Accurate vehicle trajectory prediction is critical for autonomous vehicles and advanced driver assistance systems to make driving decisions and improve traffic safety. This paper proposes a novel Temporal Multi-task Mixture Of Experts (TMMOE) model for simultaneously predicting the vehicle trajectory and driving intention, considering interconnections among tasks. As for the methodology, the proposed model consists of three layers: a shared layer, an expert layer, and a fully connected layer. In more detail, the first layer utilizes Temporal Convolutional Network (TCN) to extract temporal features whereas the expert layer incorporates the gating mechanism to memorize and filter the temporal dependence of sequences and, finally, the fully connected layer is applied to integrate and export prediction results. Furthermore, the homoscedastic uncertainty algorithm is used to construct the multi-task loss function. The open data source CitySim dataset is chosen to validate the performance of the proposed TMMOE model; moreover, a novel lane line reconstruction method is introduced to mitigate measurement errors of the dataset. Two-part information, including the history of the vehicle's trajectory and the interaction indicators, are employed as the input variables. The result indicates that the TMMOE algorithm exhibits superior performance when compared to the other five models, including Long Short-Term Memory (LSTM) Network, Convolutional Neural Network (CNN), CNN-LSTM, TCN, and Gate Recurrent Unit (GRU), while considering varying input sequence lengths are 3 s, 6 s, and 9 s respectively. Finally, the sensitivity analysis demonstrates that considering driving intentions in vehicle trajectory prediction can significantly enhance the prediction accuracy of vehicle trajectories.

This study investigates the differences in the factors affecting the injury severity of speeding-related crashes occurring in the daytime and nighttime. Two log-likelihood ratio tests are conducted to validate whether speeding-related crashes classified by daytime and nighttime should be modeled separately. The result proves that separate modeling is necessary. Two correlated random parameter order probit models with heterogeneity in means are conducted using the data collected from 2018 to 2020 in the United States. Model estimation results show that urban areas, speed limits, and young and older drivers are temporal instability. Angle crashes, head-on crashes, intersections, downhill, exceeding the speed limit, drunk driving, and motorcycles are statistically significant in both models with an increased crash severity. Interaction and heterogeneity effects between random parameters are also reported. For instance, large trucks driving above the speed limit are more likely to increase the probability of severe injury.

Accurately detecting and predicting lane change (LC)processes of human-driven vehicles can help autonomous vehicles better understand their surrounding environment, recognize potential safety hazards, and improve traffic safety. This paper focuses on LC processes, first developing a temporal convolutional network with an attention mechanism (TCN-ATM) model to recognize LC intention. Considering the intrinsic relationship among output variables, the Multi-task Learning (MTL)framework is employed to simultaneously predict multiple LC vehicle status indicators. Furthermore, a unified modeling framework for LC intention recognition and driving status prediction (LC-IR-SP) is developed. The results indicate that the classification accuracy of LC intention was improved from 96.14% to 98.20% when incorporating the attention mechanism into the TCN model. For LC vehicle status prediction issues, three multi-tasking learning models are constructed based on MTL framework. The results indicate that the MTL-LSTM model outperforms the MTL-TCN and MTL-TCN-ATM models. Compared to the corresponding single-task model, the MTL-LSTM model demonstrates an average decrease of 26.04% in MAE and 25.19% in RMSE.

Accurately detecting and predicting lane change (LC)processes can help autonomous vehicles better understand their surrounding environment, recognize potential safety hazards, and improve traffic safety. This paper focuses on LC processes and compares different machine learning methods' performance to recognize LC intention from high-dimensionality time series data. To validate the performance of the proposed models, a total number of 1023 vehicle trajectories is extracted from the CitySim dataset. For LC intention recognition issues, the results indicate that with ninety-eight percent of classification accuracy, ensemble methods reduce the impact of Type II and Type III classification errors. Without sacrificing recognition accuracy, the LightGBM demonstrates a sixfold improvement in model training efficiency than the XGBoost algorithm.

Rear-end crashes are one of the most common crash types. Passenger cars involved in rear-end crashes frequently produce severe outcomes. However, no study investigated the differences in the injury severity of occupant groups when cars are involved as following and leading vehicles in rear-end crashes. Therefore, the focus of this investigation is to compare the key factors affecting the injury severity between the front- and rear-car occupant groups in rear-end crashes. First, data is extracted from the Fatality Analysis Reporting System (FARS) for two types of rear-end crashes from 2017 to 2019, including passenger cars as rear-end and rear-ended vehicles. Significant injury severity difference between front- and rear-car occupant groups is found by conducting likelihood ratio test. Moreover, the front- and rear-car occupant groups are modelled by the correlated random parameter logit model with heterogeneity in means (CRPLHM) and the random parameter logit model with heterogeneity in means (RPLHM), respectively. From the modeling, the significant factors are occupant positions, driver age, overturn, vehicle type, etc. For instance, the driving and front-right positions significantly increase the probability of severe injury when struck by another vehicle. Large truck-strike-car tends to cause severe outcomes compared to car-strike-large truck. This study provides an insightful knowledge of mechanism of occupant injury severity in rear-end crashes, and propose some effective countermeasures to mitigate the crash severity, such as implementing stricter seat belt laws, improving the coverage of the streetlights, strengthening car driver's emergency response ability.