Offline reinforcement learning plays a prominent role in reducing training costs in autonomous driving. However, owing to uncontrollable training-data distributions and high sensitivity policy-parameters, its generalization performance across scenarios exhibits large gaps. Considering risk–uncertainty adaptation, an offline context-aware reinforcement-learning vehicle-cloud end-to-end model for autonomous driving is proposed. For the original training set collected from the vehicle-end, a Diffusion-based Generative Experience Replay (DGER) mechanism is constructed in the cloud-end to expand the data. A real-time driving-risk potential field assessment module is built for uncertainty mapping offline reinforcement-learning parameters. Concurrently, a context-aware policy embedded with a Semantic Attention Encoder (SAE) is established, enabling the on-board control unit to switch and adapt across scenarios. Experiments are conducted on the CARLA simulation platform. Relative to baseline algorithms, the proposed method delivers improved stability, safety, efficiency, and fuel-efficiently. The capacity for precise control-action regulation under extreme conditions and the scene-parsing ability across different scenarios are also verified.

Camera-based Vehicle-Infrastructure Cooperative 3D object detection (VIC3D) faces challenges including cross-view feature misalignment caused by viewpoint discrepancies, as well as semantic degradation and redundancy introduced by direct feature concatenation. To alleviate these issues, a pure-visual 3D object detection framework, VAPE-Net, is proposed for VIC3D. The framework comprises two key modules: (1) A Viewpoint-Aware Enhancement (VAE) module is introduced on both the vehicle-side and infrastructure-side branches. Instead of requiring precise extrinsic matrices for rigid cross-view geometric alignment, it captures semantic and geometric consistency by modeling feature correlations across adjacent and cross-view frames while only conditioning on static camera metadata, thereby improving robustness under moderate calibration perturbations. (2) A Stage-wise Cascaded Feature Fusion (SCFF) module is used to fuse voxel features in multiple stages, with a balancing mechanism to reduce information loss and suppress noise during fusion. Experiments on the real-world DAIR-V2X dataset demonstrate that VAPE-Net has a significant advantage over common fusion methods, achieving 16.05%AP3Dand 22.03%APBEV. This research expands the model paradigm for cooperative perception dominated by vision, providing new insights and support for the theoretical framework of VIC3D.

The integration of connected and automated vehicles (CAVs) into traffic systems holds potential to mitigate undesired disturbances. Nevertheless, coexisting human-driven vehicles (HDVs) introduce complex behavioral disturbances, which has imposed critical challenges for control robustness. This study develops a computational framework based on policy iteration to derive robust control policies with optimized attenuation performance for nonlinear mixed traffic flow. Specifically, robust$H_{\infty }$control problem is solved by applying the framework of zero-sum game, whose solution at the Nash equilibrium is transformed into a Hamilton–Jacobi (HJ) inequality with a Hamiltonian constraint. For achieving desired attenuation performance, the value function is updated by gradient descent based on counterexamples violating Hamiltonian and monotonicity constraints, where the positive definiteness of the value function is ensured by convex neural networks, facilitating the analysis of control stability via Lyapunov methods. By utilizing constraint gaps, the attenuation level is optimized through the analytical formulae derived from the HJ inequality. The stability and algorithm convergence are proved. Experimental results demonstrate the capability of the learned controller to effectively attenuate disturbance propagation and stabilize mixed traffic flow.

Interacting with diverse and stochastic traffic participants is a critical challenge for autonomous vehicles (AVs), as it necessitates advanced decision-making systems to replicate the natural adaptability of human drivers. In particular, navigating safely and efficiently in dense traffic scenarios poses a significant challenge for decision-making, which is inherently an interactive task,i.e., nearby traffic participants will influence AVs’ action, and vice versa. Decision-making solutions that rely solely on unidirectional interaction schemes, neglecting the mutual influence between AVs and other traffic participants, may lead to overly defensive behaviors or the “freezing robot problem”. In recent years, researchers have been increasingly focused on incorporating bidirectional interactions into the decision-making process to make safe, intelligent, and socially compatible decisions. Currently, a comprehensive review of interaction-aware decision-making techniques remains lacking. To this end, this paper aims to provide a systematic review of interaction-aware decision-making methodologies for autonomous driving. Specifically, this paper analyzes the challenges in considering bidirectional interactions between AVs and other traffic participants. In addition, the state-of-the-art techniques for interaction-aware decision-making solutions are reviewed. More importantly, simulation and benchmarks for interaction-aware decision-making validation are also presented. Finally, research perspectives are highlighted to facilitate future studies for interaction-aware decision-making policy design.

The potential risks associated with various visual occlusion scenarios (VOS) vary greatly. For autonomous vehicles to make informed collision avoidance decisions, it is crucial to accurately assess the potential risk of each type of visual obstruction. However, this problem remains unresolved. In this paper, we simulate the data and knowledge driven cognitive mechanisms of human drivers and propose a human-like potential risk assessment method for VOS. During the perception phase, we move beyond the traditional image feature-based perception paradigm. Instead, we use natural language processing (NLP) to obtain textual semantic features of the scene as the perception result. Specifically, we utilize NLP techniques to construct a data driven VOS description model that generates textual descriptions of visible information in VOS as the perception result. In the risk assessment phase, inspired by human inductive and analogical reasoning, we develop a knowledge driven risk assessment model. Experimental results show that the proposed method can accurately assess the potential risks associated with different types of VOS, and in some cases, even identify risks up to 0.5 seconds earlier than human drivers.

An effective traffic signal control (TSC) strategy is critical for ensuring the safety and efficiency of intersections, particularly at large intersections that serve as key nodes within urban road networks. However, the implementation of real-time TSC at large intersections is more challenging than at regular ones, primarily due to the increased complexity of traffic conditions such as incomplete pedestrian crossings, as well as practical constraints in real-world applications, including the limited capacity of refuge islands. To address these challenges, we propose a novel adaptive TSC model based on deep reinforcement learning (DRL), specifically designed for large intersections with pedestrian two-stage crosswalks and refuge islands, aiming to reduce traffic risks and enhance operational efficiency. To achieve the above objectives, the model adopts a dual-network architecture, comprising two neural networks that collaboratively adjust signal phase and pedestrian clearance time according to real-time intersection conditions. In addition, considering the limited capacity of refuge islands in practical applications, an invalid action masking (IAM) method is also utilized to satisfy the associated spatial constraints. Several experiments are conducted to evaluate the performance of the proposed model. The results demonstrate that it reduces traffic risks by over 14.2% and 35.4% in two distinct scenarios, with only minimal impact on traffic efficiency. Moreover, the model effectively satisfies the capacity constraints of refuge islands, also demonstrating its practical value. Finally, a sensitivity analysis is also conducted to explore the model’s performance under different weight settings.

In an Autonomous Vehicle-Mixed Traffic Flow (AV-MTF) environment, accurately predicting vehicle speeds is essential for vehicle and traffic operation and management. However, existing research has not achieved high-precision vehicle speed prediction in mixed autonomous traffic environments. To address this, we proposed a car-following speed prediction and anomaly detection method based on the Attention-LSTM-Transformer model. We first employ a multihead attention enhanced LSTM network to dynamically classify vehicle categories in the AV-MTF environment based on vehicle motion states. We propose a novel Transformer-based model that embeds classification labels and car-following state information, enabling precise speed prediction in AV-MTF environments. Additionally, the anomaly detection algorithm is proposed to identify abnormal speeds in car-following situations, covering both constant and instant offsets. The proposed models were trained and tested using the OpenACC dataset, and the effectiveness of the Attention-LSTM-Transformer-based speed prediction model and anomaly detection algorithm is validated. Results show that the classification model achieves an accuracy of 95.57%. Compared to baseline models, the speed prediction model considering vehicle category labels effectively reduces the prediction errors by more than 6.8% in all horizons. This car-following speed anomaly detector achieves over 99% accuracy for constant speed offsets and nearly 90% detection rate for small instant speed anomalies. The findings of this study provide valuable insights for vehicle and traffic operation and management in future AV-MTF environments.

Autonomous driving (AD) is critically dependent on intelligent decision-making technology, which is the crucial ingredient in driving safety and overall vehicle performance. And comprehensive consideration of driving heterogeneity, decision synergy, and game interaction is also the cornerstones. Accordingly, this paper constructs a cooperative decision-making framework for autonomous vehicles (AVs) that integrates driving styles within a hierarchical architecture based on deep reinforcement learning (DRL). The upper layer adopts the action shielding mechanism-based dueling-double deep Q-network (D3QN) algorithm incorporating the lane advantages into shared state space to complete the prompt lane-changing (LC) decision, the lower layer applies the soft actor-3-critic (SA3C) algorithm based on the clipped triple Q-learning to provide the continuous speed adaptive control. Three personalized collaborative decision strategies are formulated for particular driving styles in multi-objective optimization preference combined with style-incentive prioritized experience replay (SIPER). The experimental results confirm that the proposed framework can satisfy the personalized driving demands in complex traffic scenarios, effectively explore the prospective LC opportunities, and enhance the driving efficiency by 35.40% with aggressive strategy and the comfort by 56.46% with defensive strategy compared with normal strategy, while maintaining the safety.

One of the primary challenges in urban autonomous vehicle decision-making and planning lies in effectively managing intricate interactions with diverse traffic participants characterized by unpredictable movement patterns. Additionally, interpreting and adhering to traffic regulations within rapidly evolving traffic scenarios pose significant hurdles. This paper proposed a rule-based autonomous vehicle decision-making and planning framework which extracts right-of-way from traffic rules to generate behavioural parameters, integrating them to effectively adhere to and navigate through traffic regulations. The framework considers the strong interaction between traffic participants mathematically by formulating the decision-making and planning problem into a differential game. By finding the Nash equilibrium of the problem, the autonomous vehicle is able to find optimal decisions. The proposed framework was tested under simulation as well as full-size vehicle platform, the results show that the ego vehicle is able to safely interact with surrounding traffic participants while adhering to traffic rules.

Driving on public roads is inherently an interactive task, i.e., autonomous vehicles’ (AVs) actions will influence nearby traffic participants’ reactions, and vice versa. Decision-making for AVs in highly interactive driving scenarios (e.g., dense traffic) requires accurately forecasting the impact of the AVs’ intention on nearby traffic participants’ motion. To this end, a hierarchical decision-making framework (HDM) is proposed to navigate through interactive scenarios safely and efficiently. Specifically, the upper layer of the HDM serves as a coarse-level policy generator, which utilizes the plan-informed graph attention network (P-GAT) to provide interaction-aware guidance. The P-GAT predictor takes the historical states of nearby traffic participants, road structure information, and AVs’ potential intentions as inputs. Subsequently, it predicts the motions of other traffic participants in response to potential actions of the AVs, which is then systematically evaluated to generate interactive guidance. Furthermore, the learned policy is utilized to guide the lower layer, which utilizes a fine-level model predictive control (MPC)-based planner to ensure safety and kinematic feasibility. Finally, to validate the effectiveness of HDM, both qualitative and quantitative experiments are carried out. More importantly, the hardware-in-the-loop (HiL) experiment is also implemented, including mandatory lane change in dense traffic flow and interaction with the human driver. The results demonstrate that the proposed HDM can improve driving safety and efficiency compared with baselines.

In this paper, we propose a new RGB-thermal image segmentation method based on parameter sharing and attention fusion for safe autonomous driving. An encoder-decoder network structure is adopted. The encoder, which has shared convolution layer parameters and private batch normalization layer parameters (parameter sharing scheme), is used to extract features from RGB and thermal images. The extracted features are then fused by spatial and channel attention. The output of each residual block is fused, and the self-learning weight is used to integrate the fusion information of all residual blocks of the same levels. Subsequently, the fused features are integrated through a feature integration (FI) module in the decoder. Cross-entropy supervision of segmentation and edge is performed on the outputs of the decoders. Our proposed method is evaluated and compared with 17 state-of-the-art image segmentation methods, both qualitatively and quantitatively on the MFNet dataset which includes various objects in urban scenes. The results show that the proposed method outperforms previous methods by at least 0.3% and 1.8% in MRecall and MIoU, respectively, providing foundations for the development of autonomous driving technologies for safety enhancement.

Autonomous techniques are becoming increasingly integrated into our daily lives. Many advanced driver assistance systems (ADAS), including functions like lane-keeping assist and car following, are already implemented in vehicles for controlled environments such as highways. However, to enhance the capabilities of current ADAS, it is essential to extend their application to more general scenarios, like urban driving. Urban environments pose considerable challenges due to the high density of traffic participants, including pedestrians and cyclists, whose behaviors are unpredictable and necessitate strong interactions with self-driving vehicles. Addressing these complex interactions through real-time decision-making is particularly challenging but crucial for effective operation in real-world urban settings. This paper aims to bring the decision-making process of autonomous driving techniques closer to real life by proposing a motion planning and decision-making framework that utilizes game theory to formulate and consider strong interactions. Additionally, we introduce a human-like attention-based traffic actor filter to enable the autonomous vehicle to focus on critical traffic participants with a higher risk of collision. The framework is tested in both simulation and real-world scenarios, demonstrating that the algorithm can make safe and efficient decisions under various traffic scenarios involving multiple types of traffic participants in real time.

The proper management of mixed traffic is crucial for unleashing the benefits of connected and automated vehicles (CAVs). Generally, the benefits of CAVs can be categorized into one-dimensional benefits in car-following performance and two-dimensional benefits in efficiently addressing right-of-way conflicts. Currently, the most effective approach to achieve this is by establishing a dedicated right-of-way for CAVs. However, existing strategies are limited to dedicated lane strategy, which can only unleash the one-dimensional benefits of CAVs while the two-dimensional benefits remain untapped. Therefore, this paper proposes a novel management approach for mixed traffic called the dedicated link strategy. The dedicated link refers to the road link that only allows CAVs to use. This strategy can unleash both the one-dimensional and two-dimensional benefits of CAVs via: (i) dedicated link deployment at the road network level and (ii) a novel intersection management approach. Specifically, at the macroscopic road network level, we introduce a bi-level dedicated link deployment model and design an artificial bee colony based algorithm to solve the optimal dedicated link deployment. At the microscopic intersection level, we develop a novel intersection management approach that integrates traditional traffic signal strategy with the emerging signal-free cooperative driving method, thereby boosting the efficiency of intersections. The macroscopic and microscopic methods will complement each other to achieve efficient management of network-wide mixed traffic systems. Finally, we verify the performance of the dedicated link strategy through comprehensive experiments. In essence, the proposed dedicated link strategy unifies the existing dedicated lane strategy and dedicated intersection strategy, providing a general solution for mixed traffic management.

Accurate forecasting of future traffic is a critical contemporary problem for transportation research. However, it is difficult to understand the feature patterns of traffic events due to the complexity of the traffic environment, heterogeneous factors, and lack of abnormal samples. This article proposes a framework to integrate the social traffic data and use the TabNet model to facilitate the representation learning task in traffic event prediction. With the tabular learning and model interpretability analysis, the importance of common traffic external factors toward traffic events is studied. The study has practical significance for regulating traffic planning and the development of the operational boundary for autonomous driving systems.

As one of the alternatives to conventional fuel vehicles, hybrid electric vehicles (HEV) offer lower fuel consumption and fewer exhaust emissions. To improve the performance of the HEV, the energy management strategy (EMS) is one of the most critical technologies. Classic EMS can be broadly classified into rule-based and optimization-based. With the development of machine learning technology, the deep reinforcement learning (DRL) algorithm of intelligent learning algorithms has been applied to the EMS. This paper mainly reviews the research progress of the EMS based on DRL from two aspects of the algorithm and training environment, and the EMS research involving combining the intelligent transportation system (ITS) is reviewed. In addition, the experimental test progress situations of DRL-based EMS research are discussed. Finally, the challenge of DRL-based EMSs is analyzed and some solutions are provided. In particular, it also involves some discussion about automotive cyber security in the intelligent transportation environment.

Left turning for autonomous vehicles at intersections is challenging due to the various driving behaviors from different human drivers and the strong interaction between the autonomous vehicle and human traffic participants. This paper proposes a planning and decision making framework for intersection left-turning which considers the interaction between autonomous vehicles and human drivers as well as pedestrians to address this issue. The proposed framework considers interactions mathematically by formulating the problem as a linear quadratic differential game. Through solving the Nash equilibrium of the game, the autonomous vehicle is able to properly interact with surrounding traffic participants. Under the differential game framework, the accuracy of the interaction formulation is closely related to the behavior model of human drivers. Therefore, real-world human behavior is extracted and evaluated from naturalistic driving dataset to help establish more realistic modeling and estimation of various kinds of traffic participants, including aggressive, neutral and conservative traffic participants. The simulation results show that the autonomous vehicle is able to properly estimate the types of traffic participants by observing their behavior using the proposed technique. Then the autonomous vehicle behave according to the types of those traffic participants to enable interactive and human-like planning and decision making at intersections.

Reinforcement learning (RL) has been widely used in the decision-making of autonomous vehicles (AVs) in recent studies. However, existing RL methods generally find the optimal policy by maximizing the expectation of future returns, which lacks distributional treatments of risky situations. Additionally, various uncertainties arising from the environment could also cause unreliable decisions, particularly in some complex urban environments. In this paper, the fully parameterized quantile network (FPQN) is utilized to estimate the full return distribution. Then, the conditional value-at-risk (CVaR) is utilized with the return distribution information to generate uncertainty-aware driving behavior. Additionally, an uncontrolled four-way intersection is developed by the Simulation of Urban Mobility (SUMO) simulation platform, which considers both the surrounding vehicles (SVs) and pedestrians. More specifically, to simulate the real-world traffic environment, the uncertainty arising from the occlusion, and the behavior uncertainty of surrounding traffic participants are also considered. The experiment results suggest that the proposed method outperforms the baseline methods in terms of safety. Furthermore, the results also indicate that the proposed method can make reasonable decisions in some challenging driving cases in the presence of uncertainty.

Connected and automated vehicles (CAVs) are expected to play a vital role in the emerging intelligent transportation system. In recent years, researchers have proposed various cooperative driving methods for CAVs, and there is an urgent need for a generic and unified traffic simulator to simulate and evaluate these methods. However, traditional traffic simulators have two critical deficiencies for CAV simulation needs: 1) the planning and dynamical modeling of vehicles in traditional simulators are based on a feedback mode, which is incompatible with the feed-forward decision and planning that CAVs commonly adopt; 2) the traditional simulators cannot provide typical traffic scenarios and corresponding standardized algorithms for multi-CAV cooperative driving. In this paper, we introduce CAVSim, a novel microscopic traffic simulator for CAVs, to address these deficiencies. CAVSim is developed modularly according to the emerging technology of the CAV environment, emphasizes feed-forward decision and planning for CAVs, and highlights the cooperative decision and planning components in the CAV environment. CAVSim incorporates rich and typical traffic scenarios and provides standardized cooperative driving algorithms and comparable performance metrics for multi-CAV cooperative driving. With CAVSim, researchers can conveniently deploy decision, planning, and control methods for CAVs at different levels, evaluate their performance, compare them with the standardized algorithms incorporated in CAVSim, and even further explore their impact on traffic flow. As a unified platform for CAVs, CAVSim can facilitate the studies on CAVs and promote the advancement of methods and techniques for CAVs.

Connected and automated vehicles (CAVs) have the potential to significantly improve the safety and efficiency of traffic. One revolutionary CAV’s impact on transportation system is cooperative driving that turns signalized intersections to be signal-free and boosts traffic efficiency by better organizing the passing order of CAVs. However, how to get the optimal passing order is an NP-hard problem (specifically, enumerating based algorithm takes days to find the optimal solution to a 20-CAV scenario). Here, we introduce a novel cooperative driving algorithm (AlphaOrder) that combines offline deep learning and online tree searching to find a near-optimal passing order in real-time. AlphaOrder builds a pointer network model from solved scenarios and generates near-optimal passing orders instantaneously for new scenarios. For the scenarios with 40 CAVs, AlphaOrder reduces the travel delay by more than 20% on average compared to the best-so-far MCTS based algorithm. Moreover, our algorithm provides a general approach to managing preemptive resource sharing between multi-agents (e.g., scheduling multiple automated guided vehicles (AGVs) and unmanned aerial vehicles (UAVs) at conflicting areas).

Advances in technologies, such as intelligent connected vehicles and the metaverse are driving the rapid development of automotive intelligent cockpits. From the perspective of the cyber–physical–social system (CPSS), this study proposed the intelligent cockpit composition framework which includes three layers of perception, cognition and decision, and interaction. Meanwhile, we also describe the relationship between the intelligent cockpit framework and the outside environment. The framework can dynamically perceive and understand humans, and provide feedback on the understanding results, which is beneficial to provide a safe, efficient, and enjoyable experience for humans in the intelligent cockpit. In the cognition and decision layers of the proposed framework, we design a case study of active empathetic auditory regulation of driver anger, focusing on improving road traffic safety. We conducted an in-depth interview experiment and designed two auditory regulation materials of active empathy speech and text-to-speech (TTS) speech. Next, 30 participants were recruited, and they completed a total of 240 anger-regulated driving experiments in the straight and obstacle avoidance scenarios. Finally, we quantitatively analyzed and compared the participants’ subjective feelings, physiological changes, driving behaviors, and driving risks, as well as validated the driver anger regulation quality of AES and TTS. The proposed research methods results are beneficial to the design of future intelligent cockpit emotion regulation systems, toward a better intelligent cockpit.

Distracted driving has been recognized as a major challenge to traffic safety improvement. This article presents a novel driving distraction detection method that is based on a new deep network. Unlike traditional methods, the proposed method uses both temporal information and spatial information of electroencephalography (EEG) signals as model inputs. Convolutional techniques and gated recurrent units were adopted to map the relationship between drivers’ distraction status and EEG signals in the time domain. A driving simulation experiment was conducted to examine the effectiveness of the proposed method. Twenty-four healthy volunteers participated and three types of secondary tasks (i.e., cellphone operation task, clock task, and 2-back task) were used to induce distraction during driving. Drivers’ EEG responses were measured using a 32-channel electrode cap, and the EEG signals were preprocessed to remove artifacts and then split into short EEG sequences. The proposed deep-network-based distraction detection method was trained and tested on the collected EEG data. To evaluate its effectiveness, it was also compared with the networks using temporal or spatial information alone. The results showed that our proposed distraction detection method achieved an overall binary (distraction versus nondistraction) classification accuracy of 0.92. In terms of task-specific distraction detection, its accuracy was 0.88. Further analysis on the individual difference in detection performance showed that drivers’ EEG performance differed across individuals, which suggests that adaptive learning for each individual driver would be needed when developing in-vehicle distraction detection applications. Note to Practitioners—Driver distraction detection is crucial for safety enhancement to avoid crashes caused by nondriving-related activities, such as calling and texting while driving. Related previous studies mainly focus on detection by monitoring head and eye movement using computer vision technologies or by extracting indicators from driving performance measures for driver state inference. However, complex traffic environments (e.g., dynamically changing light distribution on driver’s face and nighttime driving with low illumination) strongly limit the effectiveness of computer vision technologies, and the driving performance characteristics may also be caused by factors other than distraction (e.g., fatigue). To solve these problems, this article seeks to develop a deep learning-based approach to map the unique relationship between driver distraction and the bioelectric electroencephalography (EEG) signals that are not affected by traffic environments. The proposed method can be integrated into the driver assistance systems and autonomous vehicles to deal with emergency situations that need drivers to handle. The timely detection of distraction by our method will significantly facilitate its practical applications in collision avoidance or danger mitigation in the handover process.

Due to the growing interest in automated driving, a deep understanding on the characteristics of human driving behavior is critical for human-like autonomous vehicles. Among various driving behaviors, lane change is the most important one for vehicle lateral driving safety. This study proposes an unsupervised method to extract and discover the behavioral patterns of lane change maneuvers for the purpose of exploring the composed behavioral patterns during lane change. This method involves two phases: Firstly, the lane change sequences will be segmented into blocks using time-series segmentation algorithms. Three segmentation algorithms were utilized in this study. In the second phase, the segments will be clustered to find the corresponding behavioral pattern of each segment. Two extended latent Dirichlet allocation (LDA) models were adopted to cluster the segments. The combination of different segmentation and clustering algorithms were evaluated and compared by employing entropy and perplexity as the evaluation criteria. Collected lane change data from naturalistic driving were applied to examine its effectiveness. The results show that this method could effectively mine descriptive behavioral patterns from lane change data. This study provides a promising data mining solution to facilitating deep and comprehensive understanding on driver lane change behaviors, which will promote the development of human-like autonomous vehicles.

Most existing cellular probe-based freeway congestion detection methods rely on on-call WLT (Wireless Location Technologies) signal transition data. However, these techniques facing difficulties such as small sample size, frequent road tests, safety, and privacy issues. This article presents a novel approach using the FCA data for traffic congestion detection on freeways. Two cellular activity features, the link pseudo speed and link probe activity, are defined and calculated. A rule-based algorithm is then developed to determine the traffic congestion state. The proposed method has been implemented and a prototype system has been deployed for a major freeway corridor in China. Validated by fixed-point detector data and incident records, the proposed method is able to identify real-time freeway traffic congestion accurately.

The intersection is a critical traffic problem from the perspective of safety and traffic efficiency. As wireless communication technology advances, vehicle infrastructure cooperative approaches have received increased attention. In this paper, we propose a cooperative critical turning point method to help the cooperation between vehicles and infrastructures to improve the traffic efficiencies. The idea of cooperative critical turning point improves the cooperation between connected automated vehicles, the surrounding traffic and roadside infrastructures in order to provide high efficiencies of the intersection. An intersection management system using such a method is implemented based on the framework of the connected automated vehicle highway system. Such system can efficiently allow a roadside infrastructure receives state information from vehicles, reserve the associated intersection time-space occupancy, and then provide decision-making and planning feedback to the vehicles. The vehicles covered by the system then adjust their trajectories to meet their assigned time slot. The study validates the proposed system that considers the uncertainties of the driving environment by formulating the problem into a POMDP problem and solves it using an online solver. Based on preliminary simulation experiments, the proposed strategy can significantly reduce travel delays, decrease stops and improve the sustainability of the traffic system.

Though automated vehicles (AVs) are believed to play a crucial role in future transport, human driving vehicles will share the road with automated vehicles for a relatively long period. So, we need to enable automated vehicles to run along with human drivers especially when they may have conflicts in the right of way. One key problem is how to appropriately model human driving behaviors and quickly simulate their actions when training/testing automated vehicles. Many existing models were originally built for traffic flow studies and may not be suitable for automated vehicles studies. In this paper, we propose a set of new principles of human driving behaviors modeling and simulations. Then, we propose a Data-Driven Simulator (D2Sim) model for human behavior learning, description, and vehicle interaction simulation. In contrast to conventional microscopic traffic flow models, the D2Sim is a trajectory generation model that accepts rich driving environment information (e.g., lane geometry, crosswalks, traffic signals, surrounding vehicles, etc.). Different from many empirical trajectory records replay models, we can arbitrarily set the long-term intentions of the simulated vehicles and intentionally design the corner cases that had not been observed in practice. In addition, the D2Sim adopts adversarial learning to comprehend complex yet stochastic human driving behaviors from empirical data. Testing results show that the proposed model can quickly generate high-resolution trajectory data for training and testing.