall crash reduction compared to the traditional two-lane two-way design. The comprehensive evaluation results should alleviate concerns about the safety of ELRs for automobile users.
JOURNAL OF TRANSPORTATION ENGINEERING PART A-SYSTEMS
(2022)
Article
Green & Sustainable Science & Technology
Brendan Lawrence, Brian Fildes, Peter Cairney, Stephanie Davy, Amir Sobhani
Summary: The study found that Raised Safety Platforms (RSPs) are an effective safety intervention to reduce speeds at major intersections and enhance road user safety.
Article
Green & Sustainable Science & Technology
Tanvir Uddin Chowdhury, Peter Y. Park, Kevin Gingerich
Summary: The length of an acceleration lane is an important parameter in freeway design. This study evaluated the impact of heavy commercial vehicle (HCV) platooning on acceleration lane length and found that the current length is inadequate for platooned vehicles. Extending the acceleration lane to 600 meters can improve safety and operational performance.
Article
Construction & Building Technology
H. R. Pasindu, R. K. T. K. Ranawaka, R. M. K. Sandamal, T. W. K. I. M. Dias
Summary: This study proposes a methodology to incorporate road safety performance in rural roads in maintenance planning using a multi-objective optimisation approach. The developed model has been demonstrated from the illustrative example of a rural road network, showing that roads with safety issues can also be prioritised in budget allocation.
INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING
(2021)
Article
Engineering, Civil
Zhensong Wei, Peng Hao, Matthew Barth, Kanok Boriboonsomsin
Summary: As the travel demand and the number of eligible vehicles for HOV lanes increase, the performance degradation of HOV lanes has become a more prevalent issue in many regions. In this study, the impact of adding a contraflow HOV lane was evaluated using traffic microsimulation. The evaluation results showed that the contraflow HOV lane design can significantly reduce traffic delay and increase the average speed of the currently degraded HOV lane.
TRANSPORTATION RESEARCH RECORD
(2023)
Article
Green & Sustainable Science & Technology
Salvatore Cafiso, Alessandro Di Graziano, Tullio Giuffre, Giuseppina Pappalardo, Alessandro Severino
Summary: According to international traffic statistics, the quantity of daily traveling vehicles is increasing and it is estimated to reach four billion by 2050. The increase in traffic flow has significant effects on the performance and safety of different roadway categories. The dynamic use of hard shoulder running (HSR) is considered a viable solution in urban ring roads, utilizing existing infrastructures and implementing smart digital roads to improve traffic outflow.
Article
Engineering, Civil
Liang Fan, Jinfen Zhang, Chengpeng Wan, Zhongliang Fu, Shiwei Shao
Summary: In recent years, the construction of lane-level road maps has gained significant attention for its importance in various research areas. This article proposes a two-stage method for modeling both the lateral and longitudinal trajectory distributions of roads based on vehicle lane-changing behavior. The method is verified using vehicle trajectory data and shows satisfactory results in constructing lane-level road information.
JOURNAL OF ADVANCED TRANSPORTATION
(2022)
Article
Ergonomics
Heesub Rim, Mohamed Abdel-Aty, Nada Mahmoud
Summary: This study develops Safety Performance Functions (SPFs) for freeway weaving segments, which are known for their higher crash probability due to multiple movements of traffic. Lane-level traffic data was utilized to analyze detailed traffic conditions and Poisson Lognormal (PLN) regression model technique was used to develop SPFs. The results found significant traffic parameters based on different crash types, providing important insights for safety evaluation and operational strategies on freeway weaving segments.
ACCIDENT ANALYSIS AND PREVENTION
(2023)
Article
Chemistry, Analytical
Baoguo Yu, Hongjuan Zhang, Wenzhuo Li, Chuang Qian, Bijun Li, Chaozhong Wu
Summary: Correctly estimating the ego-lane index is crucial for intelligent vehicles, especially in GNSS-challenged environments. This study proposes a novel approach utilizing a particle filter in urban scenarios, incorporating IMU, odometry, and lane-level map navigation. By utilizing LiDAR measurements for lateral particle shifts instead of importance weighting, the improved PF scheme achieves accurate ego-lane index estimation compared to traditional methods.
Article
Automation & Control Systems
Wonje Jang, Junhyuk Hyun, Jhonghyun An, Minho Cho, Euntai Kim
Summary: This paper proposes a method for lane-level road marking mapping using a monocular camera and develops the SeRM dataset for training and validation. The method utilizes a deep learning network for road marking segmentation and improves the lane-level map through loop-closure detection and graph optimization.
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2022)
Article
Computer Science, Information Systems
Mengyue Yuan, Peng Yue, Can Yang, Jian Li, Kai Yan, Chuanwei Cai, Chongshan Wan
Summary: This paper presents a method to generate lane-level road networks from high-precision trajectory data, addressing the challenges of lane merging and diverging. The proposed method outperforms existing methods in terms of completeness and fragmentation, especially in complex scenarios.
INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
(2023)
Article
Engineering, Electrical & Electronic
Jinlin Shi, Guannan Li, Liangchen Zhou, Guonian Lu
Summary: With the advancement of autonomous driving technologies, road network data have attracted attention as a virtual source of information. Lane-level road networks have become a research focus due to the inability of traditional node-arc road networks to meet the demands of high-precision location awareness. Street-view pictures are a popular data source for building lane-level road networks due to the significant quantity of road information they provide. However, conflicts and overlaps arise when projecting street-view picture results into geographic space.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)