With the advancement of autonomous driving technology, trajectory prediction has become a critical task for ensuring traffic safety and intelligent decision-making. Existing motion forecasting models suffer from HD (High-Definition) map dependency, leading to high costs and poor adaptability. Furthermore, their accuracy sharply declines when maps are unavailable, motivating research into map-free alternatives. However, map-free models typically exhibit lower accuracy. To address this issue, we propose a universal enhancement framework that employs trajectory-map contrastive learning, utilizing a trajectory-to-map encoder to extract implicit map representations from raw trajectories, thereby improving performance. Extensive experiments on the Argoverse dataset demonstrate that, after incorporating our trajectory-to-map encoder into map-free models, the average minADE and minFDE are improved by 2.7% and 3.5%, respectively. These results underscore our method’s robustness and generalizability in enhancing map-free models, confirming the efficacy of implicit map representation learning and offering a promising solution for HD-map-free autonomous driving in dynamic open-road environments.

Ensuring the resilience of deep learning algorithms against adversarial attacks during edge-cloud data transmission between edge and cloud systems is crucial. Although significant strides have been made in enhancing the accuracy of hazardous driving scenario detection in autonomous vehicles, bolstering the robustness against adversarial attacks during data transfer and model recognition remains an urgent challenge. In this paper, we propose a novel approach to enhance adversarial robustness and maintain high accuracy in benign data. Using a lightweight CNN model, we detect hazardous driving scenarios, while a generative adversarial network generates decision boundary samples from original scenario images. These samples are incorporated into adversarial training, preventing overfitting on adversarial examples. Experimental results show our approach achieves robust accuracy (AUC) of 0.83 and 0.66 under FGSM and PGD attacks, surpassing vanilla adversarial training and TRADES methods with improving the standard accuracy (AUC) on benign samples by 0.22 and 0.12 relatively. Our proposed method advances beyond current adversarial training techniques to significantly enhance the model’s resilience to adversarial attacks during edge-cloud data transmission phases and minimize the loss of standard accuracy simultaneously. This advancement is crucial in enhancing the capability to correctly detect a wider range of hazardous driving scenarios, thereby providing significant support for the secure deployment of autonomous vehicles in edge-cloud collaborative environments.

Crash risk evaluation studies mainly established the relationship between the macro traffic status and crashes. However, the impact of risky driving behavior, a significant factor in crashes, has not been thoroughly investigated due to the data collection limitations of fixed detectors. In this study, the risky driving behavior data generated by Connected Vehicle (CV) techniques was introduced along with traffic flow data to develop the crash risk evaluation model. An LSTM + Transformer approach was developed, in which the Transformer could extract the non-aggregated spatial-temporal features of risky driving behaviors and LSTM learn the temporal patterns of traffic flow. An ensemble layer was proposed to integrate the macro traffic status features and micro driving behavior, and automatically fit their weights to optimize crash risk evaluation performance. Data from a Chinese freeway was used for empirical analysis. The results show that the proposed LSTM + Transformer model achieved high model accuracy (77.7%), recall (68.6%), and AUC (0.785), with average improvement of between 5.34%, 15.69%, and 5.97%, respectively, compared to existing LSTM, XGBoost, SVM and Logistic Regression (LR) models. Moreover, utilizing risky driving behavior data by incorporating the macro traffic status has proved to capture the pre-crash traffic flow turbulence more precisely. The model results explained by SHapley Additive exPlanations (SHAP) reveal that higher frequency, longer duration and greater acceleration of risky braking behavior increase the number of road vehicles affected, thereby heightening the crash risks. These findings could help the deployment of proactive traffic management and target CV control strategies to reduce crashes.

Interactive decision-making between multiple automated vehicles under unsigned intersections is a high-level dynamic decision-making scenario, greatly increasing the complexity of decision-making. In this situation, making the decision-making manner in accordance with the logic of human and guaranteeing driving safety is technically challenging. A multi-factor-enabled interactive decision-making method is proposed in this paper to realize such behavior, which employs multiple complementary factors and switchable modes in a dynamic game. More specifically, these factors are driving performance requirements, e.g., moving safety, smoothness comfort, fast passing, and surrounding space, as well as diversified driving styles suitable for different driver groups. Meanwhile, to improve the reasonability of automated driving and reduce the complexity of multi-vehicle games, switchable game modes are established to realize the dynamic adjustment mechanism. The effectiveness of the proposed method in resolving conflicts in a continuous interactive way is verified through extensive simulations. The results indicate the proposed method can reflect the interaction process between multi-agents, and improve compliance between intelligent decision-making and the logic of human.

Real-time crash risk prediction models aim to identify pre-crash conditions as part of active traffic safety management. However, traditional models which were mainly developed through matched case-control sampling have been criticised due to their biased estimations. In this study, the state-of-art class balancing method known as the Wasserstein Generative Adversarial Network (WGAN) was introduced to address the class imbalance problem in the model development. An extremely imbalanced dataset consisted of 257 crashes and over 10 million non-crash cases from M1 Motorway in United Kingdom for 2017 was then utilized to evaluate the proposed method. The real-time crash prediction model was developed by employing Deep Neural Network (DNN) and Logistic Regression (LR). Crash predictions were performed under different crash to non-crash ratios where synthetic crashes were generated by Wasserstein Generative Adversarial Network (WGAN), Synthetic Minority Over-sampling Technique (SMOTE) and Adaptive Synthetic (ADASYN) sampling respectively. Comparisons were then made with algorithmic-level class balancing methods such as cost-sensitive learning and ensemble methods. Our findings suggest that WGAN clearly outperforms other oversampling methods in terms of handling the extremely imbalanced sample and the DNN model subsequently produces a crash prediction sensitivity of about 70% with a 5% false alarm rate. Based on the findings of this study, proactive traffic management strategies including Variable Speed Limit (VSL) and Dynamic Messing Signs (DMS) could be deployed to reduce the probability of crash occurrence.

Highly Automated Vehicles (HAVs) must undergo strict safety testing before being released to the public. Mileage-based on-road testing suffers from unaffordable time costs and high safety risks. Simulated scenario-based testing has been found to be a trustworthy alternative for testing HAVs’ built-in algorithms and functionalities. Test automation is typically used to generate target scenarios. This approach facilitates customized testing and avoids wasting time on simple and redundant scenarios. This study aims to review test automation methods and discuss how to accentuate their strengths rather than be trapped in their weaknesses under certain applicable conditions. According to their main purposes, we classify test automation methods into coverage-oriented, unsafe-scenario-oriented, and naturalistic-assessment-oriented categories. To further demonstrate the differences of these methods, we then design numerical experiment to compare the capabilities of seven test automation methods. Finally, we compile our observations to form a comprehensive guide for selecting test automation methods with different test requirements in mind.

Highly automated vehicles (HAVs) have been introduced to the transportation system for the purpose of providing safer mobility. Considering the expected long co-existence period of HAVs and human-driven vehicles (HDVs), the safety operation of HAVs interacting with HDVs needs to be verified. To achieve this, HAVs’ Operational Design Domain (ODD) needs to be identified under the scenario-based testing framework. In this study, a novel testing framework aiming at identifying the Safety performance boundary (SPB) is proposed, which assures the coverage of safety-critical scenarios and compatible with the black-box feature of HAV control algorithm. A surrogate model was utilized to approximate the safety performance of HAV, and a gradient descent searching algorithm was employed to accelerate the search for SPB. For empirical analyses, a three-vehicle following scenario was adopted and the Intelligent Driver Model (IDM) was tested as a case study. The results show that only 4% of the total scenarios are required to establish a reliable surrogate model. And the gradient descent algorithm was able to establish the SPB by identifying 97.42% of collision scenarios and only false alarming 0.29% of non-collision scenarios. Furthermore, the concept of safety tolerance was proposed to measure the possibilities of boundary scenarios dropping in safety performance. The applications of helping to construct ODD and compare different control algorithms were discussed. It shows that the IDM performs better than the Wiedemann 99 (W99) model with larger ODD.

Real time traffic crash risk prediction is very important for proactive safety management systems. In this paper, a new model is developed to predict real time traffic crash risk based on some elaborately selected characteristics of traffic flow. Compared with the dominant conventional matched case-control logistic regression model which is based on the assumption that all the traffic crashes share the same contributing factors and ignores the variability of traffic flow and heterogeneity of crash causations, the latent class logit model can considerably account for the unobserved heterogeneity. Data from Shanghai urban expressway between April to June 2014 are utilized to build the latent class logit model. The collected data are divided into a training set for model building and a validation set for model evaluation by random selection. Some criteria including Akaike information criterion (AIC), area under receiver operating characteristic curve (AUC), sensitivity and specificity are used to evaluate the model quality. The experimental results show that the overall accuracy of the latent class logit model is 70.23% and AUC of the model is 0.7576, which are both higher comparing to the traditional widely used case-control logistic regression model.

Traffic incidents such as crashes have significant impacts on urban expressway operation. The roadside service and operational efficiency of urban expressways could be improved based on a well-developed incident duration prediction model. In this study, a hybrid approach that combines Cox regression and random survival forests algorithm is developed to establish incident duration analysis model. The study is conducted based on traffic incident data from Shanghai urban expressways. For each traffic incident, information about the road geometry, traffic operation, and weather conditions was collected for experiments, where 80% of sample is used for training and the rest 20% for validation. In the hybrid model, a Cox regression model is predeveloped to investigate and identify the significant contributing factors of incident duration. Then, these identified significant factors are used as inputs for the random survival forests model. Finally, the statistical measurements including mean absolute error (MAE) and normalized mean square error (NMS) are used to measure the model performance and compare with other models. The analysis results show that incident type, location, affected lane numbers and other attributes have significant impacts on incident duration, and the hybrid approach model provides better prediction accuracy over traditional traffic incident duration prediction methods.

This paper investigates the effects of microscopic traffic, weather, and roadway geometric factors on the occurrence of specific crash types for a freeway. The I-70 Freeway was chosen for this paper since automatic vehicle identification (AVI) and weather detection systems are implemented along this corridor. A main objective of this paper is to expand the purpose of the existing intelligent transportation system to incorporate traffic safety improvement and suggest active traffic management (ATM) strategies by identifying the real-time crash patterns. Crashes have been categorized as rear-end, sideswipe, and single-vehicle crashes. AVI segment average speed, real-time weather data, and roadway geometric characteristic data were utilized as explanatory variables in this paper. First, binary logistic regression models were estimated to compare single- with multivehicle crashes and sideswipe with rear-end crashes. Then, a hierarchical logistic regression model that simultaneously fits two conditional logistic regression models for the three crash types has been developed. Results from the models indicate that single-vehicle crashes are more likely to occur in snowy seasons, at moderate slopes, three-lane segments, and under free-flow conditions, whereas the sideswipe crash occurrence differs from rear-end crashes with the visibility situation, segment number of lanes, grades, and their directions (up or down). Furthermore, the innovative way of estimating two conditional logistic regression models simultaneously in the Bayesian framework fits the correlated data structure well. Conclusions from this paper imply that different ATM strategies should be designed for three- and two-lane roadway sections and are also considering the seasonal effects.