Adverse weather conditions—such as rain, fog, and snow—significantly degrade LiDAR point cloud quality, causing substantial performance deterioration in detection models trained on clean data. To address this, we propose LTDNet, a novel point cloud quality improvement net-work that restores degraded LiDAR scans by learning an end-to-end mapping from corrupted to clean geometry. LTDNet leverages position encoding, spatial–frequency joint feature extraction, weather-aware refinement, and probabilistic pruning to effectively recover structural in-tegrity while suppressing weather-induced noise. To fa-cilitate standardized evaluation, we introduce IQA3D, a new benchmark comprising both synthetic and real-world sequences under adverse weather. This dual-design benchmark serves two complementary purposes: synthet-ic sequences provide pixel-wise correspondences between degraded and clean point clouds for quantitatively as-sessing restoration fidelity, while real-world sequences enable evaluation of the practical impact of improvement methods on downstream 3D object detection under au-thentic weather conditions. This makes IQA3D particular-ly suitable for jointly measuring both perceptual quality and task-level robustness of point cloud improvement models. Extensive experiments on IQA3D demonstrate that LTDNet significantly improves detection perfor-mance across various state-of-the-art 3D detectors and three tested weather conditions, making it a practical and effective solution for robust LiDAR-based detection.

Feature selection is a critical step in data mining, with the granular ball rough set model widely applied in this area. However, the randomness issue during the initialization of the existing fuzzy granular ball rough set algorithm may lead to the loss of samples during the feature measurement process. Additionally, it also lacks consistency in handling fuzzy samples in different regions of the granular ball, which further weakens the classification performance of high-dimensional fuzzy data. To this issue, we propose a fuzzy advantage granular ball rough set feature selection algorithm via deep reinforcement learning. First, to reduce the randomness in the generation process of granular balls, the center generation method is optimized by defining sample aggregation degree and spacing. Second, to enhance feature credibility, the granular ball advantage degree is constructed and integrated with purity to evaluate feature importance. Third, to improve the handling of fuzzy samples, a deep reinforcement learning mechanism is introduced to uniformly process the fuzzy samples. Finally, a feature selection algorithm (FGFSD) suitable for high-dimensional fuzzy data is proposed. Evaluated on 20 benchmarks, FGFSD achieves a feature reduction rate of 65% on low-dimensional datasets and up to 99.6% on high-dimensional datasets. Furthermore, it attains a mean accuracy of 0.9459, surpassing the suboptimal feature selection method's 0.9013 by 4.95%.

Merging roadways are a major source of conflict and congestion, and can increase risk of collision, and fuel consumption. Coordinating merging of connected and automated vehicles (CAVs) in on-ramp scenarios can improve traffic efficiency, increase safety, and reduce the negative environmental impacts. In our previous work, a multi-player game-based centralized optimization algorithm was proposed to achieve global optimization of merging sequences and the decentralized non-linear model predictive controller was proposed for tracking optimal trajectory in the vehicle lower-level. This paper addresses the problem of developing a longitudinal and lateral cooperative motion control for CAVs merging at on-ramps. The vehicle longitudinal and lateral kinematics was decoupled by feedback linearization method to be linear uncorrelation. Quadratic of longitudinal and lateral virtual accelerations are used as the optimal objective to reduces the fuel consumption. A decentralized optimization of longitudinal and lateral cooperative control method was proposed and the analytical solution considering the strict input constraint was derived. Efficiency of the proposed cooperative method was validated by simulation. The proposed decentralized merging control system can improve traffic efficiency and reduce fuel consumption with the potential for real-time application.

With Petri nets, this paper aims to design a fast response and recovery strategy for abnormal situations where some of right-of-way (ROW) resources are not available due to accidents, thereby enhancing the resilience of unsignalized autonomous intersections. First, based on the analysis of vehicle trajectory characteristics at intersections, we extend the semantic types of places in classical Petri nets and propose the ROW resource Petri net (RRPN) for modeling fundamental autonomous intersections. Then, we introduce lane change transitions and establish a failure and recovery model for a failed ROW. With these two models, the RRPN with resource failure and recovery (RRPN-FR) model for autonomous intersections is built. Subsequently, based on the RRPN-FR model, we introduce maximal perfect resource transition circuit (MPC) and resource recovery circuit (RRC), and analyze the deadlocks caused by these two structures. Then, we introduce the notion of enhanced transition cover and design a resilient intersection control strategy based on the enhanced transition cover. It formally shows that this control strategy can enhance the resilience of a controlled intersection, effectively responding to unexpected situations and abnormal traffic conditions, which in turn prevents traffic congestion. Simulation experiments and comparative analysis further validate the effectiveness of the proposed control strategy in the failure and recovery process and overall performance. Model is available at:https://github.com/yaxwei/Supplement/blob/TITS/SupplementaryMaterials.pdf

In the context of rapid advancements in the automotive industry and intelligent transportation systems, assessing cognitive load during driving has become a key factor for driving safety and user experience. This paper presents a comprehensive narrative review of theories, methods, and technological advancements in assessing cognitive load during driving. Rather than following a systematic review protocol,the structure of the review is organized around key research questions and critical gaps identified in the current literature. We assess the applicability and performance of major evaluation methods, including physiological indicators, behavioral measures, subjective self-report scales, and data-driven approaches, across various driving scenarios. The review also discusses the integration of multi-source information and propose a conceptual framework for holistic and adaptive cognitive load assessment. Furthermore, it highlights challenges in current practices, such as technical constraints, environmental variability, and individual differences. Special emphasis is placed on the relevance of cognitive load assessment for industrial informatics, particularly in the context of advanced driver assistance systems (ADAS), autonomous driving technologies, and driver training programs. This review aims to provide a structured synthesis of current approaches, offer practical insights for application and system design, and guide future research toward developing more robust, generalizable, and context-aware assessment tools. By analyzing the state of the art, we contribute a timely reference to support both academic development and industrial implementation for next-generation intelligent vehicle systems.

LiDAR is widely used in autonomous driving and intelligent roadside perception systems due to its high detection accuracy and light independence. However, snowfall has a significant impact on LiDAR, increasing noise and changing object resolution in point clouds, posing a significant challenge to the task of traffic object detection using LiDAR. This paper proposes a probabilistic model-driven adaptive filter for effectively removing snowfall noise from LiDAR point clouds and improving LiDAR detection capabilities under snowfall conditions. First, the proposed filter extracts snow noise from a point cloud, creates a spatial distribution model for the snow noise, and obtains the model’s key parameters. Then, the snow noise is extracted using a density filter based on the spatial model, which is iteratively optimized. Compared to existing methods, the filter is more scene-adaptable and less dependent on priori datasets, and it can effectively remove snow noise from various types of LiDAR sensors under varying snowfall intensities. Experimental evaluation on publicly available datasets, including CADC, BOREAS, and WADS, demonstrates that the proposed method achieves an F1-Score of more than 90 on all three datasets, indicating excellent accuracy and generalizability. Additionally, testing object detection algorithms under snowfall conditions reveal that the proposed filter improves the accuracy of three typical detection algorithms by 5.9, 9.7, and 6.4 percentage points, indicating that our filter improves the performance of downstream 3D target detection tasks under snowfall.

Human–machine co-driving is expected to be a long-term driving mode. However, existing cooperative steering control strategies often struggle to effectively handle human–machine interaction conflicts and dynamically allocate driving authority, making it difficult to balance safety and driver’s comfort. To address these issues, this article establishes a Stackelberg game-based model predictive control (MPC) framework and derives a human–machine optimal control strategy under the equilibrium conditions. Furthermore, a two-layer adaptive authority allocation model is developed using the deep deterministic policy gradient (DDPG) method, which comprehensively considers environmental risks, human–machine conflict, and driver’s states. This model prevents a vehicle from entering an unstable state by dynamically allocating the driving authority to both the human driver and the autonomous driving system. Results from driver-in-the-loop experiments indicate that, in obstacle avoidance scenarios, the proposed control strategy enhances vehicle driving stability by 31.49%, improves control stability by 48.11%, and reduces the driver’s burden by 42.87%, demonstrating that the proposed strategy can assist the driver in completing obstacle avoidance tasks and ensure driving safety in high-risk scenarios. In low-risk scenarios, it maintains the driver’s freedom, prevents excessive intervention from the autonomous driving system that could lead to significant human–machine conflicts, and alleviates the driver’s operational burden.

Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to high computational overhead. To mitigate computation cost, some researchers propose window attention based sparsification strategies to discard unimportant regions, which sacrifices the global modeling ability and results in suboptimal performance. To achieve better trade-off between accuracy and efficiency, we propose Sparse Mamba (SMamba), which performs adaptive sparsification to reduce computational effort while maintaining global modeling capability. Specifically, a Spatio-Temporal Continuity Assessment module is proposed to measure the information content of tokens and discard uninformative ones by leveraging the spatiotemporal distribution differences between activity and noise events. Based on the assessment results, an Information-Prioritized Local Scan strategy is designed to shorten the scan distance between high-information tokens, facilitating interactions among them in the spatial dimension. Furthermore, to extend the global interaction from 2D space to 3D representations, a Global Channel Interaction module is proposed to aggregate channel information from a global spatial perspective. Results on three datasets (Gen1, 1Mpx, and eTram) demonstrate that our model outperforms other methods in both performance and efficiency.

Recently, deep convolutional neural networks (DCNN) have been widely used in semantic segmentation tasks and have achieved high segmentation accuracy. However, most algorithms based on DCNN have high computational complexity, making them unsuitable for real‐time segmentation. To solve this problem, this paper proposes a real‐time semantic segmentation algorithm based on the STDC network. The algorithm adopts an “encoder–decoder” embedded in a U‐shaped architecture to realize real‐time segmentation while maintaining high accuracy. Following the encoder, a mixed pooling attention module is designed to expand the receptive field, enhancing the network model’s learning ability in complex scenarios. Then, a feature fusion module is used for combining features from different stages, and channel attention based on atrous convolution is employed to expand the receptive field and avoid dimensionality reduction learning. Finally, a Tversky‐based detail loss function is used to encode more spatial details. The proposed algorithm was extensively tested on the challenging Cityscapes and CamVid datasets, and the experimental results showed that the proposed algorithm obtained 76.4% and 72.8% of mIoU, respectively. Meanwhile, our algorithm achieves 105.2 FPS and 165.6 FPS inference speed with a single NVIDIA GTX 1080Ti GPU, meeting the real‐time segmentation requirements. The proposed algorithm can conduct real‐time segmentation while maintaining high accuracy, achieving a good balance between accuracy and speed.

Effectively leveraging data and domain knowledge remains a significant challenge in controlling the Internet of Unmanned Agent (IUA). This article proposes a novel multiagent deep reinforcement learning-based cooperative control model called MARL-CTV to efficiently control two key IUA agents: 1) connected and automated vehicle (CAV) and 2) controllable traffic signal light (TSL). The CAV agents are controlled by the deep deterministic policy gradient (DDPG) algorithm, and the TSL agent is controlled by a dueling double deep Q-network (D3QN). To reduce the control burden and ensure the cumulative reward converges, the actor and critic networks are pretrained by the expert dataset, and the expert dataset initializes the experience replay buffer of DDPG. This dataset is generated by multiple velocity profiles derived from a genetic algorithm (GA) based on various random initial states of CAVs. Numerical experiments conducted using a joint simulation platform composed of SUMO and CARLA and real-world data from CitySim demonstrate the effectiveness of MARL-CTV. Specifically, when the market penetration rate (MPR) of CAV is 35%, MARL-CTV enables most CAVs to pass through the signalized intersection without stop-and-go behavior, reducing average travel time by 24.2%, fuel consumption by 22.7%, and the traffic conflicts by 68.3%.

The rapid development of autonomous driving and robotics has led to increasingly higher demands for high-precision localization, making it an indispensable key component of modern autonomous systems. High-definition maps have become widely used to enhance localization accuracy, particularly in complex and dynamic environments. However, persistent challenges such as sensor measurement errors, environmental drift, and inaccuracies remain, making place recognition an increasingly critical research focus. This paper introduces a novel place recognition method based on a complex number framework, wherein environmental features are stored in both the real and imaginary parts of a complex number. This innovative approach significantly improves the richness and accuracy of environmental descriptions, thereby enhancing the system’s ability to distinguish between highly similar environments. Furthermore, a descriptor similarity evaluation strategy based on the angle between complex number vectors is proposed, which enhances the distinction of descriptors, especially in scenarios where the environments share similar characteristics, thus reducing the likelihood of mismatches. To ensure real-time performance, a hierarchical retrieval filtering process is introduced that effectively combines both coarse and fine-grained search strategies, optimizing the KD-Tree search and filtering out irrelevant matches. Experimental results on public datasets and real-world vehicle data across diverse scenarios validate the proposed method’s effectiveness and robustness, showing notable gains in recognition accuracy and real-time performance in complex environments.

A deep reinforcement learning-based method for planning the lane-changing trajectory of connected and automated vehicles (CAVs) is proposed to increase traffic efficiency and reduce fuel consumption. The long-short-term-memory-based twin delayed deep deterministic policy gradient (LSTM-TD3) algorithm is implemented and trained to achieve the optimal longitudinal and lateral lane-changing trajectory. The instantaneous fuel consumption and the desired speed and acceleration difference are used as reward and penalty terms. The effectiveness of the algorithm was verified through real data based typical lane-changing scenarios using CARLA software. The results indicate that the proposed LSTM-TD3-based lane-changing planning method reduced fuel consumption by 6.36% compared to TD3, 9.84% compared to LSTM-DDPG, and 26.31% compared to DDPG. Compared to TD3, LSTM-DDPG, and DDPG, the completion time for lane-changing is reduced by 0.18s, 0.15s and 0.2s, respectively. The success rate of trajectory planning has also increased compared to other algorithms. Furthermore, the results demonstrate the potential of deep reinforcement learning technologies in the control and applications of CAVs.

Coordination at unsignalized intersections has attracted increasing attention in recent years, which aims at improving the efficiency of intersection operations, while eliminating conflicts and deadlocks for Connected and Automated Vehicles (CAVs). This paper addresses the challenging issue of systematically optimizing CAV trajectories, tackling the high computational cost for finding a good solution, especially as the number of lanes and CAVs increases. To do so, a novel systematic optimal trajectory planning model is designed to efficiently guide CAVs through intersections without conflicts and deadlocks. To tackle the computational hurdles and enable real-time applications, based on the model, we develop a Petri net-aided Iterative Trajectory Optimization (P-ITO) solution algorithm. Leveraging the unique characteristics of the problem, this algorithm first designs a Petri net-based controller for conflict and deadlock avoidance so that initial feasible solutions are generated. Then, refinement is made on the initial feasible solutions to obtain an optimal or near optimal solution by designing an iterative process. This algorithm effectively ensures solution feasibility and enhances computing efficiency by searching for an optimal solution in the feasible region. Numerical experiments for intersections with bidirectional six-lane configurations illustrate the efficacy of our model in facilitating the safe and efficient passage of all CAVs while mitigating the risk of deadlocks. The P-ITO algorithm significantly outperforms the commercial solvers in both solution quality and computational time. Furthermore, our method is versatile, applicable to diverse intersection scenarios, and capable of maintaining high computational efficiency.

As cities and traffic become increasingly digitized, vehicle retrieval technology has emerged as a vital component of Intelligent Transportation Systems (ITS), aiming to identify target vehicle tracks or clips from calibrated road cameras. Recently, the task of text-based vehicle retrieval has garnered increasing attention, which is more applicable compared to image-based vehicle retrieval, i.e., vehicle re-identification. However, the text-based vehicle retrieval is also facing great challenges due to the huge semantic gap between images and texts. In this paper, we propose a novel method, called multi-level alignment over aggregation semantic graph with attribute enhancement (MAGAE), for text-based vehicle retrieval task. Specifically, we employ large language models (LLMs) and pretrained visual models to extract global vision and text feature embeddings, respectively. Then, an F-Encoder architecture is developed to dynamically integrate local and global features of vehicles. Furthermore, we design a co-attention learning mechanism to extract and enhance the robustness of vehicle attribute embeddings. Additionally, a multi-level semantic graph alignment module is introduced to effectively bridge the significant gap between vision and text through attribute aggregation and interaction. Finally, to improve the learning capacity of the network, we employ the merits of multi-task learning by incorporating four learning loss functions. Experimental results on the CityFlow-NL benchmarks validate the effectiveness of the proposed model. Findings of this study may assist urban traffic management, particular in providing guidance in capturing hit-and-run vehicles.

Proper planning of charging infrastructure can significantly facilitate the popularization of electric vehicles and alleviate users’ mileage anxiety. Charging station siting and sizing are two key challenges in the planning with each of them being a complex optimization problem. In this paper, a multi-objective optimization approach is proposed to solve them together. First, considering that accurate charging demand estimation is crucial for planning, a traffic road network is established for this purpose. A Monte Carlo method is used to estimate the spatiotemporal distribution of charging demand in a region based on the probabilistic characteristics of user trips. Since uncoordinated charging not only increases the load but also leads to unstable operation of the local power system, a heuristic algorithm is proposed to coordinate charging scheduling. Then, based on the scheduled demand, this paper proposes a framework for the siting and sizing of charging stations to optimize the benefits for both operators and users by minimizing the construction, operation and maintenance costs, and the user’s detour time. As the given problem is a complex multi-objective combinatorial optimization problem, it is easy to fall into local optimum if traditional evolutionary algorithms are employed. Therefore, a multi-objective dynamic binary particle swarm optimization method is designed to solve this problem effectively. Finally, experimental simulations show that the proposed method outperforms the other comparative algorithms in terms of solution quality. A case study is presented to demonstrate the applicability and effectiveness of the proposed method in optimizing the location and capacity of charging stations.

Lidars and cameras are critical sensors for 3D object detection in autonomous driving. Despite the increasing popularity of sensor fusion in this field, accurate and robust fusion methods are still under exploration due to non-homogenous representations. In this paper, we find that the complementary roles of point clouds and images vary with depth. An important reason is that the point cloud appearance changes significantly with increasing distance from the Lidar, while the image's edge, color, and texture information are not sensitive to depth. To address this, we propose a fusion module based on the Depth Attention Mechanism (DAM), which mainly consists of two operations: gated feature generation and point cloud division. The former adaptively learns the importance of bimodal features without additional annotations, while the latter divides point clouds to achieve differential fusion of multi-modal features at different depths. This fusion module can enhance the representation ability of original features for different point sets and provide more comprehensive features by using the dual splicing strategy of concatenation and index connection. Additionally, considering point density as a feature and its negative correlation with depth, we build an Adaptive Threshold Generation Network (ATGN) to generate the depth threshold by extracting density information, which can divide point clouds more reasonably. Experiments on the KITTI dataset demonstrate the effectiveness and competitiveness of our proposed models.

Autonomous vehicles have stridden over the budding stage and are stepping into the phase of large-scale commercial deployment. Nonetheless, safety issues of autonomous driving remain to be fully solved. Sensor data provide the observations of the internal status and the driving environment of the autonomous vehicle, and sensor data anomaly detection is indispensable to ensure the safety since the occurrence of sensor data anomalies indicate potential safety risks. Tremendous works has contributed to the sensor data anomaly detection issue but most of them ignore the trustworthiness estimation of the anomaly detection results, leading to difficulties for decision-making in safety-critical systems. Therefore, this work proposes an uncertainty-aware sensor data anomaly detection method to enhance the trustworthiness of anomaly detection results. Specifically, this method includes a Bayesian LSTM prediction network that outputs both the predicted values and the distribution of the predicted values, an anomaly uncertainty quantification method, and an adaptive thresholding method to improve the anomaly detection performance. Anomaly detection is achieved by capturing the predicted values with high uncertainty. The efficacy and robustness of the proposed methodology have been substantiated through empirical field tests conducted with real-world autonomous driving vehicles. The evaluation yielded a recall of 0.893 and an F1-Score of 0.937, which underscores the superior anomaly detection capabilities of the approach within practical autonomous driving contexts.

Motion forecasting plays a pivotal role in autonomous driving systems, enabling vehicles to execute collision warnings and rational local-path planning based on predictions of the surrounding vehicles. However, prevalent methods often assume complete observed trajectories, neglecting the potential impact of missing values induced by object occlusion, scope limitation, and sensor failures. Such oversights inevitably compromise the accuracy of trajectory predictions. To tackle this challenge, we propose an end-to-end framework, termed Multi-scale Transformer (MSTF), meticulously crafted for incomplete trajectory prediction. MSTF integrates a Multiscale Attention Head (MAH) and an Information Increment-based Pattern Adaptive (IIPA) module. Specifically, the MAH component concurrently captures multiscale motion representation of trajectory sequence from various temporal granularities, utilizing a multi-head attention mechanism. This approach facilitates the modeling of global dependencies in motion across different scales, thereby mitigating the adverse effects of missing values. Additionally, the IIPA module adaptively extracts continuity representation of motion across time steps by analyzing missing patterns in the data. The continuity representation delineates motion trend at a higher level, guiding MSTF to generate predictions consistent with motion continuity. We evaluate our proposed MSTF model using two large-scale real-world datasets. Experimental results demonstrate that MSTF surpasses state-of-the-art (SOTA) models in the task of incomplete trajectory prediction, showcasing its efficacy in addressing the challenges posed by missing values in motion forecasting for autonomous driving systems.

Traffic object detection under variable illumination is challenging due to the information loss caused by the limited dynamic range of conventional frame-based cameras. To address this issue, we introduce bio-inspired event cameras and propose a novel Structure-aware Fusion Network (SFNet) that extracts sharp and complete object structures from the event stream to compensate for the lost information in images through cross-modality fusion, enabling the network to obtain illumination-robust representations for traffic object detection. Specifically, to mitigate the sparsity or blurriness issues arising from diverse motion states of traffic objects in fixed-interval event sampling methods, we propose the Reliable Structure Generation Network (RSGNet) to generate Speed Invariant Frames (SIF), ensuring the integrity and sharpness of object structures. Next, we design a novel Adaptive Feature Complement Module (AFCM) which guides the adaptive fusion of two modality features to compensate for the information loss in the images by perceiving the global lightness distribution of the images, thereby generating illumination-robust representations. Finally, considering the lack of large-scale and high-quality annotations in the existing event-based object detection datasets, we build a DSEC-Det dataset, which consists of 53 sequences with 63,931 images and more than 208,000 labels for 8 classes. Extensive experimental results demonstrate that our proposed SFNet can overcome the perceptual boundaries of conventional cameras and outperform the frame-based methods, e.g., YOLOX by 7.9% in mAP50 and 3.8% in mAP50:95. Our code and dataset will be available athttps://github.com/YN-Yang/SFNet.

Light detection and ranging sensors (LiDARs) have become indispensable for autonomous vehicles because of their high detection accuracy and independence from lighting conditions. At present, although LiDARs with various beams have been developed, their performance is degraded to varying degrees in severe weather such as rain and snowfall. This restricts the reliable operation of autonomous vehicles in all weather and all scenes. To quantitatively evaluate the impact of snow on LiDAR performance, this paper creates and publishes a LiDAR point cloud dataset (MSP dataset) covering different LiDAR models, snowfall intensities, and test scenarios. Through theoretical and data-driven analysis, the influence of snow on the performance parameters of LiDAR, such as point cloud distribution, detection range, and sensing accuracy, is evaluated qualitatively and quantitatively. The experimental results show that the presence of snow induces a significant amount of noise in LiDAR systems. The level of noise varies with distance and height, following the Gamma and t location-scale distributions, respectively. During heavy snowfall, the recognition of vehicles and pedestrians by LiDARs is reduced by 50% and 20%, respectively. The target detection accuracy is reduced by about 9 percentage points, and the effective detection distance is reduced by 14-17m. The sensing performance of LiDAR will be significantly reduced within the range affected by snowflake noise. The research results of this paper provide important data and a theoretical basis for evaluating the performance of LiDAR-based autonomous driving systems during snowfall conditions and designing corresponding LiDAR sensing and processing methods.

Cameras, millimeter-wave radars, and lidars are widely deployed on smart roads to obtain personalized vehicle trajectories for advanced traffic control and risk avoidance. However, these asynchronous roadside sensors need to be spatiotemporally calibrated accurately before they are put into service. Traditional manual manipulation methods are inefficient and will affect traffic operation and safety. A rapid and convenient method has become essential under the trend that large amounts of roadside sensors need to be tested and calibrated frequently. As more and more connected and automated vehicles (CAVs) flood the smart roads, this paper proposes a novel spatiotemporal calibration framework using the positioning and perception data of CAVs. First, a trajectory matching algorithm is designed using motion feature and point feature histogram sequences as the descriptors, which can determine the approximate spatiotemporal correspondence for the CAV from the roadside trajectory dataset. An optimization method is then formulated to tune transformation parameters through the Gaussian Process trajectory representation and Gauss-Newton algorithms, considering the sampling frequency deviation and measurement noise. Based on numerical analysis via the NGSIM and HighD datasets, it is shown that the proposed calibration method can significantly reduce transformation errors and perform robustly in different scenarios. The feasibility and practicability of the calibration method are further validated through real-world experiments at Tongji University and on the Donghai Bridge in Shanghai, China. This study provides an economical and practical way for spatiotemporal calibration of roadside sensors in an era of CAVs.

Improving the performance of autonomous vehicles in adverse weather conditions is vital for the commercialization of such automated systems. Existing synthetic datasets for developing rain-tolerant vision are of limited value. To address this deficiency, a closed environment capable of simulating different degrees of rainfall is constructed. And a new Closed Field Rain dataset is collected in 36 testing cycles. Inspired by the idea that human can infer the content of rainy images directly without removing the raindrops. A new single-image deraining method is proposed, that does not require ground truth images . This method incorporates an image content estimation module applied to predict the scene content representation, and a pixel-wise content attention block used to evaluate the significance of each pixel. After that, an encoder-decoder network is applied to complete the image. On the other hand, it is almost impossible to obtain the ground truth of rainy images because of the dynamic characteristics of real traffic environment. Thus, the model is trained by employing PatchGAN, using a patch-based loss. Using common no-reference and feature point metrics as performance indicators, this paper conducts a comprehensive evaluation on both synthetic and real-world datasets including Closed Field Rain dataset. Results show the effectiveness of our model quantitatively and qualitatively.

Effectively extracting features from a discrete point cloud is necessary for three-dimensional (3D) vehicle tracking. However, a point cloud data set is large and sparsely distributed, hindering the success of vehicle-tracking algorithms. To solve this problem, this paper proposes a 3D vehicle object tracking algorithm based on bounding box similarity measurement. The algorithm includes state prediction, temporal association, trajectory management, state update, and other processes. Also incorporated is a vehicle object temporal association method based on a siamese encoder. The bounding box is encoded into a high-dimensional space, the feature distance is calculated as the time series association cost, and triplet loss was introduced to urge the encoder to learn the geometric similarity of the truth matching box. A 3D Kalman filter and greedy matching are used to effectuate 3D vehicle object tracking algorithm. The experimental results using a KITTI multi-object tracking dataset show that the proposed algorithm can achieve good vehicle tracking performance. In the case of frame loss of point cloud in the frequency reduction simulation, compared with the benchmark method AB3DMOT, the average multi-object tracking accuracy (AMOTA) and the average multi-object tracking accuracy (AMOTP) of the improved method are increased by 2.62% and 1.41% respectively, and the performance is better in the frame loss scene.

To address the problems of low resolution and blurred details in highway images caused by factors such as rain and fog, illumination interference, and nighttime lighting, this paper proposes a highway traffic image enhancement algorithm based on improved GAN in complex weather conditions. The attention mechanism and the multiscale feature fusion were combined to improve the generator network, which could effectively reduce noise while improving the attention of high-frequency region information. The improved PatchGAN in the discriminator used a local discrimination strategy to distinguish the generated image from the real image, and then the Nash equilibrium was achieved through the continuous interaction between the generator and the discriminator, to ensure the integrity and authenticity of the restored image. Compared with other image enhancement algorithms, using PSNR and SSIM as measurement indicators, the experimental results showed that the proposed algorithm’s results were, respectively, 21.97% and 12.89% higher in nighttime enhancement, 26.16% and 12.75% higher in rain removal, and 26.56% and 12.1% higher in fog removal. The proposed algorithm can not only retain the image details and feature information, but also produce effective denoising, which increases the reliability of image-based traffic information processing and analysis.

Capturing the evolution mechanism of traffic dynamics is of great significance when alleviating traffic congestion and improving traffic efficiency. While several studies have presented stability analyses of various traffic systems, most have relied on linear analysis methods, which cannot capture the complex nonlinear dynamic behavior of heterogeneous traffic flow. To address this shortcoming, this paper derives a generic Hopf bifurcation structure that can be applied to multiclass traffic models. The proposed bifurcation structure is investigated to understand the characteristics of heterogeneous traffic flow in a connected and autonomous environment as case studies. The results, based on selected on- field calibrated traffic models, show that (i) the linear analysis results deviate significantly from the actual instability of the mixed traffic system, which illustrates the necessity of a bifurcation analysis; and (ii) connected human-driven vehicles and connected autonomous vehicles have the ability to alleviate the formation and propagation of traffic oscillations. Finally, the theoretical analysis results are verified through simulation experiments.

This paper mainly addresses the issue of designing safety Petri net-based controllers to prevent vehicle flow deadlocks at intersections. The designed controller can monitor the flow of vehicles at an intersection and guide them to pass an intersection safely without causing deadlocks. This study begins by investigating the intersection deadlock scenarios, analyzing the physical size of the “right-of-way” cells with the discretization of the interior area of an intersection, and developing the intersection initial Petri net (PN) model based on simple sequential processes with resources (S3PR). Then, based on the initial PN model, we propose a deadlock prevention strategy for controller design to control the vehicle flows to ensure that the vehicle flows in different directions do not result in deadlocks. Finally, the effectiveness of the proposed strategy is illustrated by examples and theoretical proof. This study contributes to the advancement of the state-of-the-art in the design of safety controllers for self-driving vehicles passing through intersections.

Ramp merging represents a bottleneck scenario that causes traffic congestion, accidents, and increases emissions. Connected and Automated Vehicles (CAVs) can realize the coordinated control of ramp merging through vehicle-to- infrastructure (V2I) for relieving above problems. Considering the previous studies on centralized ramp merging only involved single mainline, this paper proposes a multi-lane centralized collaborative control strategy using cooperative game. First, the merging rules of different lanes of vehicles in the merging area are defined, so that the vehicles can achieve the cooperative merging safely. Second, driving efficiency, comfort, and fuel consumption in the merging control zone are used as the cost function. The best merging sequences of vehicles in different lanes are solved by cooperative game. Finally, analytical solution of longitudinal optimal control for all vehicles is obtained by applying the Pontryagin principle. The effectiveness of the proposed method is verified through simulation under random traffic conditions. Compared to other centralized control algorithms, it can significantly improve driving efficiency and reduce fuel consumption. At the same time, the applicability of the method is verified by comparing with ExiD datasets, and some advantages are obtained in terms of fuel consumption.

Autonomous vehicle trajectory prediction is an important component of autonomous driving assistance algorithms (ADAAs), which can help autonomous driving systems (ADSs) better understand the traffic environment, assess critical tasks in advance thus improve traffic safety and traffic efficiency. However, some existing neural network-based trajectory prediction models focus on theoretical numerical analysis and are not tested in real time, leading to doubts about the practical usability of these trajectory prediction models. To address the above limitations, this study first proposes a collaborative simulation environment integrating traffic scenario construction, driving environment perception, and neural network modeling, afterwards used the co-simulation environment for trajectory data and driving environment data collection. In addition, based on the characteristics of the collected data, a trajectory prediction model based on Bi-Encoder-Decoder and deep neural network (DNN) is proposed and pre-trained. Finally, the pre-trained completed model is embedded in the co-simulation environment and tested in real-time with different batches of data. The simulation results show that the proposed trajectory prediction model can predict trajectories well under specific training data batches, and the best performing trajectory prediction model has a prospective time of 4.9 s and a prediction accuracy of 91.55%.

Discriminative correlation filters (DCFs) have shown promising tracking performance in recent years thanks to the powerful representation ability of deep features. However, a large number of target-irrelevant channels in deep features limits the tracking performance and increases the computational cost. To eliminate the negative impact of noisy channels and improve the utilization efficiency of deep features in DCF-based trackers, we present an adaptive feature channel selection method for robust visual tracking. Our method adaptively chooses the most discriminative channels to learn a more robust target appearance model, which is achieved by evaluating the energy relationship between background and foreground in each feature channel. Moreover, according to the feedback of channel selection, an adaptive model update strategy is proposed to alleviate the model degradation problem caused by incorrect model updating. Extensive experimental results obtained on five popular tracking benchmarks demonstrate the effectiveness of the proposed algorithm and its superiority over the state-of-the-art trackers.

Improper handling of on-ramp merging may cause severe decrease of traffic efficiency and contribute to lower fuel economy, even increasing the collision risk. Cooperative control for connected and automated vehicles (CAVs) has the potential to significantly reduce the negative impact and improve safety and traffic efficiency. Implementation of cooperative on-ramp merging requires the assistance of the vehicle to vehicle (V2V) and vehicle to infrastructure (V2I) communication, wherein the communication delay may cause negative impact on CAV cooperative control. In this paper, scenario of on-ramp merging for CAVs considering the V2I communication delay are studied. Statistical characteristics of the V2I communication delay are explored from both literature and real field test, and a communication delay estimation model based on statistical techniques are proposed. Specifically, we firstly model the CAV on-ramp merging scenario using optimal control in ideal situation. Then, several statistical characteristics of the V2I communication are investigated especially the probability density function of the V2I communication delay in several application scenarios. Further, we proposed a communication delay estimation model and used the modified vehicle state to compute the corresponding control law. Real field test of V2I communication delay indicated that distribution of V2I communication delay could correlate with the application scenario and normal distribution can be generally adopted to approximate the probability density function (PDF) when the number of samples is large enough. Numerical simulation of the CAV on-ramp merging scenario considering the V2I communication delay revealed that dynamic performance of the control process would be deteriorated impacted by the V2I communication delay and it might further impact the final control effect and lead to potential lateral collision in the merging area.

Connected and automated vehicles (CAVs) can improve traffic safety and transportation network efficiency while also reducing environmental impacts. However, congestion and accidents can easily occur at merging roadways. Therefore, coordinating cooperative merging of CAVs is one of the most common traffic management problems. This paper addresses the problem of integrated longitudinal and lateral cooperative merging control with practical implications for CAVs approaching on-ramps. A hierarchical and decentralized cooperative coordination framework was developed to systematically control the merging of CAVs. The control system of each vehicle can be divided into an upper-level and lower-level. For upper-level control, an optimal control-based algorithm considering input constraints was presented to optimize fuel consumption and passenger comfort. A decision strategy was developed to optimize the start time of lateral trajectory planning. To achieve lower-level control, a Proportional-Integral (PI) controller was used for tracking the optimized longitudinal speed of the upper-level and a decentralized unified algorithm based on nonlinear model predictive control was proposed for tracking the upper-level optimal trajectory. To avoid lateral collision, the driving safety field based on vehicle size and motion state was selected as one of tracking the optimization objectives. Efficiency of the proposed framework and the algorithm was validated by CarSim/Simulink co-simulations of near-real-world vehicle scenarios. The proposed integrated merging control system can improve traffic efficiency and reduce fuel consumption compared to baseline with the potential for real-world application. Furthermore, the results demonstrate the potential applicability of cooperative control methods based on upper-level vehicle control.

Visual perception system is the key component of safety driving assistance and unmanned driving systems, and the perceptive performance of which will directly affect the running safety. There are various perception algorithms for the visual system, especially in recent years, deep learning algorithms are adopted with increasing popularity among them. However, the majority of existing works mainly focuses on daytime scenes with favorable illumination and weather conditions, and relies on visible light with intensity imaging equipment. This paper is based on polarization features acquired by deep learning methods, attempting to address the problems about vehicle-road environment perception in Low-Visibility Condition. Polarization is one of the essential properties of matter, here we propose a new method by studying and analyzing the transmission characteristics of the target’s polarization information. In the proposed method, the polarization features of vehicle-road environment are first acquired by a kind of three-channel polarization imaging device, then, fused together with an intensity image, and finally followed by a semantic segmentation operation by deep networks. The experimental results clearly demonstrate that the effect of perception based on polarization features via deep learning are greatly improved compared with intensity imaging, especially in low illumination and severe weather conditions. It is of great value for environmental robustness of visual perception system and further traffic safety.

Numerous fast heuristic algorithms, including shooting heuristics (SH), have been developed for real-time trajectory optimization, although their optimality has not yet been quantified. This paper compares the performance between fast heuristics and exact optimization models. We investigate a core trajectory optimization problem as a building block for numerous trajectory optimization problems, i.e., guiding movements of connected automated vehicles on a one-lane highway when the arrival and departure times and velocity are given. To apply the SH algorithm to this problem, we adapt it to a fast-simplified shooting heuristic (FSSH) model to solve the trajectory smoothing problems with different arrival and departure velocities. An exact trajectory optimization (ETO) model is formulated that takes the vehicle position and velocity as the decision variables, and the fuel consumption and driving comfort as the objective function. The constraints of the model are based on the limits and safety of the vehicle dynamics between consecutive vehicles. We demonstrate the convexity of the ETO objective function, ensuring the solvability of the ETO model at the true optimum using gradient descent algorithms supplied by the MATLAB optimization toolbox. Six groups of numerical experiments using different input parameters and one experiment using real Next Generation Simulation (NGSIM) data are conducted. ETO can improve the objective values by a few to tens of percentage points. However, FSSH achieves a greater solution efficiency with an average solution time of less than 0.1 s compared to ~450 s for ETO.

Owing to lack of enough face image and invalidation of many traditional face recognition algorithms, face recognition with single training sample is really a great challenge. To solve the above problem, this study proposes a novel local weighted fusion Gabor (LWFG) algorithm. First, one single sample is segmented into a series of block sub‐images, and then, each of these sub‐images is decomposed into a series of multi‐resolution Gabor wavelets with multi‐orientation and multi‐scale. Second, different orientation Gabor wavelets with the same scale are fused. Next, different scale Gabor wavelets with the same orientation are fused according to the proposed fusion criterion. Third, the fusion Gabor feature histograms are calculated in each of the divided local regions. Meanwhile, every local region's information importance is measured by the proposed local image information content model. Finally, the fusion Gabor wavelet histograms are adaptively weighed by weighting map which calculated from information content model. This study conducted simulation experiments on different face databases under the different conditions including partial occlusion, expression change and illumination variation. The results indicated that the proposed LWFG algorithm is more effective with single training sample.

Road detection is one of the crucial tasks for scene understanding in autonomous driving. Recently, methods based on deep learning had rapidly grown and addressed this task excellently, because they can extract more abundant features. In this study, the authors consider the visual road detection problem as a classification for each pixel of the given image, which is road or non‐road. There is complex illumination encounter in traffic applications, so that the detection model has poor adaptability. They address this problem by proposing a deep network architecture, which combines the network U‐Net‐prior and domain adaptation model (DAM). U‐Net‐prior is a modified segmentation network which integrates location prior and shape prior into U‐Net. DAM is a model for reducing the gap between training images and test images, which is optimised in adversarial learning to make the features extracted from different datasets close to each other. They validate the effectiveness of each component of the algorithm, and compare the overall architecture with other state‐of‐the‐art methods, and the results show that the architecture achieves top accuracies with the shortest run time in monocular‐vision‐based methods, simultaneously, compared with the methods based on other sensors, the architecture also achieves a competitive result.

Vehicle merging is one of the main causes of reduced traffic efficiency, increased risk of collision, and fuel consumption. Connected and automated vehicles (CAVs) can improve traffic efficiency, increase safety, and reduce the negative environmental impacts through effective communication and control. Therefore, to improve the traffic efficiency and reduce the fuel consumption in on-ramp scenarios, this paper addresses the global and optimal coordination of the CAVs in a merging zone. Herein, a cooperative multi-player game-based optimization framework and an algorithm are presented to coordinate vehicles and achieve minimum values for the global pay-off conditions. Fuel consumption, passenger comfort, and travel time within the merging control zone were used as the pay-off conditions. After analyzing the characteristics of the merging control zone and selecting the appropriate control decision duration, multi-player games were decomposed into multiple two-player games. An optimal merging strategy was, thereby, derived from a pay-off matrix, and minimum payoffs were predicted for a number of different potential strategies. The optimal trajectory corresponding to the predicted minimum payoffs was then utilized as the control law to coordinate the vehicles merging. The proposed control scheme derives an optimal merging sequence and an optimal trajectory for each vehicle. The effectiveness of the proposed model is validated through simulation. The proposed controller is compared with two alternative methods to demonstrate its potential to reduce fuel consumption and travel time and to improve passenger comfort and traffic efficiency.

When facing with sudden terrorist attacks or natural disasters, in order to avoid the paralysis of communication networks caused by the destruction of partial ordinary 4G cellular base stations in urban area, this paper proposed a unmanned aerial vehicle (UAV) communication system based on 4G technology for public safety and investigated its optimal hovering height for maximizing its effective coverage radius. In this system, collaborative operation, among several airborne 4G cellular base stations, some unmanned aerial vehicle relays and other still worked ordinary 4G cellular base stations, could form a seamless communication coverage in the accident area, and provide the alternate communication links with QoS guarantee to people involved in the disaster relief and rescue. At meanwhile, in different urban environments, the hovering height of UAV equipped with the 4G cellular base station could be quickly optimal adjusted to maximize its effective coverage area by the configuration information sent from the emergency command management center, so as to effectively cut the cost of urban security emergency response system with the limited number of UAVs, ensure its smooth operation, and save people's life and property loss to the greatest extent.

The research presents in this paper develops an Ant Colony System (ACS) based system optimal route choice strategy to ensure the rational traffic flow assignment for urban traffic network. In this work, the traffic flow and impedance function of each road section are calculated firstly, and then the individual traveler's route choice behaviors on network nodes are simulated based on applying the pseudo-random state transition rule, route and road section pheromone update formula, which implement the synthesizing of static prior knowledge, dynamic traffic state and the randomness of route choice. This paper's findings reveal that the designed strategy is in a position to reflecting the overlay and delay effect of route choice under different Origin-Destination (OD) demands. In addition, the findings can obtain better network equilibrium comparing with the incremental assignment method, and will benefit for achieving the route guidance system with time varying traffic conditions.

A new filter structure called adaptive multistage median filter (say AMM for simple) is proposed. It follows the basic architecture of the multistage median filter (MLM), but its subfilters are based on the date-dependent and sizes variant subwindows, that allows AMM give better performance than MLM. In addition, like MLM, the proposed filter is not only computationally effective, but also needs no a priori information about image or noise. Experiment results are given to show the superiority of the new proposed filters.