Urban traffic demand distribution is dynamic in both space and time. A thorough analysis of individuals’ travel patterns can effectively reflect the dynamics of a city. This study aims to develop an analytical framework to explore the spatiotemporal traffic demand and the characteristics of the community structure shaped by travel, which is analyzed empirically in New York City. It uses spatial statistics and graph-based approaches to quantify travel behaviors and generate previously unobtainable insights. Specifically, people primarily travel for commuting on weekdays and entertainment on weekends. On weekdays, people tend to arrive in the financial and commercial areas in the morning, and the functions of zones arrived in the evening are more diversified. While on weekends, people are more likely to arrive at parks and department stores during the daytime and theaters at night. These hotspots show positive spatial autocorrelation at a significance level of p = 0.001. In addition, the travel flow at different peak times form relatively stable community structures, we find interesting phenomena through the complex network theory: 1) Every community has a very small number of taxi zones (TZs) with a large number of passengers, and the weighted degree of TZs in the community follows power-law distribution; 2) As the importance of TZs increases, their interaction intensity within the community gradually increases, or increases and then decreases. In other words, the formation of a community is determined by the key TZs with numerous traffic demands, but these TZs may have limited connection with the community in which they are located. The proposed analytical framework and results provide practical insights for urban and transportation planning.

We propose a motion planning method for automated vehicles (AVs) to complete driving tasks in dynamic traffic scenes. The proposed method aims to generate motion trajectories for an AV after obtaining the surrounding dynamic information and making a preliminary driving decision. The method generates a reference line by interpolating the original waypoints and generates optional trajectories with costs in a prediction interval containing three dimensions (lateral distance, time, and velocity) in the Frenet frame, and filters the optimal trajectory by a series of threshold checks. When calculating the feasibility of optional trajectories, the cost of all optional trajectories after removing obstacle interference shows obvious axisymmetric regularity concerning the reference line. Based on this regularity, we apply the constrained Simulated Annealing Algorithm (SAA) to improve the process of searching for the optimal trajectories. Experiments in three different simulated driving scenarios (speed maintaining, lane changing, and car following) show that the proposed method can efficiently generate safe and comfortable motion trajectories for AVs in dynamic environments. Compared with the method of traversing sampling points in discrete space, the improved motion planning method saves 70.23% of the computation time, and overcomes the limitation of the spatial sampling interval.

By the end of the 2020s, full autonomy in autonomous driving may become commercially viable in certain regions. However, achieving Level 5 autonomy requires crucial collaborations between vehicles and infrastructure, necessitating high-speed data processing and low-latency capabilities. This paper introduces a vehicle tracking algorithm based on roadside LiDAR (light detection and ranging) infrastructure to reduce the latency to 100 ms without compromising the detection accuracy. We first develop a vehicle detection architecture based on ResNet18 that can more effectively detect vehicles at a full frame rate by improving the BEV mapping and the loss function of the optimizer. Then, we propose a new three-stage vehicle tracking algorithm. This algorithm enhances the Hungarian algorithm to better match objects detected in consecutive frames, while time–space logicality and trajectory similarity are proposed to address the short-term occlusion problem. Finally, the system is tested on static scenes in the KITTI dataset and the MATLAB/Simulink simulation dataset. The results show that the proposed framework outperforms other methods, with F1-scores of 96.97% and 98.58% for vehicle detection for the KITTI and MATLAB/Simulink datasets, respectively. For vehicle tracking, the MOTA are 88.12% and 90.56%, and the ID-F1 are 95.16% and 96.43%, which are better optimized than the traditional Hungarian algorithm. In particular, it has a significant improvement in calculation speed, which is important for real-time transportation applications.

Understanding and predicting pedestrian crossing behavioral intention is crucial for the driving safety of autonomous vehicles. Nonetheless, challenges emerge when using promising images or environmental context masks to extract various factors for time-series network modeling, causing preprocessing errors or a loss of efficiency. Typically, pedestrian positions captured by onboard cameras are often distorted and do not accurately reflect their actual movements. To address these issues, GTransPDM – a Graph-embedded Transformer with a Position Decoupling Module – was developed for pedestrian crossing intention prediction by leveraging multi-modal features. First, a positional decoupling module was proposed to decompose pedestrian lateral motion and encode depth cues in the image view. Then, a graph-embedded Transformer was designed to capture the spatio-temporal dynamics of human pose skeletons, integrating essential factors such as position, skeleton, and egovehicle motion. Experimental results indicate that the proposed method achieves 92% accuracy on the PIE dataset and 87% accuracy on the JAAD dataset, with a processing speed of 0.05ms. It outperforms the state-of-the-art in comparison.

As an emerging type of spatio-temporal big data based on positioning technology and navigation devices, vehicle-based crowdsourcing data has become a valuable trajectory data resource. However, crowdsourcing trajectory data has been collected by non-professionals and with multiple measurement terminals, resulting in certain errors in data collection. In these cases, to minimize the impact of outliers and obtain relatively accurate trajectory data, it is crucial to detect and clean outliers. This paper proposes an efficient crowdsourcing trajectory outlier detection (CTOD) method that detects outliers from the trajectory sequence data in both spatial view and temporal view. Specifically, we first use the adaptive spatial clustering algorithm based on the Delaunay triangulation (ASCDT) algorithm to remove the location offset points in the trajectory sequence. After that, based on the most basic attributes of the trajectory points, a 6-dimensional movement feature vector is constructed for each point as an input. The feature-rich trajectory sequence data is reconstructed using the proposed temporal convolutional network autoencoder (TCN-AE), and the Squeeze-and-Excitation (SE) channel attention mechanism is introduced. Finally, the effectiveness of the CTOD method is experimentally verified.