Abstract: With the continuous growth of the demand for container transportation, the proportion of container trucks passing through ports and surrounding roads has increased significantly. Due to their large size and poor maneuverability, once a truck accident occurs, it is often accompanied by serious casualties and property losses. Current research on traffic conflicts for container trucks is limited by the lack of high-quality data: first, publicly available container truck trajectory datasets are extremely rare; second, although drones have the ability to collect data over a large range, their shooting data have problems such as limited accuracy and discontinuous trajectories, which make it difficult to meet the high requirements of micro-modeling for data quality. This problem directly restricts the accuracy of conflict prediction and the credibility of causal analysis. To improve the accuracy and completeness of trajectory data, we introduce a trajectory reconstruction method to repair and complete the original trajectory. The experimental results show that the reconstructed trajectory is significantly better than the original data in terms of continuity and rationality. On this basis, a two-dimensional time to collision (2D-TTC) indicator was constructed to identify side-swipe conflict events, and based on the extraction of micro-behavior features, sample sets of side-swipe and rear-end conflicts were constructed, and a variety of machine learning models were introduced to carry out conflict prediction analysis. The results show that the gradient boosting decision tree (GBDT) model performs best in side-swipe conflict prediction, and the extreme gradient boosting (XGBoost) model in rear-end conflict prediction. By introducing the Shapley additive explanation (SHAP) method to improve the interpretability of the model, our analysis shows that the key factors influencing side-swipe conflict are the lateral speed and the average longitudinal speed within 5 s. The lateral speed reflects the lateral deviation of the vehicle, and the average longitudinal speed within 5 s reflects the driving stability and acceleration trend in a short time. The two together determine the lateral controllability of the vehicle in the dynamic process. Rear-end conflict is affected mainly by the change in longitudinal acceleration, revealing the instability of the vehicle during braking and the lack of control over the distance between the vehicle and the preceding vehicle. Finally, the model performance was optimized through feature ablation experiments, where, in the prediction of side-swipe conflicts, the GBDT achieved an accuracy of 0.911 and an area under the receiver operating characteristic curve (AUC) of 0.953.

基于轨迹重构数据的集装箱卡车横向风险预测及影响因素分析

[1]AhnS, VadlamaniS, LavalJ, 2013. A method to account for non-steady state conditions in measuring traffic hysteresis. Transportation Research Part C: Emerging Technologies, 34:138-147.

[2]AnderssonJAE, GillisJ, HornG, et al., 2019. CasADi: a software framework for nonlinear optimization and optimal control. Mathematical Programming Computation, 11(1):1-36.

[3]BarmpounakisE, GeroliminisN, 2020. On the new era of urban traffic monitoring with massive drone data: the pneuma large-scale field experiment. Transportation Research Part C: Emerging Technologies, 111:50-71.

[4]BradleyAP, 1997. The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recognition, 30(7):1145-1159.

[5]ChenAY, ChiuYL, HsiehMH, et al., 2020. Conflict analytics through the vehicle safety space in mixed traffic flows using UAV image sequences. Transportation Research Part C: Emerging Technologies, 119:102744.

[6]ChenTQ, GuestrinC, 2016. XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, p.785-794.

[7]FriedmanJH, 2001. Greedy function approximation: a gradient boosting machine. The Annals of Statistics, 29(5):1189-1232.

[8]GuX, Abdel-AtyM, XiangQJ, et al., 2019. Utilizing UAV video data for in-depth analysis of drivers’ crash risk at interchange merging areas. Accident Analysis & Prevention, 123:159-169.

[9]HaywardJC, 1972. Near miss determination through use of a scale of danger. Highway Research Record, 384:24-34.

[10]HeJC, PengB, FengZY, et al., 2024. A Gaussian mixture unscented Rauch–Tung–Striebel smoothing framework for trajectory reconstruction. IEEE Transactions on Industrial Informatics, 20(5):7481-7491.

[11]HouJ, ListGF, GuoXC, 2014. New algorithms for computing the time-to-collision in freeway traffic simulation models. Computational Intelligence and Neuroscience, 2014(1):761047.

[12]HouKN, ZouJ, ZhengFF, et al., 2024. On the precise quantification of the impact of a single discretionary lane change on surrounding traffic. arXiv:2407.18557.

[13]HuXW, ZhengZD, ChenDJ, et al., 2022. Processing, assessing, and enhancing the Waymo autonomous vehicle open dataset for driving behavior research. Transportation Research Part C: Emerging Technologies, 134:103490.

[14]HuYP, LiY, HuangHL, et al., 2022. A high-resolution trajectory data driven method for real-time evaluation of traffic safety. Accident Analysis & Prevention, 165:106503.

[15]IslamZ, Abdel-AtyM, 2023. Traffic conflict prediction using connected vehicle data. Analytic Methods in Accident Research, 39:100275.

[16]JansenRJ, VarottoSF, 2022. Caught in the blind spot of a truck: a choice model on driver glance behavior towards cyclists at intersections. Accident Analysis & Prevention, 174:106759.

[17]JiQ, LyuH, YangH, et al., 2023. Bifurcation control of solid angle car-following model through a time-delay feedback method. Journal of Zhejiang University-SCIENCE A, 24(9):828-840.

[18]JiaoYR, CalvertSC, van CranenburghS, et al., 2025. A unified probabilistic approach to traffic conflict detection. Analytic Methods in Accident Research, 45:100369.

[19]KatrakazasC, QuddusM, ChenWH, 2018. A simulation study of predicting real-time conflict-prone traffic conditions. IEEE Transactions on Intelligent Transportation Systems, 19(10):3196-3207.

[20]KrajewskiR, BockJ, KloekerL, et al., 2018. The highD dataset: a drone dataset of naturalistic vehicle trajectories on German highways for validation of highly automated driving systems. 2018 21st International Conference on Intelligent Transportation Systems (ITSC), p.2118-2125.

[21]LiGF, YangYF, LiS, et al., 2022. Decision making of autonomous vehicles in lane change scenarios: deep reinforcement learning approaches with risk awareness. Transportation Research Part C: Emerging Technologies, 134:103452.

[22]LiJQ, ChengRJ, 2025. A real-time adaptive signal control method for multi-intersections in mixed connected vehicle environments. Journal of Zhejiang University-SCIENCE A, 26(8):801-810.

[23]LiJQ, WangXS, YangXH, et al., 2024. Analyzing freeway safety influencing factors using the CatBoost model and interpretable machine-learning framework, SHAP. Transportation Research Record, 2678(7):563-574.

[24]LiLY, LyuH, WangT, et al., 2024. STdi4DMPC: distributed model predictive control for connected and automated truck platoon with mixed traffic flow based on spatiotemporal trajectory prediction. IEEE Transactions on Vehicular Technology, 73(10):14563-14579.

[25]LiP, Abdel-AtyM, CaiQ, et al., 2020. The application of novel connected vehicles emulated data on real-time crash potential prediction for arterials. Accident Analysis & Prevention, 144:105658.

[26]LiuMQ, ZhaoJ, HoogendoornS, et al., 2022. A single-layer approach for joint optimization of traffic signals and cooperative vehicle trajectories at isolated intersections. Transportation Research Part C: Emerging Technologies, 134:103459.

[27]LundbergSM, LeeSI, 2017. A unified approach to interpreting model predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems, p.4768-4777.

[28]MartinezJJ, Canudas-de-WitC, 2007. A safe longitudinal control for adaptive cruise control and stop-and-go scenarios. IEEE Transactions on Control Systems Technology, 15(2):246-258.

[29]MohammadianS, HaqueMM, ZhengZD, et al., 2021. Integrating safety into the fundamental relations of freeway traffic flows: a conflict-based safety assessment framework. Analytic Methods in Accident Research, 32:100187.

[30]MontaninoM, PunzoV, 2015. Trajectory data reconstruction and simulation-based validation against macroscopic traffic patterns. Transportation Research Part B: Methodological, 80:82-106.

[31]OrsiniF, GeccheleG, RossiR, et al., 2021. A conflict-based approach for real-time road safety analysis: comparative evaluation with crash-based models. Accident Analysis & Prevention, 161:106382.

[32]OuyangPY, GuoYY, LiuP, et al., 2025. An approach for evaluating traffic safety of expressway weaving segments: investigating risk patterns of lane-changing conflicts. Journal of Transportation Safety & Security, 17(2):125-157.

[33]PengZP, ZuoJP, JiH, et al., 2024. A comparative analysis of risk factors in taxi-related crashes using XGBoost and SHAP. International Journal of Injury Control and Safety Promotion, 31(3):508-520.

[34]Rafati FardM, Shariat MohaymanyA, ShahriM, 2017. A new methodology for vehicle trajectory reconstruction based on wavelet analysis. Transportation Research Part C: Emerging Technologies, 74:150-167.

[35]RibeiroMT, SinghS, GuestrinC, 2016. “Why should I trust you?”: explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, p.1135-1144.

[36]SafavianSR, LandgrebeD, 1991. A survey of decision tree classifier methodology. IEEE Transactions on Systems, Man, and Cybernetics, 21(3):660-674.

[37]ShahanaA, VedagiriP, 2024. Developing rear-end and side-swipe conflict prediction models for urban signalized intersections under disordered traffic conditions. IATSS Research, 48(1):1-13.

[38]ShawkyM, AlsobkyA, Al SobkyA, et al., 2023. Traffic safety assessment for roundabout intersections using drone photography and conflict technique. Ain Shams Engineering Journal, 14(6):102115.

[39]ThiemannC, TreiberM, KestingA, 2008. Estimating acceleration and lane-changing dynamics from next generation simulation trajectory data. Transportation Research Record, 2088(1):90-101.

[40]TianJF, ZhangHM, TreiberM, et al., 2019. On the role of speed adaptation and spacing indifference in traffic instability: evidence from car-following experiments and its stochastic model. Transportation Research Part B: Methodological, 129:334-350.

[41]TianZQ, ChenFC, MaSQ, et al., 2024. Analysis of the severity of heavy truck traffic accidents under different road conditions. Applied Sciences, 14(22):10751.

[42]VapnikVN, 1995. The Nature of Statistical Learning Theory. Springer, New York, USA.

[43]VenthuruthiyilSP, ChunchuM, 2022. Anticipated collision time (ACT): a two-dimensional surrogate safety indicator for trajectory-based proactive safety assessment. Transportation Research Part C: Emerging Technologies, 139:103655.

[44]WächterA, BieglerLT, 2006. On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming. Mathematical Programming, 106(1):25-57.

[45]WangC, XuCC, DaiYL, 2019. A crash prediction method based on bivariate extreme value theory and video-based vehicle trajectory data. Accident Analysis & Prevention, 123:365-373.

[46]WardJR, AgamennoniG, WorrallS, et al., 2015. Extending time to collision for probabilistic reasoning in general traffic scenarios. Transportation Research Part C: Emerging Technologies, 51:66-82.

[47]WuFY, SternRE, CuiSM, et al., 2019. Tracking vehicle trajectories and fuel rates in phantom traffic jams: methodology and data. Transportation Research Part C: Emerging Technologies, 99:82-109.

[48]XieK, YangD, OzbayK, et al., 2019. Use of real-world connected vehicle data in identifying high-risk locations based on a new surrogate safety measure. Accident Analysis & Prevention, 125:311-319.

[49]XingL, HeJ, Abdel-AtyM, et al., 2019. Examining traffic conflicts of up Stream toll plaza area using vehicles’ trajectory data. Accident Analysis & Prevention, 125:174-187.

[50]XingL, HeJ, LiY, et al., 2020. Comparison of different models for evaluating vehicle collision risks at upstream diverging area of toll plaza. Accident Analysis & Prevention, 135:105343.

[51]YaoRY, ZengWL, ChenYH, et al., 2021. A deep learning framework for modelling left-turning vehicle behaviour considering diagonal-crossing motorcycle conflicts at mixed-flow intersections. Transportation Research Part C: Emerging Technologies, 132:103415.

[52]YuanC, LiY, HuangHL, et al., 2022. Using traffic flow characteristics to predict real-time conflict risk: a novel method for trajectory data analysis. Analytic Methods in Accident Research, 35:100217.

[53]ZakiMH, SayedT, ShaabanK, 2014. Use of drivers’ jerk profiles in computer vision-based traffic safety evaluations. Transportation Research Record, 2434(1):103-112.

[54]ZhaoJ, MaRM, WangM, 2024a. A behaviourally underpinned approach for two-dimensional vehicular trajectory reconstruction with constrained optimal control. Transportation Research Part C: Emerging Technologies, 159:104489.

[55]ZhaoJ, YangXL, ZhangC, 2024b. Vehicle trajectory reconstruction for intersections: an integrated wavelet transform and Savitzky-Golay filter approach. Transportmetrica A: Transport Science, 20(2):2163207.

[56]ZhengL, HuZL, SayedT, 2023. Traffic conflict prediction at signal cycle level using Bayesian optimized machine learning approaches. Transportation Research Record, 2677(5):183-195.

[57]ZhengO, Abdel-AtyM, YueLSS, et al., 2024. CitySim: a drone-based vehicle trajectory dataset for safety-oriented research and digital twins. Transportation Research Record: Journal of the Transportation Research Board, 2678(4):606-621.

[58]ZhouMF, QuXB, LiXP, 2017. A recurrent neural network based microscopic car following model to predict traffic oscillation. Transportation Research Part C: Emerging Technologies, 84:245-264.

[59]ZhuZH, MengY, ChengRJ, 2025. Container truck high-risk events prediction and its influencing factors analyses based on trajectory data. Systems, 13(5):326.