Accurate and real-time prediction of surrounding vehicles' lane-changing intentions is a critical challenge in deploying safe and efficient autonomous driving systems in open-world scenarios. Existing high-performing methods remain hard to deploy due to their high computational cost, long training times, and excessive memory requirements. Here, we propose an efficient lane-changing intention prediction approach based on brain-inspired Spiking Neural Networks (SNN). By leveraging the event-driven nature of SNN, the proposed approach enables us to encode the vehicle's states in a more efficient manner. Comparison experiments conducted on HighD and NGSIM datasets demonstrate that our method significantly improves training efficiency and reduces deployment costs while maintaining comparable prediction accuracy. Particularly, compared to the baseline, our approach reduces training time by 75% and memory usage by 99.9%. These results validate the efficiency and reliability of our method in lane-changing predictions, highlighting its potential for safe and efficient autonomous driving systems while offering significant advantages in deployment, including reduced training time, lower memory usage, and faster inference.

Intelligent Transportation Systems (ITS) increasingly rely on real-time 3-Dimensional (3D) data for vehicle dynamics, making edge computing crucial for timely and scalable 3D object detection, vehicle tracking, and counting. This paper introduces a real-time vehicle fleet monitoring system operating at 10 Hertz with a latency of 62.71 ms using advanced hardware and software. The primary objective of “fleet monitoring” is accurate vehicle counting and classification across diverse vehicle types. The hardware consists of a multi-beam flash Light Detection and Ranging (LiDAR), and an edge computing device. The software architecture is comprised of four modules: (1) a Graphics Processing Unit (GPU)-accelerated sensor interface module, which effectively processes high-density LiDAR point clouds by filtering out irrelevant background data and extracting regions of interest (RoIs); (2) Dynamic Voxelization Detector (DV-Det), a 3D object detection model which identifies and categorizes various vehicle types. It demonstrated exceptional performance, achieving 75 Hertz on the Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset and surpassing bird’s eye view (BEV)-based methods in all evaluation metrics; (3) A-Baseline-for-3D-Multi-Object-Tracking (AB3DMOT) algorithm, a robust multi-vehicle tracking module; (4) a specialized multi-vehicle counting algorithm, tailored for accurate vehicle enumeration in 3D environments. Field experiments validate the system’s capability to perform fine-grain vehicle classification with high precision and recall, achieving at least 80 Mean Average Precision (mAP) at a 3D Intersection-over-Union (IoU) threshold of 0.5 for most vehicle classes, along with a recall of 100% and a precision of at least 80% for the majority of the 10 fine-grain vehicle classes.

Traffic prediction is a crucial aspect of modern traffic management and has been a research focus for decades. Unlike the forecasting of traffic flow, speed, and demand, traffic accidents occur irregularly and are highly unpredictable. As a result, developing theory-based methods for traffic accident prediction is particularly challenging. In this study, we model the occurrence of traffic accidents as a Spatial-Temporal Point Process (STPP). First, we decompose the intensity function of the STPP into a Neural Temporal Point Process (NTPP) and a conditional spatial distribution. To manage both discrete and continuous historical information, we propose a contextual embedding module utilizing multi-head self-attention. The TPP is then modeled as a Hawkes Process, with the intensity function generated by neural networks. Afterwards, we employ a score-based diffusion model to learn the conditional spatial distribution. In addition, we introduce a co-prediction module to forecast the severity and duration of future accidents. We verify the effectiveness of our model based on real-world traffic accident datasets from three cities. The results demonstrate that our model can capture the complicated spatial-temporal patterns of traffic accidents well and outperform current approaches.

Lane changing presents a dynamic scenario characterized by intricate interactions among vehicles. Within mixed-autonomy traffic environment, modeling a human-like lane-change trajectory enables human drivers to better understand and predict autonomous vehicles’ behaviors, thereby enhancing road safety and travel efficiency. In this study, we achieve human-like interactive lane-change modeling based on a novel framework named Diff-LC. The human-like modeling of LCV behaviors relies on an advanced diffusive planner, and the implemented trajectory is selected based on the recovered LCV reward function learned through Multi-Agent Adversarial Inverse Reinforcement Learning (MA-AIRL). To account for interactions between FVs and LCVs, we further employ a diffusive predictor to forecast future behaviors of FVs conditioned on both historical and planned trajectories. Additionally, we leverage the recovered reward function of FVs to enable controllable prediction of trajectories. In the experimental part, we begin by analyzing the significance of features in the recovered reward functions and then proceed to compare the distinctions between the LCV and the FV. To validate the effectiveness of the proposed framework, we compare the diffusive predictor and planner with several state-of-the-art methods. The results demonstrate that motions planned by Diff-LC closely reach the intended positions with small displacement errors and exhibit highly similar speed and jerk distributions to those of human drivers. We also conduct a dynamic simulation to evaluate Diff-LC’s performance across different traffic conditions. Finally, we explore customized generation using the Diffusion Posterior Sampling method. The codes can be found athttps://github.com/zeonchen/Diff-LC/.

Intelligent Transportation Systems (ITS) play a crucial role in enhancing traffic efficiency and safety. Recently, diffusion models have emerged as transformative tools for addressing the complex challenges faced within ITS, including traffic uncertainty, data multimodality, and data imperfections. This paper presents a comprehensive survey of diffusion models in ITS, exploring both theoretical and practical dimensions. We begin by introducing the theoretical foundations of diffusion models and their key variants, such as conditional and latent diffusion models, highlighting their probabilistic modeling nature, capacity to model complex multimodal traffic data, and support for controllable generation. Next, we analyze the major challenges in ITS and explain how diffusion models offer robust, flexible, and controllable solutions, thereby elucidating their unique advantages in this domain. We then conduct a multi-perspective examination of current applications of diffusion models across ITS domains, including autonomous driving, traffic simulation, traffic forecasting, and traffic safety. Finally, we discuss state-of-the-art diffusion model techniques and highlight key research directions within ITS that merit further exploration. Through this structured overview, we aim to equip researchers with a comprehensive understanding of diffusion models in ITS, thereby fostering their future applications in the transportation domain. An open-source repository accompanying this survey is available at:https://github.com/Pemixing/Diffusion-Models-in-ITS-A-Survey

Learning and understanding car-following (CF) behaviors are crucial for microscopic traffic simulation. Traditional CF models, though simple, often lack generalization capabilities, while many data-driven methods, despite their robustness, operate as "black boxes" with limited interpretability. To bridge this gap, this work introduces a Bayesian Matrix Normal Mixture Regression (MNMR) model that simultaneously captures feature correlations and temporal dynamics inherent in CF behaviors. This approach is distinguished by its separate learning of row and column covariance matrices within the model framework, offering an insightful perspective into the human driver decision-making processes. Through extensive experiments, we assess the model’s performance across various historical steps of inputs, predictive steps of outputs, and model complexities. The results consistently demonstrate our model’s adeptness in effectively capturing the intricate correlations and temporal dynamics present during CF. A focused case study further illustrates the model’s outperforming interpretability of identifying distinct operational conditions through the learned mean and covariance matrices. This not only underlines our model’s effectiveness in understanding complex human driving behaviors in CF scenarios but also highlights its potential as a tool for enhancing the interpretability of CF behaviors in traffic simulations and autonomous driving systems.

The on-demand ride-pooling service, defined as two or more passengers sharing the same vehicle en-route along a proportion of their travel trajectories, offers many benefits, such as discounted trip fares for customers, higher income for drivers, increased profit for ride-sourcing companies, and reduced fuel consumption for environmental protection. Motivated by the potential of ride-pooling, many ride-sourcing companies launch pooling services based on the non-pooling market. By providing pooling and non-pooling services simultaneously, they compete with public transit for passengers. Of particular interest to service providers is the upfront pricing problem for the pooling service. It allows pooling riders to be informed of service prices even before the trip starts, and consequently makes the pooling service more attractive to passengers. However, it remains a challenging issue to obtain the optimal spatial-temporal upfront pricing strategy for the pooling service, considering the heterogeneity, dynamics, imbalance of demand /supply, and differentiation between pooling and non-pooling services. To address this problem, two reinforcement learning frameworks (i.e., single-agent Markov Decision Process (MDP) and multi-agent Markov Decision Process (MMDP)) are implemented to gain the pricing policy with the maximum daily profit of the platform, where the pooling price, as the action, not only directly affects the profit of each pooling request, but also has an influence on the mode splitting among pooling, non-pooling, and public transit service. Two tailored reinforcement learning methods are developed and adopted to solve the MDPs. Through extensive empirical experiments with a well-designed simulator, we show that the proposed multi-agent framework is able to remarkably improve the system performance.

Multi-step traffic speed prediction is a challenging issue due to the multiple spatial-temporal dependencies among roads. Some spatial dependencies, especially those formed by different traffic modes, are not fully exploited, and how to simultaneously consider spatial and temporal dependencies and effectively integrate them within a single prediction framework needs further exploration. To tackle the above issues, we propose a multi-view spatial-temporal graph convolutional framework MVSTG, which adequately exploits the multi-view spatial-temporal dependencies and their interactions to improve the accuracy of traffic prediction. Multi-view temporal learning captures the multiple temporal trends by temporal convolution from multi-granularity historical data, and multi-view spatial learning handles the multiple spatial correlations by graph convolution from multiple graphs. In addition, view-wise attention-based fusion is proposed to adaptively identify the importance of each upstream view, fuse the multi-view information, and generate integrated results for downstream views. The experiments on two real-world urban traffic datasets demonstrate that the multi-view data and the proposed model framework enhance performance on the accuracy of speed prediction, especially in mid-term and long-term prediction.

Ride-hailing service has witnessed a dramatic growth over the past decade but meanwhile raised various challenging issues, one of which is how to provide a timely and accurate short-term prediction of supply and demand. While the predictions for zone-based demand have been extensively studied, much less efforts have been paid to the predictions for origin-destination (OD) based demand (namely, demand originating from one zone to another). However, OD-based demand prediction is even more important and worth further explorations, since it provides more elaborate trip information in the near future as reference for fine-grained operations, such as the routing and matching of shared ride-hailing services that pick up and drop off two or more passengers in each ride. Simultaneous prediction of both zone-based and OD-based demand can be an interesting and practical problem for the ride-hailing platforms. To address the issue, we propose a multi-task matrix factorized graph neural network (MT-MF-GCN), which consists of two major components: (1) a GCN (graph convolutional network) basic module that captures the spatial correlations among zones via mixture-model graph convolutional (MGC) network, and (2) a matrix factorization module for multi-task predictions of zone-based and OD-based demand. By evaluations on the real-world on-demand data in Manhattan and Haikou, we show that the proposed model outperforms the state-of-the-art baseline methods in both zone- and OD-based predictions.

This paper aims to reveal the uncertainty of traffic flow by introducing a new quantity based on the concept of information entropy (IE). We discover the existence and analyze the properties of IE of traffic flows. It is revealed by both real-world trajectory data and simulation data that the IE of traffic flows can be clearly measured and observed. More importantly, the relationships between IE and other key quantities, those are space mean speed and density, in traffic flow analysis can be described by linear and parabolic functions. We also discover that these relationships are not sensitive to traffic volume. With the inspiration from IE, another new quantity termed speed entropy (SE) is then proposed. Tests with aggregated traffic data from Performance Measurement System (PeMS) show that the pattern of the relationship between SE and flow-weighted average speed illustrates different traffic conditions. In general, a key achievement of the IE analysis is that it gives us a new pathway to better capture the intricate traffic flows from the dimension of uncertainty, thus it has the potential to enhance existing models for traffic data analysis.

Fitting and modeling spatial-temporal processes are essential research topics in transportation studies. Recently, due to the analytically tractable formulation and good fitting accuracy, the Gaussian Process (GP) is becoming increasingly preferable in fitting transportation processes. However, conventional GPs are inapplicable for large-scale problems due to computational issues. Moreover, they dismiss physics laws when conducting multi-output fitting tasks. This paper proposes a physics regularized multi-output grid Gaussian Process Model (PRMGGP) model for fast and multi-output fitting of large-scale spatial-temporal processes in transportation systems. The PRMGGP model adopts a grid input structure to capture inherent spatial-temporal correlations in the fitting process, takes advantage of the Kronecker algebra to notably accelerate the computation speed, and utilizes a shadow GP to incorporate physics laws of the process. Model training and predictive algorithms are developed coordinately and are tested via synthetic datasets. Furthermore, we apply the proposed model and other widely used machine learning models to fit the numbers of pickups, returns, and idle bikes of a large-scale bike-sharing system based on Citi Bike data from New York City. The results demonstrate the computational efficiency, interpretable results, and the prediction accuracy of the PRMGGP model, which can be a promising methodology for modeling multi-output processes in transportation systems.

Ride-sourcing services are now reshaping the way people travel by effectively connecting drivers and passengers through mobile internets. Online matching between idle drivers and waiting passengers is one of the most key components in a ride-sourcing system. The average pickup distance or time is an important measurement of system efficiency since it affects both passengers’ waiting time and drivers’ utilization rate. It is naturally expected that a more effective bipartite matching (with smaller average pickup time) can be implemented if the platform accumulates more idle drivers and waiting passengers in the matching pool. A specific passenger request can also benefit from a delayed matching since he/she may be matched with closer idle drivers after waiting for a few seconds. Motivated by the potential benefits of delayed matching, this paper establishes a two-stage framework which incorporates a combinatorial optimization and multi-agent deep reinforcement learning methods. The multi-agent reinforcement learning methods are used to dynamically determine the delayed time for each passenger request (or the time at which each request enters the matching pool), while the combinatorial optimization conducts an optimal bipartite matching between idle drivers and waiting passengers in the matching pool. Four tailored reinforcement learning methods, delayed multi-agent deep Q learning (Delayed-M-DQN), delayed multi-agent actor-critic (Delayed-M-A2C), delayed multi-agent Proximal Policy Optimization (Delayed-M-PPO), and delayed multi-agent actor-critic with experience replay (Delayed-M-ACER), are developed. Through extensive empirical experiments with a well-designed simulator, we show that the proposed framework is able to remarkably improve system performances, by well balancing the trade-off among pick-up time, matching time, successful matching rate.

Ride-sourcing services are becoming an increasingly popular transportation mode in cities all over the world. With real-time information from both drivers and passengers, the ride-sourcing platform can reduce matching frictions and improve efficiencies by surge pricing, optimal vehicle-trip assignment, and proactive ridesplitting strategies. An important foundation of these strategies is the short-term supply-demand forecasting. In this paper, we tackle the problem of predicting the short-term supply-demand gap of ride-sourcing services. In contrast to the previous studies that partitioned a city area into numerous square lattices, we partition the city area into various regular hexagon lattices, which is motivated by the fact that hexagonal segmentation has an unambiguous neighborhood definition, smaller edge-to-area ratio, and isotropy. To capture the spatio-temporal characteristics in a hexagonal manner, we propose three hexagon-based convolutional neural networks (H-CNN), both the input and output of which are numerous local hexagon maps. Moreover, a hexagon-based ensemble mechanism is developed to enhance the prediction performance. Validated by a 3-week real-world ride-sourcing dataset in Guangzhou, China, the H-CNN models are found to significantly outperform the benchmark algorithms in terms of accuracy and robustness. Our approaches can be further extended to a broad range of spatio-temporal forecasting problems in the domain of shared mobility and urban computing.

The resilience of transportation systems has been extensively studied in the past decade. This paper aims to provide a synthesis of the up-to-date literature on resilient transportation, focusing on concepts and methodologies. A systematic literature search method integrating database search, related journal search, and citation supplement is proposed to select all the appropriate articles. Based on the selected core papers, the definition of resilience is examined, and some related concepts are compared. The main body of the paper is devoted to the review of metrics and mathematical models used to measure resilience and the strategies used to enhance resilience. Several popular subtopics are identified and discussed. Finally, current research gaps and challenges are addressed, and some potential research directions are presented.

No abstract available.

Urbanization's rapid progress has modernized many people's lives but also engendered big issues, such as traffic congestion, energy consumption, and pollution. Urban computing aims to tackle these issues by using the data that has been generated in cities (e.g., traffic flow, human mobility, and geographical data). Urban computing connects urban sensing, data management, data analytics, and service providing into a recurrent process for an unobtrusive and continuous improvement of people's lives, city operation systems, and the environment. Urban computing is an interdisciplinary field where computer sciences meet conventional city-related fields, like transportation, civil engineering, environment, economy, ecology, and sociology in the context of urban spaces. This article first introduces the concept of urban computing, discussing its general framework and key challenges from the perspective of computer sciences. Second, we classify the applications of urban computing into seven categories, consisting of urban planning, transportation, the environment, energy, social, economy, and public safety and security, presenting representative scenarios in each category. Third, we summarize the typical technologies that are needed in urban computing into four folds, which are about urban sensing, urban data management, knowledge fusion across heterogeneous data, and urban data visualization. Finally, we give an outlook on the future of urban computing, suggesting a few research topics that are somehow missing in the community.

Linear variational inequality is a uniform approach for some important problems in optimization and equilibrium problems. In this paper, we give a neural-network model for solving asymmetric linear variational inequalities. The model is based on a simple projection and contraction method. Computer simulation is performed for linear programming (LP) and linear complementarity problems (LCP). The test results for LP problem demonstrate that our model converges significantly faster than the three existing neural-network models examined in a recent comparative study paper.