Real-Time Vehicle Trajectory Prediction for Traffic Conflict Detection at Unsignalized Intersections

Real-time prediction of vehicle trajectory at unsignalized intersections is important for real-time traffic conflict detection and early warning to improve traffic safety at unsignalized intersections. In this study, we propose a robust real-time prediction method for turning movements and vehicle trajectories using deep neural networks. Firstly, a vision-based vehicle trajectory extraction system is developed to collect vehicle trajectories and their left-turn, go straight, and right-turn labels to train turning recognition models and multilayer LSTM deep neural networks for the prediction task. Then, when performing vehicle trajectory prediction, we propose the vehicle heading angle change trend method to recognize the future move of the target vehicle to turn left, go straight, and turn right based on the trajectory data characteristics of the target vehicle before passing the stop line. Finally, we use the trained multilayer LSTM models of turning left, going straight, and turning right to predict the trajectory of the target vehicle through the intersection. Based on the TensorFlow-GPU platform, we use Yolov5-DeepSort to automatically extract vehicle trajectory data at unsignalized intersections. The experimental results show that the proposed method performs well and has a good performance in both speed and accuracy evaluation.

A Traffic-Aware Federated Imitation Learning Framework for Motion Control at Unsignalized Intersections with Internet of Vehicles

The wealth of data and the enhanced computation capabilities of Internet of Vehicles (IoV) enable the optimized motion control of vehicles passing through an intersection without traffic lights. However, more intersections and demands for privacy protection pose new challenges to motion control optimization. Federated Learning (FL) can protect privacy via model interaction in IoV, but traditional FL methods hardly deal with the transportation issue. To address the aforementioned issue, this study proposes a Traffic-Aware Federated Imitation learning framework for Motion Control (TAFI-MC), consisting of Vehicle Interactors (VIs), Edge Trainers (ETs), and a Cloud Aggregator (CA). An Imitation Learning (IL) algorithm is integrated into TAFI-MC to improve motion control. Furthermore, a loss-aware experience selection strategy is explored to reduce communication overhead between ETs and VIs. The experimental results show that the proposed TAFI-MC outperforms imitated rules in the respect of collision avoidance and driving comfort, and the experience selection strategy can reduce communication overheads while ensuring convergence.

Parameter Estimation of the Macroscopic Fundamental Diagram: A Maximum Likelihood Approach

This paper extends the Stochastic Method of Cuts (SMoC) to approximate of the Macroscopic Fundamental Diagram (MFD) of urban networks and uses Maximum Likelihood Estimation (MLE) method to estimate the model parameters based on empirical data from a corridor and 30 cities around the world. For the corridor case, the estimated values are in good agreement with the measured values of the parameters. For the network datasets, the results indicate that the method yields satisfactory parameter estimates and graphical fits for roughly 50\% of the studied networks, where estimations fall within the expected range of the parameter values. The satisfactory estimates are mostly for the datasets which (i) cover a relatively wider range of densities and (ii) the average flow values at different densities are approximately normally distributed similar to the probability density function of the SMoC. The estimated parameter values are compared to the real or expected values and any discrepancies and their potential causes are discussed in depth to identify the challenges in the MFD estimation both analytically and empirically. In particular, we find that the most important issues needing further investigation are: (i) the distribution of loop detectors within the links, (ii) the distribution of loop detectors across the network, and (iii) the treatment of unsignalized intersections and their impact on the block length.

The Impact on Mobile Phone use on Pedestrian Road Crossing Behaviour

Mobile phone use at pedestrian crossings has been recognized as a growing problem in the field of traffic safety. The objective of the paper is to analyze the impact of mobile phone use at pedestrian crossings considering specific territory. Signalized and unsignalized intersections are observed in the study. Several factors having the impact on unsafe pedestrian crossing behaviour are identified such as: age, location and the type of mobile phone using. The model of unsafe pedestrian behaviour based on displayed mobile phone use while crossing the intersection is constructed. It has been shown in this research that talking and texting on mobile phone distract pedestrians. Listening to music does not affect pedestrians to behave unsafely because it requires less cognitive activity than talking or texting. Also, location affects the pedestrian crossing behavior. The results of this research can serve the purpose of preventing the mobile phones use and reduce the negative impact on pedestrian crossing behavior.