Driving intention prediction from a bird’s-eye view has always been an active research area. However, existing research, on one hand, has only focused on predicting lane change intention in highway scenarios and, on the other hand, has not modeled the influence and spatiotemporal relationship of surrounding vehicles. This study extends the application scenarios to urban road scenarios. A spatial-temporal convolutional long short-term memory (ConvLSTM) model is proposed to predict the vehicle’s lateral and longitudinal driving intentions simultaneously. This network includes two modules: the first module mines the information of the target vehicle using the long short-term memory (LSTM) network and the second module uses ConvLSTM to capture the spatial interactions and temporal evolution of surrounding vehicles simultaneously when modeling the influence of surrounding vehicles. The model is trained and verified on a real road dataset, and the results show that the spatial-temporal ConvLSTM model is superior to the traditional LSTM in terms of accuracy, precision, and recall, which helps improve the prediction accuracy at different time horizons.

In recent years, the Vehicle-to-Vehicle (V2V) communication system has been considered one of the most promising technologies to build a much safer and more efficient transportation system. Both simulation and field test have been extensively performed to evaluate the performance of the V2V communication system. However, most of the evaluation methods are communication-based, and although in a transportation environment, lack a V2V application-oriented analysis. In this study, we conducted real-world tests and built an application-oriented evaluation model. The experiments were classified into four scenarios: static, following, face 2 face, and crossing vertically, which almost covered all the V2V communication patterns on the road. Under these scenarios, we conducted experiments and built a probability model to evaluate the performance of 802.11p and LTE-V in safety-related applications. Consequently, we found out that improvements are still needed in Non-Line-of-Sight scenarios.

To simulate the passenger behavior in subway system, a Dynamic Parameters Cellular Automaton (DPCA) model is put forward in this paper. Pedestrian traffic flows during waiting, getting on or off, and traveling can be simulated. The typical scenario in Beijing Subway Line 13 is modeled to analyze the passenger behavior in subway system. By comparing simulation results with statistical ones, the correctness and practicality of the DPCA model are verified. At last, the additional results made by DPCA model can make contribution to passenger comfort analysis and pedestrian facility planning and guidance.