Bulletin Board
Highlights
Spatio-temporal differential memory attention model for traffic flow prediction, CAO Chunjie, et al.
2026-03-09 Top“Four chains””collaborative empowerment: a strategy research forhigh-quality development of the low-altitude economy throughmulti-path integration, LI Jun.
2025-09-18 TopLow-altitude trajectory planning for aircraft considering RAIM availability undercomplex terrain conditions, TANG Xinmin, et al.
more..Analysis of the impact of in-vehicle information system interaction task complexity on drivers' cognitive load and behavioral performance
GAO Ya;FENG Zhongxiang;LI Jingyu;[Background] In recent years, in-vehicle information systems(IVIS) have rapidly become popular in the commercial vehicle market. This touchscreen-based human-machine interaction system enhances the level of information visualization and simultaneously introduces the non-negligible issue of driver distraction, posing a potential threat to driving safety. [Objective] This study aimed to explore the effects of interaction task complexity and demographic parameters on drivers' cognitive load and behavioral performance when interacting with IVIS interfaces. [Method] A within-and between-subject repeated measures experimental design was employed by recruiting 60 drivers for a driving simulator experiment. The effects of different independent variables on drivers' fixation allocation, steering entropy, vehicle speed, task completion time, and subjective and objective cognitive loads were explored using generalized estimating equations and their post hoc tests, and the drivers' fixation behaviors while interacting with the IVIS interface were visualized using Python software. [Result] Tasks with high complexity led to distraction, poorer driving performance(i.e., increased steering entropy and operation completion time), and subjective and objective cognitive loads also tended to increase. The average vehicle speed of male drivers was 9.45 km/h higher than that of females. Additionally, drivers in the older age group(41-60 years old) had a higher risk-perceiving ability, even though the task operation completion time was longer. [Application] In conclusion, the study findings can provide guidance for the optimization of IVIS interaction and personalized human-machine interaction(HMI) design for future intelligent vehicles, and improve HMI reliability.
Modeling and analysis of traffic flow safety in highway diverging zones within connected and autonomous environment
ZHANG Jian;ZHANG Zhishun;XU Ting;LAI Xinhe;JI Hangxu;[Background] Diverging zones are critical components of highway systems and act as traffic bottlenecks that significantly affect the overall safety and capacity of highway networks. [Objective] To examine the safety characteristics of traffic flows in diverging highway zones, a heterogeneous traffic flow model was developed that incorporates driver heterogeneity and driving intentions within a connected and autonomous environment. [Method] First, the characteristics of heterogeneous traffic flow in diverging zones of highways were analyzed to model the behaviors of various vehicle types. Driver heterogeneity was factored in to accurately calibrate these behavioral models.Next, the composition of the heterogeneous traffic flow was examined, accounting for variations in driver behavior and intentions, to construct a comprehensive heterogeneous traffic flow model. Finally, simulation experiments were conducted using the time exposed to collision, time-integrated time to collision, and time-exposed modified time to collision as evaluation metrics. These experiments analyzed the impact of intelligent connected vehicle(ICV) penetration rates, driver heterogeneity,and diverging ratios on the heterogeneous traffic safety of the diverging zone of highways. [Conclusion] The results indicate that a high penetration rate of ICVs in highway diverging zones significantly improves heterogeneous traffic safety, although the extent of this improvement is limited during periods of heavy traffic. A greater proportion of aggressive human-driven vehicles may, to some extent, contribute to improved heterogeneous traffic safety within the diverging zone at higher vehicle speeds. Additionally, a lower diverging ratio positively influences the heterogeneous traffic safety enhancement in these areas. [Application] This study provides theoretical support for the research and analysis of highway traffic safety in connected and autonomous environments and offers a scientific basis for the management of highway diverging zones by traffic management departments.
Evaluation of driving behavior regulation and safety benefits based of multi-level visual guidance at tunnel entrances
ZHOU Hongzhuo;SUN Wenpeng;WANG Yunxiao;BEI Runzhao;LYU Nengchao;[Objective] To improve the smoothness of driving behavior and traffic safety levels at tunnel entrances, an improved solution was developed based on a multilevel visual guidance concept.Field experiments with real vehicles were conducted to evaluate its effectiveness and quantify its comprehensive safety benefits during the day and night. [Method] Field experiments were performed both during the day and at night in two tunnels. One tunnel was equipped with the proposed solution, whereas the other used the solution specified in current standards and served as the control group. A driving behavior evaluation system for the tunnel entrance zone was developed by statistically analyzing the regulatory effects of the solution on behavior and exploring its regulatory mechanisms. Subsequently, the comprehensive safety benefits during the day and night were evaluated using factor analysis and the entropy weight method. [Result] The scheme significantly improved driving behavior by inducing 62.98% and 55.57% earlier tunnel detection in the day and night, respectively, while significantly reducing lateral avoidance maneuvers(83.27%/79.95% reduction in portal avoidance and 41.38%/37.94% reduction in sidewall avoidance during daytime/nighttime, respectively). This intervention significantly increased trajectory gradient by 4.02 times(daytime) and 3.68 times(nighttime), with deceleration initiated 54.67%(daytime) and 45.41%(nighttime) earlier with smoother execution. Comprehensive safety evaluation scores demonstrated the hierarchy: 0.96(post-implementation nighttime) > 0.12(post-implementation daytime) >-0.28(baseline nighttime) >-0.80(baseline daytime). [Conclusion] Regardless of the time, the tunnel entrance improvement solution based on the multi-level visual guidance concept prompted earlier driver perception and reaction, promoted smoother driving behavior, and significantly improved safety benefits. [Application] This study provides a paradigm for the design and evaluation of the effectiveness of visual guidance schemes in similar high-risk traffic scenarios.
Modeling of lateral takeover control behavior in conditional automated driving environment
ZHANG Junjie;MA Yongfeng;ZHANG Ziyu;KANG Kai;HU Buyu;[Background] In conditional automated driving, human drivers must take over when the system capability boundaries are reached. However, control instability and delayed responses often occur during the early takeover phase, compromising vehicle safety and efficiency of human-machine coordination. [Objective] This study aims to characterize drivers' control recovery and environmental adaptation during takeovers, and to identify the key factors influencing takeover stability. [Method] A Carla-based driving simulation platform was developed to construct a fog-zone takeover scenario, and the information about participants' driving behavior, eye-tracking data, and subjective evaluations were collected. The sliding-window sample entropy(SW-SampEn) method was used to capture the control dynamics, from which two temporal indicators, takeover instability duration(TID) and environmental adaptation duration(EAD), were defined. A dual-Weibull accelerated failure time(AFT) model incorporating clustered heterogeneity and gamma frailty was developed to model the lateral takeover control behavior and stability characteristics of drivers. [Result]The results demonstrate that takeover control exhibits a “disruption-adaptation-stabilization” pattern of evolution. Synchronized traffic flow significantly prolongs both TID and EAD, while interrupted secondary tasks shorten the recovery time. Driving style, gender, experience, and trust in automation significantly affect takeover stability. [Application] The proposed analytical framework provides methodological support and quantitative insights for takeover stability assessment, strategy design, and optimization of human-machine coordination, offering theoretical and practical references for safety management and control strategy development in complex automated driving environments.
Analysis of multi-factor superposition effects and characteristics in highway traffic risk
HUANG Lei;GUO Miao;YAO Ying;QIN Yaqin;SU Yuxin;[Background]The interrelationships among multiple risk factors during the occurrence of traffic accidents are highly complex. When multiple risk factors superposition simultaneously, a “superposition effect” is formed owing to the interactions among elements, which increases the complexity of traffic accident risk assessment. [Objective] To analyze the overlapping relationships among the influencing factors of traffic accident risk, this study proposed a superposition model to evaluate different dynamic traffic risk factors with the aim of identifying the superposition effects among multidimensional risk factors. [Method] First, dynamic traffic risk sources were quantified and standardized. Then, based on the relationship between the volatility of the risk series identified by the generalized autoregressive conditional heteroskedasticity(GARCH) model and value at risk(VaR), a GARCH-VaR model was constructed. The interactions among the different risk factors were analyzed by evaluating the VaR sequences of each risk. [Data] By collecting data on traffic volume,inner-lane speed, inter-lane speed difference, temperature, precipitation, daily maximum wind speed,daily average wind speed, visibility, and traffic accidents from certain highway sections, a multidimensional dynamic risk database was established to ensure data diversity. [Result] The results indicated that when conducting a superimposed risk assessment, the superimposed effects among various risk factors were relatively complex. The magnitude of risk did not necessarily increase with the number of superimposed risk factors; the relationship between them was not a simple linear one but rather exhibited certain synergistic or offsetting dynamics. [Application] In conclusion, with regards to road traffic accident risk management, comprehensive risk management measures should be developed for different superposition scenarios by considering the complex relationships among risk factors, so as to improve the level of road traffic safety.
About Journal
Founded in 2003, Bimonthly
Competent Authority：Ministry of Education of PRC
Sponsor：Southwest Jiaotong University
Editor in Chief： LIU Xiaobo; HE Zhengbing
E-mail：jtt@swjtu.edu.cn
ISSN ：1672-4747
CN ：51-1652/U
Impact Factor: 3.245
Category Ranking: 7/169
Quartile: Q1
Indexed
CSTPCD
Scopus
RCCSE
JST
CSTJ
CNKI
COJ
Tracking the information about your manuscript
Communicate with the editorial office
Query manuscript payment status Peer ReviewCollecting, editing, reviewing and other affairs offices
Managing manuscripts
Managing author information and external review Expert Information Office WorkOnline Review
Online Communication with the Editorial Department