Road Side Units (RSUs) play a pivotal role in enhancing the safety of Connected Vehicles (CVs), yet their safety benefits hinge significantly on effective deployment strategies. Traditional approaches often focus on high-risk areas, but such locations may not necessarily yield the most substantial safety improvements. This study redefines hot spots as road segments where RSU deployment results in the greatest reduction of collision risk and introduces a cost-efficient method for identifying such locations. The proposed method requires only small-scale real-world driving data, which is further augmented to support broader scenario evaluation. Additionally, an accelerated sampling strategy is incorporated to enhance the efficiency of the identification process. Simulation-based evaluations demonstrate that the method achieves superior performance in terms of safety impact, data efficiency, compared to conventional approaches.

Perception technology plays a crucial role in vehicle automation, yet traditional approaches solely rely on onboard computing and have inherent limitations in perception range. To improve perception range, edge computing is introduced. Through edge computing, some perception computing tasks can be offloaded from onboard sensors to sensors installed on roadside infrastructures. This infrastructure-enabled perception (IEP) expands perception range beyond what onboard sensors alone can achieve. However, existing IEP systems have limited precision in long-distance perception and require costly sensors for optimal performance. To enhance the performance without significant financial investment, this article proposes an enhanced IEP system. The proposed IEP system adopts a virtual-detector-based perception solution, designing multiple virtual detectors to detect vehicle arrivals. Unlike traditional IEP approaches, the proposed system does not rely on dense data points for estimating vehicle geometry. Instead, it bypasses the geometry-estimation step and only needs sparse data points to detect vehicle arrivals. Consequently, even with sparse data points at long perception distances, our IEP system can achieve high precision in long-distance perception. Due to this enhanced solution, the proposed IEP system has the following features: 1) ensuring wide perception range; 2) enabling cm-level precision perception; 3) maintaining robustness against perception distances, vehicle speeds, and sensor frequencies; 4) compatible with mass-produced and cost-effective sensors; and 5) laying a foundation for infrastructure-enabled cooperative driving. Experimental validation confirms the system’s advanced features and demonstrates its superiority over the state-of-the-art IEP system. It achieves a wide perception range up to 150 m and a low localization error down to 6.500 cm. Further investigation suggests that the IEP system should primarily be deployed on expressways and implemented for speed-related cooperative driving applications, such as speed harmonization.

Automated Vehicle (AV) safety is a critical issue and appeals to worldwide focus. To ensure AV safety, AV functions should be tested and evaluated in an enormous number of scenarios. Since such AV testing is time-consuming, scenario filters have been developed to identify safety-critical scenarios and omit ordinary ones. However, the scenarios identified by these filters do not uniquely match the AV function to be tested and are most likely not critical for the AV function. Therefore, an enhanced scenario filter is proposed in this paper. It bears the following features: 1) Automated-driving-function-specific scenario identification; 2) High coverage of critical scenarios; 3) Enhanced identification efficiency by avoiding adopting a surrogate model; 4) High reliability of critical scenario identification. To enable the above features, the proposed filter formulates the identification problem into an optimization problem and solves it with a model-free approach. Experiments have been conducted to evaluate and validate the proposed filter. The results confirm that the proposed filter is able to improve coverage of critical scenarios, efficiency of identification, and reliability of identification compared to the state-of-the-art filter. Specifically, the proposed filter improves coverage by up to 70 percent, efficiency by up to 97 percent, and reliability by up to 22 percent. The results also reveal that the proposed filter shows an increasing advantage for testing AV functions with higher complexity.

Active Traffic Management (ATM) plays a crucial role in alleviating congestion. However, traditional ATM strategies struggle to precisely control traffic demand to match bottleneck capacity. This limitation not only worsens congestion but also negatively impacts traffic, resulting in increased vehicle cruising discomfort and traffic flow fluctuations. To address this issue, this paper proposes a multi-centralized Trajectory-based Traffic Management (TTM) strategy. The goal is to enable precise demand control for multi-segment scenarios with the help of Connected and Automated Vehicles (CAVs). It is able to regulate traffic demand by precisely matching bottleneck capacity. The proposed TTM strategy bears three novel features: 1) stronger demand regulation capability in terms of control range and precision; 2) reduced negative impacts to achieve improved vehicle cruising comfort and traffic flow stability; and 3) enhanced computation efficiency to avoid the curse of dimensionality. The proposed TTM is evaluated against the conventional ATM strategy, named variable speed limit. The results confirm the aforementioned features of the proposed method and demonstrate its superiority over the conventional approach. Additional discussion highlights that the proposed TTM enhances lane-change smoothness by 78.6%. It is also revealed that the multi-centralized structure of the proposed TTM is critical in achieving a balance between global optimality and computational efficiency.

Benefitting from the maturing of intelligence techniques and advanced sensors, recent years have witnessed the full flourishing of change detection (CD) on multi-temporal remote sensing images. However, extraneous interference caused by normal temporal evolution and the extreme sparsity of spatial changes still plague the detection accuracy. To counteract this dilemma, a lightweight axial-shunted spatial-temporal conversation network (ASCNet) is proposed, which models the intrinsic representations in dually augmented images with a parallel treatment of convolutions and attentions. Specifically, for the features of weakly augmented bi-temporal image pairs from Siamese CNN, a roundtable attention-based and intra-scale axial-shunted interaction, with linear complexity, is presented. By splitting horizontally or vertically into multiple chunks and then performing axial-squeeze operation, axial-shunted scheme can achieve fine-grained attention while maintaining linear complexity. Moreover, roundtable attention pursues efficient bi-temporal modeling by incorporating both self-attention and cross-attention in a single attentional computation, while imposing change guiding and difference gating for focusing on changes. Simultaneously, a video transformer is introduced for the modeling of strongly augmented sequences, followed by an inter-scale spatial-temporal alignment to recalibrate the feature responses. ASCNet demonstrates state-of-the-art performance on four publicly available CD datasets while maintaining superior computational efficiency. The source code is available at https://github.com/fengyuchao97/ASCNet .

A motion planner is established to realize piloting automated driving on unstructured roads. It has the following features: i) improved adaptivity to over-the-horizon driving environment, ii) enhanced compatibility with unstructured roads, and iii) guaranteed computational efficiency for real time application. The performance of the proposed motion planner was evaluated in a software-in-the-loop simulation platform. section. The evaluation includes: i) unstructured roads compatibility validation, and ii) validation of adaptivity to traffic events. Experiment results showed that applying the planner can enhance adaptivity to over-the-horizon traffic events on unstructured roads. The average travel efficiency enhancement is about 12.18% and the average perceived risk reduction is about 57.19%.

Accompanied by the booming development of remote sensing (RS) imaging techniques, change detection (CD) has emerged as a conspicuous focal point in the realm of geoscience. Traditionally, extensive research has predominantly centered on extracting semantic features from individual images yet neglecting the interinput correlations latent in bitemporal imagery. This oversight gives rise to the occurrence of pseudovariant regions and the blurring of detection boundaries. To address these challenges, we propose a spatial selection and temporal evolution network, named STENet, which aims to unravel semantic correlations between bitemporal images from both spatial and temporal perspectives. Specifically, a dual pathway is crafted. The first one explores precisely the spatial localization of changes in bitemporal pairs, while the other complements the local details by generating a pseudovideo input via specific data augmentation. To boost the precision (Pre) of localizing sparsely changed targets, we further present a dynamic selective attention (DSA) mechanism, which strives for more focus on the positive regions while holding a mild computational demand. Moreover, by leveraging data augmentation to derive the temporal evolution of a set of progressively changed images, we then exploit a 3-D convolution-based encoder to mine the potential details therein, endeavoring to a refinement of target boundaries. Ultimately, STENet enforces the fusion of multiscale spatial and temporal features through a dedicated decoder and generates the final change map. Experiments on four popular datasets show that our proposal scores higher than most state-of-the-art approaches. In addition, the appealing performance is achieved with mild quantities of parameters and computations. The code is available athttps://github.com/ZhengJianwei2/STENet.

Truck platooning is a promising technology in freight transport. To commercialize truck platooning as early as possible, its evaluation is in urgent need. For truck platooning evaluation, simulation platforms play a crucial role. However, there has not been a simulation platform to meet the evaluation needs of various stakeholders, including Original Equipment Manufacturers (OEMs), Freight Operators (FOs) and Transportation Management Administrations (TMAs). To fill the research gap, this paper proposes a next-generation simulation platform. It integrates a traffic simulator, platoon management system, and truck control module to satisfy all the evaluation needs. The proposed platform bears the following features: i) Compatibility with various platooning decision makers, planners, controllers, vehicle types and platoon management strategies; ii) Capability of evaluating platoon performance on the lateral dimension; iii) Prototype platoon management system provided for FOs; iv) Capability of evaluating truck platoon management performance in terms of sustainability and economy; v) Capability of evaluating the impact of interactive background traffic on platoon performance. vi) Capability of evaluating the impact of truck platoon management on traffic mobility. The proposed platform is validated by comparison against an actual field test. Its credibility is confirmed in terms of truck platoon performance and interactive traffic simulation. Additional tests are conducted to evaluate truck platoon performance and the impact of truck platoons on mixed traffic. The results reveal that existing platoon lane-change technologies should be upgraded to be compatible with high-traffic-demand scenarios. It is also revealed that a localized and up-to-date assessment is required before allowing truck platooning.

This paper proposed a speed harmonization controller for partially connected and automated traffic. It regulated the flow rate of the entire traffic by adjusting only the target cruising speed of Connected and Automated Vehicles (CAVs). The major breakthrough of the proposed controller is that it is able to manage mesoscopic level traffic by controlling microscope level status (desired speed) of a small portion of vehicles. To evaluate the proposed controller, a VISSIM based microscopic simulation evaluation was conducted. Sensitivity analysis was performed for CA V Penetration Rate (PR) and demand level (v/c ratio). Results confirm that the control accuracy of the proposed controller is over 85% across all CA V PRs and demand levels.

Although Cooperative Adaptive Cruise Control (CACC) is a promising technology for Connected and Automated Vehicle (CAV), it is urgent to validate its applicability in real traffic situation. To support the validation, simulation plays a key role, but up-to-date simulation platforms are not generic enough in terms of CACC controller type, background traffic condition, road geometry and traffic control scheme. This paper proposes a generic simulation platform for CACC. It is featured by: i) Enabling evaluation of both CACC-controller performance and its impact on the transportation system; ii) Fast simulation speed and large-scale simulation; iii) Enabling simulation for human-machine task switching; iv) Compatibility with any CACC controller and any vehicle dynamics model.