Accident anticipation is essential for proactive and safe autonomous driving, where even a brief advance warning can enable critical evasive actions. However, two key challenges hinder real-world deployment: (1) noisy or degraded sensory inputs from weather, motion blur, or hardware limitations, and (2) the need to issue timely yet reliable predictions that balance early alerts with false-alarm suppression. We propose a unified framework that integrates diffusion-based denoising with a time-aware actor-critic model to address these challenges. The diffusion module reconstructs noise-resilient image and object features through iterative refinement, preserving critical motion and interaction cues under sensor degradation. In parallel, the actor-critic architecture leverages long-horizon temporal reasoning and time-weighted rewards to determine the optimal moment to raise an alert, aligning early detection with reliability. Experiments on three benchmark datasets (DAD, CCD, A3D) demonstrate state-of-the-art accuracy and significant gains in mean time-to-accident, while maintaining robust performance under Gaussian and impulse noise. Qualitative analyses further show that our model produces earlier, more stable, and human-aligned predictions in both routine and highly complex traffic scenarios, highlighting its potential for real-world, safety-critical deployment.

Long-tail motion forecasting is a core challenge for autonomous driving, where rare yet safety-critical events-such as abrupt maneuvers and dense multi-agent interactions-dominate real-world risk. Existing approaches struggle in these scenarios because they rely on either non-interpretable clustering or model-dependent error heuristics, providing neither a differentiable notion of “tailness” nor a mechanism for rapid adaptation. We propose SAML, a Semantic-Aware Meta-Learning framework that introduces the first differentiable definition of tailness for motion forecasting. SAML quantifies motion rarity via semantically meaningful intrinsic (kinematic, geometric, temporal) and interactive (local and global risk) properties, which are fused by a Bayesian Tail Perceiver into a continuous, uncertainty-aware Tail Index. This Tail Index drives a meta-memory adaptation module that couples a dynamic prototype memory with an MAML-based cognitive set mechanism, enabling fast adaptation to rare or evolving patterns. Experiments on nuScenes, NGSIM, and HighD show that SAML achieves state-of-the-art overall accuracy and substantial gains on top 1-5% worst-case events, while maintaining high efficiency. Our findings highlight semantic meta-learning as a pathway toward robust and safety-critical motion forecasting.

Diffusion models demonstrate superior performance in capturing complex distributions from large-scale datasets, providing a promising solution for quadrupedal locomotion control. However, the robustness of the diffusion planner is inherently dependent on the diversity of the pre-collected datasets. To mitigate this issue, we propose a two-stage learning framework to enhance the capability of the diffusion planner under limited dataset (reward-agnostic). Through the offline stage, the diffusion planner learns the joint distribution of state-action sequences from expert datasets without using reward labels. Subsequently, we perform the online interaction in the simulation environment based on the trained offline planner, which significantly diversified the original behavior and thus improves the robustness. Specifically, we propose a novel weak preference labeling method without the ground-truth reward or human preferences. The proposed method exhibits superior stability and velocity tracking accuracy in pacing, trotting, and bounding gait under different speeds and can perform a zero-shot transfer to the real Unitree Go1 robots. The project website for this paper is at https://shangjaven.github.io/preference-aligned-diffusion-legged/.

In the realm of driving technologies, fully autonomous vehicles have not been widely adopted yet, making advanced driver assistance systems (ADAS) crucial for enhancing driving experiences. Among these, car-following behavior modeling plays a pivotal role, forming the foundation for systems that ensure safe and efficient vehicle interactions. However, current approaches often rely on fixed parameters, failing to capture the diverse social preferences and driving styles of individuals. To overcome these limitations, we propose the Editable Behavior Generation (EBG) model, a data-driven car-following model that allows for adjusting driving discourtesy levels. The framework integrates diverse courtesy calculation methods into long short-term memory (LSTM) and Transformer architectures, offering a comprehensive approach to capture nuanced driving dynamics. By integrating various discourtesy values during the training process, our model generates realistic agent trajectories with different levels of courtesy in car-following behavior. Experimental results on the naturalistic datasets showcase a reduction in Mean Squared Error (MSE) of spacing and MSE of speed compared to baselines, establishing style controllability. To the best of our knowledge, this work represents the first data-driven car-following model capable of dynamically adjusting discourtesy levels. Our model provides valuable insights for the development of ADAS that take into account drivers’ social preferences.

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/.

Planning safe and efficient trajectories through signal-free intersections presents significant challenges for autonomous vehicles (AVs), particularly in dynamic, multi-task environments with unpredictable interactions and an increased possibility of conflicts. This study aims to address these challenges by developing a unified, robust, adaptive framework to ensure safety and efficiency across three distinct intersection movements: left-turn, right-turn, and straight-ahead. Existing methods often struggle to reliably ensure safety and effectively learn multi-task behaviors from demonstrations in such environments. This study proposes a safety-critical planning method that integrates Dynamic High-Order Control Barrier Functions (DHOCBF) with a diffusion-based model, called Dynamic Safety-Critical Diffuser (DSC-Diffuser), offering a robust solution for adaptive, safe, and multi-task driving in signal-free intersections. The DSC-Diffuser leverages task-guided planning to enhance efficiency, allowing the simultaneous learning of multiple driving tasks from real-world expert demonstrations. Moreover, the incorporation of goal-oriented constraints significantly reduces displacement errors, ensuring precise trajectory execution. To further ensure driving safety in dynamic environments, the proposed DHOCBF framework dynamically adjusts to account for the movements of surrounding vehicles, offering enhanced adaptability and reduce the conservatism compared to traditional control barrier functions. Validity evaluations of DHOCBF, conducted through numerical simulations, demonstrate its robustness in adapting to variations in obstacle velocities, sizes, uncertainties, and locations, effectively maintaining driving safety across a wide range of complex and uncertain scenarios. Comprehensive performance evaluations demonstrate that DSC-Diffuser generates realistic, stable, and generalizable policies, providing flexibility and reliable safety assurance in complex multi-task driving scenarios.

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

Interacting with the actual environment to acquire data is often costly and time-consuming in robotic tasks. Model-based offline reinforcement learning (RL) provides a feasible solution. On the one hand, it eliminates the requirements of interaction with the actual environment. On the other hand, it learns the transition dynamics and reward function from the offline datasets and generates simulated rollouts to accelerate training. Previous model-based offline RL methods adopt probabilistic ensemble neural networks (NN) to model aleatoric uncertainty and epistemic uncertainty. However, this results in a great increase in training time and computing resource requirements. Furthermore, these methods are easily disturbed by the accumulative errors of the environment dynamics models when simulating long-term rollouts. To solve the above problems, we propose an uncertainty-aware sequence modeling architecture called Environment Transformer. It models the probability distribution of the environment dynamics and reward function to capture aleatoric uncertainty and treats epistemic uncertainty as a learnable noise parameter. Benefiting from the accurate modeling of the transition dynamics and reward function, Environment Transformer can be combined with arbitrary planning, dynamics programming, or policy optimization algorithms for offline RL. In this case, we perform Conservative Q-Learning (CQL) to learn a conservative Q-function. Through simulation experiments, we demonstrate that our method achieves or exceeds state-of-the-art performance in widely studied offline RL benchmarks. Moreover, we show that Environment Transformer's simulated rollout quality, sample efficiency, and long-term rollout simulation capability are superior to those of previous model-based offline RL methods.

Traffic oscillations pose safety and efficiency challenges in mixed scenarios involving connected and automated vehicles (CAVs) and human-driven vehicles (HDVs). Existing control strategies fail to handle the unpredictability of HDV behaviors, resulting in disruptive "stop-and-go" traffic patterns. This study proposes a novel algorithm that uses Deep Reinforcement Learning (DRL) integrated into a distinctive "CAV-AHDV-CAV" structure for car-following events. The consecutive HDVs are treated as an aggregated unit called Aggregated HDVs (AHDVs) to eliminate stochasticity and leverage collective traffic features as inputs, addressing the driver heterogeneity issue. Our training and testing were conducted using a dataset of 9,200 car-following events extracted from the HighD dataset. In these events, the lead vehicle serves as our CAV in front, while the following vehicle represents the AHDV. We simulated our controlled vehicle to follow the AHDV, aiming to achieve the vehicle equilibrium state with respect to both the AHDV and the CAV in front. The results demonstrate a reduction in the impact of HDVs and an enhancement of equilibrium states compared to baseline models. Specifically, we achieved a speed mean square error (MSE) of 3.151 and spacing MSE values of 50.484 (with respect to the AHDV) and 47.855 (with respect to the CAV). These findings offer robust and adaptable control strategies for efficient and safe mixed traffic dominated by CAVs.

This study proposes to find the most appropriate transport modes with an awareness of user preferences (e.g., costs, times) and trip characteristics (e.g., purpose, distance). The work was based on real-life trips obtained from a map application. Several methods including gradient boosting tree, learning to rank, multinomial logit model, automated machine learning, random forest, and shallow neural network have been tried. For some methods, feature selection and over-sampling techniques were also tried. The results show that the best-performing method is a gradient-boosting tree model with the synthetic minority oversampling technique (SMOTE). Also, results of the multinomial logit model show that (1) an increase in travel cost would decrease the utility of all the transportation modes; (2) people are less sensitive to the travel distance for the metro mode or a multi-modal option that contains metro, i.e., compared to other modes, people would be more willing to tolerate long-distance metro trips. This indicates that metro lines might be a good candidate for large cities.

Vehicle recognition and classification are critical for a number of traffic applications, e.g., traffic signal control, traffic flow modeling, tolling, and logistics optimization. Commonly used sensing systems are mainly counted on in-pavement loops or surveillance video cameras, while both of them have their inherent limitations. Leveraging micro high-speed pulse LiDAR mounted overhead of travel lanes, this study proposes Compact LiDAR Empowered Vehicle Enhancing-minority Recognition (CLEVER) system, a real-time cost-effective vehicle detection and classification framework that is empowered by edge Artificial Intelligence (AI). Based on the customized minority-enhancing vehicle classification deep neural network, the CLEVER system outperforms cutting-edge LiDAR-based vehicle classification methods up to 15.98% true-positive rate in classifying ten types of vehicles. Furthermore, by highly integrating the hardware, the pre-processing algorithm and the classification neural network into an edge computing node, the CLEVER system only consumes 10% of the cost in LiDAR systems and works perfectly in a plug-and-play mode with a negligible sub-second inference time (212ms to 459ms). The proposed CLEVER system offers an affordable end-to-end solution that can benefit traffic operators by collecting more accurate and reliable vehicle classification data streams and that can lead to a more efficient and flexible ITS.

As a vital component in autonomous driving, accurate trajectory prediction effectively prevents traffic accidents and improves driving efficiency. To capture complex spatial-temporal dynamics and social interactions, recent studies developed models based on advanced deep-learning methods. On the other hand, recent studies have explored the use of deep generative models to further account for trajectory uncertainties. However, the current approaches demonstrating indeterminacy involve inefficient and time-consuming practices such as sampling from trained models. To fill this gap, we proposed a novel model named Graph Recurrent Attentive Neural Process (GRANP) for vehicle trajectory prediction while efficiently quantifying prediction uncertainty. In particular, GRANP contains an encoder with deterministic and latent paths, and a decoder for prediction. The encoder, including stacked Graph Attention Networks, LSTM and 1D convolutional layers, is employed to extract spatial-temporal relationships. The decoder is used to learn a latent distribution and thus quantify prediction uncertainty. To reveal the effectiveness of our model, we evaluate the performance of GRANP on the highD dataset. Extensive experiments show that GRANP achieves state-of-the-art results and can efficiently quantify uncertainties. Additionally, we undertake an intuitive case study that showcases the interpretability of the proposed approach. The code is available at https://github.com/joy-driven/GRANP.

Despite the widespread implementation, the Adaptive Cruise Control (ACC) systems still fall short in delivering a satisfactory human-likely experience, primarily due to the heterogeneity in driving experience preferences and the unpredictable, heterogeneous nature of human driving behaviors. To address this critical gap, we introduce an innovative driving style-aware car-following model that effectively captures the varying cut-in tendencies of adjacent vehicles by utilizing the Maximum Entrop Inverse Reinforcement Learning (Max-Ent IRL) method. A distinct reward function is developed to replicate human driving behavior, which can achieve a harmonious equilibrium between efficiency, safety, and comfort. The efficacy of this model is rigorously evaluated through a comprehensive analysis on car-following episodes extracted from the Next Generation Simulation (NGSIM) I-80 dataset. A novel human-likely metric is utilized for evaluating the performance of the proposed model in comparison to standard benchmarks. The results demonstrably favor our approach, showing notable enhancements in efficiency, safety, and comfort. Additionally, the model’s versatility is confirmed by its ability to accommodate a wide spectrum of driving styles, as evidenced by the diverse weights learned from different driving styles. These findings highlight the significant potential of our model in advancing ACC technology for more human-oriented vehicular systems that align closely with the natural driving instincts and preferences of humans.

With the rapid advancement of deep learning technology, feature extraction backbones that are effectively trained have found increasing use in various traffic perception tasks, such as vehicle recognition and roadway user detection and classification. However, given the naturally imbalanced distribution of objects in the real world, deep learning networks can inadvertently act as bias amplifiers, leading to unfair detection and classification outcomes. Addressing and quantifying this bias in traffic applications has thus become a pressing challenge. In response, this research introduces the first comprehensive traffic imbalance object recognition dataset tailored for autonomous vehicles, called the Autonomous-vehicle Long-tail Image Dataset (ALIDA). This dataset reflects real-world sample distribution and includes four categories—motorized users, non-motorized users, roadway facilities, and traffic signs—spanning 87 classes and totaling 37,558 images. Our experimental results confirm that these backbones may struggle to accurately recognize less common objects with limited training data, such as children and wheelchair users. To mitigate such biases and improve traffic perception equality, we introduce a DEbiased Traffic Object Recognition (DETOR) scheme. This scheme leverages both few-shot and representation learning techniques. Employing DETOR, the residual neural network achieved a 290% increase in accuracy for recognizing minority classes, such as children, motorcyclists, deer, and bears. This not only enhances the effectiveness but also significantly improves the fairness and scalability of traffic perception using deep neural networks.

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.

In recent years, remarkable strides have been made in the field of autonomous driving, with a particular focus on enhancing perception and prediction capabilities through the integration of big data and advanced deep learning algorithms. Despite these advancements, the persistent challenge of effectively validating the performance of autonomous vehicles (AVs) remains a critical issue. In the realm of microscopic traffic simulation, a noteworthy challenge persists – that of bridging the behavior gap between simulated scenarios and real-world driving situations. Efforts to define agent behavior in simulations manually or replay observed behaviors have proven to be inefficient and prone to inaccuracies, mainly because simulated agents often fail to authentically react to actions initiated by AVs. While rule-based traffic simulation models offer plausible behaviors, they exhibit limitations in adapting to diverse and data-driven behavior patterns within complex driving interactions. Addressing these challenges, we propose a learning-based method for traffic agent simulation, emphasizing realism and reactivity. This involves learning data-driven agent models from real-world driving data with detailed interaction information and high-definition (HD) maps. Utilizing a convolutional neural network (CNN), we extract features and predict future trajectories, achieving realism and reactivity through closed-loop simulation at inference. The proposed model is evaluated using real-world data, demonstrating its effectiveness in simulating diverse and realistic traffic behaviors, like stopping at red traffic lights, yielding to other vehicles during right-turn-on-red, and car following.

Autonomous vehicles (AVs) have the potential to prevent accidents caused by drivers’ errors and reduce road traffic risks. Due to the nature of heavy vehicles, whose collisions cause more serious crashes, the weights of vehicles need to be considered when making driving strategies aimed at reducing the potential risks and their consequences in the context of autonomous driving. This study develops an autonomous driving strategy based on risk anticipation, considering the weights of surrounding vehicles and using hierarchical deep reinforcement learning. A risk indicator integrating surrounding vehicles’ weights, based on the risk field theory, is proposed and incorporated into autonomous driving decisions. A hybrid action space is designed to allow for left lane changes, right lane changes and car-following, which enables AVs to act more freely and realistically whenever possible. To solve the above hybrid decision-making problem, a hierarchical proximal policy optimization (HPPO) algorithm with an attention mechanism (AT-HPPO) is developed, providing great advantages in maintaining stable performance with high robustness and generalization. An indicator, potential collision energy in conflicts (PCEC), is newly proposed to evaluate the performance of the developed AV driving strategy from the perspective of the consequences of potential accidents. The performance evaluation results in simulation and dataset demonstrate that our model provides driving strategies that reduce both the likelihood and consequences of potential accidents, at the same time maintaining driving efficiency. The developed method is especially meaningful for AVs driving on highways, where heavy vehicles make up a high proportion of the traffic.

Traffic safety, reliability, and resilience are significantly influenced by environmental factors such as visibility, road surface, and weather conditions. Yet, current monitoring methods, including weather stations and onboard environmental sensors, often fall short due to their high costs, significant latency, and limited dissemination. This paper presents the Edge-based Multi-task Safety-oriented Environmental (Edge-MuSE) sensing system, designed to address these traffic safety challenges associated with environmental factors. Edge-MuSE departs from traditional single-task sensing methods by performing multidimensional traffic environment perception tasks. It estimates key safety-related environmental factors exclusively through camera inputs and incorporates four innovative sensing tasks: visibility estimation, image dehazing, road segmentation, and road surface condition classification. The system is tailored to edge devices to transition computational loads from central servers to distributed nodes, thereby enhancing privacy and reducing latency. Additionally, Edge-MuSE integrates communication functions based on TCP/IP and Wi-Fi protocols, enabling rapid dissemination of sensing results and warning messages to local road users. System structures and data streaming have been optimized to accommodate the constraints of edge devices, ensuring high-efficiency edge computing. Field testing of Edge-MuSE in multiple testbeds in Bellevue (WA, US) and Oslo (Norway) has demonstrated its reliable and precise performance in perception tasks (92.15% accuracy in visibility estimation and 92.25% in road surface condition classification) as well as an impressive processing speed of 21.3 FPS. As such, Edge-MuSE presents a promising solution for enhancing roadway safety, efficiency, and resilience.

This study proposes a new multi-input multi-output optimal bilinear signal control method in which a bilinear dynamic model approximation is used to capture the nonlinear dynamics of the urban traffic networks. With signal green time splits as the control input and traffic delay changes as the output for each intersections in the network, a bilinear system model was developed, which, on the basis of linear system modeling, takes interactions among traffic delays and signal timing splits into consideration. Based on the bilinear system modeling framework, we conducted two steps in each time interval to derive traffic control strategies: (1) we used the normalized least-squared algorithm to estimate system parameters; and (2) we solved an online optimization problem to obtain the updated traffic control inputs for the signal timing that minimizes future traffic delays. We evaluated the proposed method in a microscopic traffic simulation environment (VISSIM) with a 35-intersection network of Bellevue city in Washington. Two different traffic demand patterns: (1) normal traffic demands; and (2) time-varying traffic demands were simulated to compare the performance of different control strategies. Experimental results show that (1) the proposed bilinear system model can better describe traffic system dynamics than linear-model based methods, such as our previously developed linear-quadratic regulator control; and (2) the proposed method outperforms the state-of-the-art signal control strategies, namely the max-pressure and the self-organizing traffic light control methods. We have also shown that the proposed method is applicable to all other possible network layouts and signal controller phasing structures.

Traffic signal control is important for intersection safety and efficiency. However, most traffic signal control methods are designed for individual intersections or corridors. Although some adaptive control systems have been developed, the methods used are often proprietary and not published, making it difficult to evaluate their effectiveness. This study proposes an adaptive multi-input and multi-output traffic signal control method that not only can improve network-wide traffic operations in terms of reduced traffic delay and energy consumption, but also is more computationally feasible than existing centralized signal control methods. Considering intersection interactions, a linear dynamic traffic system model was built and adaptively updated to reflect how the signal control input of each intersection affects network-wide vehicle travel delay. Based on the system model, an adaptive linear-quadratic regulator (LQR) was designed to minimize both traffic delay and incremental changes in the control input. The proposed control method was evaluated in a microscopic traffic simulation environment with a 35-intersection network of Bellevue City, Washington. Simulation results show that the proposed method had shorter average traffic delays in the network when compared with the traffic delays controlled by the state-of-the-art max-pressure, self-organizing traffic lights, and independent deep Q network methods.

Surveillance cameras are widely deployed traffic sensors, due to their affordable prices and being able to capture rich information. However, current surveillance systems have not been fully exploited: these cameras are isolated and can only extract information from their own fixed views. To enable a collaborative sensing system, we propose a novel framework called Traffic-Informed Multi-camera Sensing (TIMS) system for network-level traffic information estimation. By pushing multi-camera Re-IDentification (ReID) workflow towards network-wide traffic information extraction, TIMS system integrates a customized metric-learning vision-based vehicle ReID method (TIM-ReID) and establishing a traffic-informed workflow. To integrate the traffic network connection information along with visual and vehicle attributes features, the road network is extracted as a weighted graph through the Spatial-temporal Camera Graph Inference Model (StCGIM) and serves for matching and re-ranking ReID candidates. Moreover, an Accuracy Model (AAM) is designed to provide accurate, reliable and comprehensive traffic information estimation, including both the values and distribution of parameters under a high penetration rate. In experiments based on real-world multi-camera datasets captured in the city of Seattle, the customized TIM-ReID outperforms existing state-of-the-art methods, and delivers accurate cross-camera information estimation, whose value error is less than 8% and the Kullback-Leibler (KL) distance between the estimated and real distribution is less than 3.42 among all the evaluated camera pairs. TIMS system empowers cameras to work collaboratively through an interactive brain, and provides users with valuable and comprehensive traffic information.

Customized path-based speed prediction is an eventful tool for congestion avoidance, route optimization and travel time prediction for navigation apps, cab-hailing companies and autonomous vehicles. Traditionally, the speed prediction algorithms are based on road segments and can only support several main roads. Path-based speed prediction is very challenging since the speed is always changing in different path locations and is jointly affected by lots of complicated factors. This article presents a novel deep learning framework for customized path-based speed prediction. A Path-based Speed Prediction Neural Network (PSPNN) is designed to achieve speed predictions for a given path and attributes information. A hierarchical Convolutional Neural Network (CNN) and deep Bidirectional Long Short-Term Memory (Bi-LSTM) structure for different kinds of feature extraction are applied for multiple levels: the path cell, sub-path and the whole path. The method narrows down the prediction unit from road segments to customized path cells (mean length: 59.52m) and achieves a mean absolute error (MAE) of 1.94 m/s and Mean Absolute Percentage Error (MAPE) of 18.14%, showing the potential of serving rigorous data-driven applications. So far, PSPNN is the first made-to-order path-based speed prediction algorithm and can help both travelers and managers to obtain large-scale bespoke paths speed information in advance.

Real-time public transit ridership flow and origin-destination (O-D) information is essential for improving transit service quality and optimizing transit networks in smart cities. The effectiveness and accuracy of the traditional survey-based methods and smart card data-driven methods for O-D information inference have multiple disadvantages in terms of biased results, high latency, insufficient sample size, and the high cost of time and energy. By considering the ubiquity of smart mobile devices in the world, monitoring public transit ridership flow can be accomplished by passively sensing Wi-Fi and Bluetooth (BT) mobile devices of passengers. This study proposed a system for monitoring real-time public transit passenger ridership flow and O-D information based on customized Wi-Fi and BT sensing device. By combining the consideration of the assumed overlapping feature spaces of passenger and nonpassenger media access control address data, a three-step data-driven algorithm framework for estimating transit ridership flow and O-D information is proposed. The observed ridership flow is used as the ground truth for evaluating the performance of the proposed algorithm. According to the evaluation results, the proposed algorithm outperformed all selected baseline models and the existing filtering methods. The findings of this study can help to provide real time and precise transit ridership flow and O-D information for supporting transit vehicle management and the quality of service enhancement.

An effective forward collision warning (FCW) system must be compatible with drivers' risk perceptions and behavioral responses. The Collision Avoidance Metrics Partnership (CAMP) developed a kinematic-based FCW algorithm to determine the minimum distance needed to stop safely under various levels of rear-end crash risk. The algorithm generates a linear function for predicting drivers' expected response decelerations (ERDs) by considering motions of the involved vehicles. This linear function works well when the risks perceived by drivers are low; however, at elevated risks when the lead vehicle (LV) decelerates at an unexpectedly high rate, or at high relative speeds, the warnings are triggered too late for the subject vehicle to avoid a rear-end collision. The current study extends the CAMP FCW algorithm to improve the handling of extreme high-collision-risk scenarios. A total of 111 brake-only noncollision events was presented in the Tongji University Driving Simulator, and drivers' braking behaviors were used to model their ERDs. We found that ERDs depended on the interaction of LV deceleration and relative speed. In response to this finding, a nonlinear function with an interaction term was combined with a linear function into a piecewise function that accommodated both higher and lower LV deceleration conditions. The applicable domain of the warning onset range was then computed for a wide range of kinematic conditions. Results showed the piecewise function to be a better predictor of ERD than the linear function, as well as to result in fewer driver rejections of the FCWs.