Vehicular edge computing (VEC) has emerged as a key paradigm to support computation-intensive and delay-sensitive vehicular applications by offloading tasks from vehicles to nearby multi-access edge computing (MEC) servers. However, in realistic urban environments, task processing performance is heavily affected by heterogeneous vehicle-MEC interactions, spatiotemporal traffic dynamics, and continuously varying vehicle populations. To address these challenges, this paper considers a traffic-aware embodied edge intelligence-enabled vehicular network (EEIVN), where edge intelligence is grounded in the physical traffic environment by integrating VLM-based semantic perception with edge decision making. Based on this architecture, we formulate a reliability-constrained delay minimization problem (RDMP) by jointly optimizing task offloading ratio, computing resource allocation, and vehicle association, while constraining the queue reliability to mitigate queue-induced tail delay. To solve the NP-hard RDMP, we propose a VLM-multi-agent proximal policy optimization (VLM-MAPPO) approach that integrates a VLM-based traffic awareness method, a vehicle-adaptive MAPPO algorithm, and a vehicle association scoring and selection mechanism. Extensive simulations based on SUMO and CARLA demonstrate that the proposed VLM-MAPPO approach outperforms benchmarks in terms of task completion delay and tail delay, while maintaining comparable vehicle energy consumption and exhibiting robust scalability under dynamic traffic conditions and varying vehicle densities.

The Policy-Space Response Oracles (PSRO) framework scales equilibrium computation to large zero-sum games by iteratively expanding a restricted strategy set using deep reinforcement learning (DRL). A central challenge is to construct, under limited computational budgets, a small strategy population whose induced game well approximates the full game. Existing PSRO variants typically expand the population using best responses to meta-strategies computed from restricted-game payoffs, which can lead to inefficient expansions that provide limited global improvement. We propose to guide population expansion by directly evaluating the post-expansion population quality. Specifically, we adopt Population Exploitability (PE) to measure how well a restricted strategy set represents the full game, and introduce a two-phase exploration--selection framework that explicitly minimizes PE during expansion. We instantiate this framework as Global PSRO, a practical DRL-based algorithm that efficiently generates candidate responses and estimates PE via parameter-sharing conditional neural networks. Experiments across multiple two-player zero-sum games show that Global PSRO achieves lower exploitability and approximates Nash equilibria with significantly fewer policy iterations than prior PSRO methods.

Finding the Nash equilibrium in large-scale zero-sum games has long been a challenging problem due to the vast and unknown policy space and the utility matrix. The Policy-Space Response Oracles (PSRO) framework, as a combination of conventional game analysis with deep reinforcement learning, iteratively constructs a restricted game by including a pure policy that is the best response to the equilibrium of the restricted game in the previous iteration. However, adding a pure policy at a time is inefficient, as there may be multiple policies that dominate the equilibrium of the current restricted game. In this regard, we propose Mixed Policy-Space Response Oracles (M-PSRO), which add a mixed policy rather than a pure policy to the current policy set. To obtain more effective mixed policy candidates, we adopt a parallelized training framework to promote policy diversity. Theoretical analysis shows that M-PSRO can converge to an approximate Nash equilibrium. We conduct extensive experiments across a wide range of complex games, and results show that the M-PSRO algorithm achieves state-of-the-art performance across all the games and can approach the Nash equilibrium more efficiently. Numerous ablation studies show that the improvement benefits from the usage of mixed policies in M-PSRO, which offer an even more flexible optimization space.

With the rapid advancement of networked applications, privacy protection has emerged as a paramount concern for billions of users and service providers worldwide. While users have grown accustomed to submitting personal information through registration forms to access digital services, and service providers depend on such data disclosures to deliver tailored experiences, there remains a significant gap in protective frameworks. Current practices lack systematic mechanisms to empower users with optimal privacy control while disclosing only the minimally necessary information required for service acquisition. This imbalance between data disclosure and privacy preservation underscores a fundamental challenge in contemporary digital ecosystems. To address this issue, this paper proposes an evolutionary game theory approach combined with information entropy to explore how to provide more accurate and personalized services for users while minimizing privacy exposure. Focusing on real-world interactions in social networks, the game is exclusively played between users and service providers, aiming to strike a balance between user privacy and service precision. The theory of entropy is employed to quantify the information disclosed by users, and a privacy calculation formula is derived using a sensitivity coefficient and a modified information entropy formula. Building on this foundation, we present the time-varying dynamic replication equation, the equilibrium solution, and the evolutionary stable strategy (ESS). To validate our approach, we collected 200 real-world questionnaire responses and conducted simulation experiments. The results demonstrate that our strategy can provide users with an optimal solution, effectively balancing privacy preservation with the need for personalized services.

The vehicle anti-collision system stands as a pivotal innovation, markedly reducing the frequency of vehicular accidents by issuing timely alerts to drivers about imminent collision risks. This preemptive safety feature is now a standard component within the safety packages provided by many automotive manufacturers. While current anti-collision technologies, predominantly advanced driver assistance systems that synthesize diverse sensor inputs, are sophisticated, their performance can be impeded by the operational constraints of the sensors themselves. This limits their capacity to ensure traffic safety comprehensively and efficiently. To overcome these constraints, there has been a significant shift towards anti-collision systems employing short-range wireless communication technologies. This paper introduces the design and development of a blind spot warning system based on cellular vehicle-to-everything technology. It enables the fluid communication of vehicle and road segment data among the host vehicle, remote vehicles, and roadside units through cellular vehicle-to-everything protocols. The system evaluates spatial relationships of surrounding RVs to the HV and the associated collision risks by analyzing the consolidated vehicle and environmental data, subsequently delivering early warnings to the driver. Utilizing simulation software named Virtual Test Drive, this research constructs detailed collision scenarios and performs exhaustive Hardware-in-the-Loop testing. A comparative analysis of various experimental data sets confirms the algorithm’s proficiency in delivering precise and prompt blind spot collision alerts to the HV, validating its effectiveness in bolstering vehicular safety.

As autonomous driving technology matures, the focus shifts to enhancing the safety and reliability of these systems. Simulation testing is a critical method for efficiently and rapidly validating the performance of autonomous vehicles (AVs). A robust AV system requires extensive testing across a wide range of scenarios and iterative improvements. However, current simulation systems have limitations in supporting diverse scenarios, often relying on expert-designed situations. To address these challenges, we introduce DTTF-Sim, a novel simulation system based on Digital Twin technology for traffic flow. DTTF-Sim aims to accurately replicate real-world traffic flow conditions, offering continuous long-term simulation capabilities for AV testing. The system can simulate detailed dynamic traffic scenarios with a focus on interactions between multiple vehicles and between AVs and background traffic vehicles, modeling the strategic decision-making processes that occur in these encounters. This paper outlines the architecture and functionalities of DTTF-Sim, highlighting its ability to overcome the shortcomings of existing simulation platforms. We demonstrate the effectiveness of DTTF-Sim through case studies and experimental results, showing its potential to significantly advance the development and testing of autonomous driving technologies.

In the field of autonomous driving, accurate and efficient 3D object detection is crucial for ensuring safe and reliable operation. This paper focuses on the fusion of camera and LiDAR data in a late-fusion manner for 3D object detection. The proposed approach incorporates contrastive learning to enhance feature consistency between camera and LiDAR candidates, which is named as Contrastive Camera-LiDAR Object Candidates (C-CLOCs) fusion network, facilitating better fusion results. We delve into the label assignment aspect in late fusion methods and introduce a novel label assignment strategy to filter out irrelevant information. Additionally, a Multi-modality Ground-truth Sampling (MGS) method is introduced, which leverages the inclusion of point cloud information from LiDAR and corresponding images in training samples, resulting in improved performance. Experimental results demonstrate the effectiveness of the proposed method in achieving accurate 3D object detection in autonomous driving scenarios. Our code will be released upon accepted in https://github.com/zhangtingyu11/C-CLOCs .

Collecting LiDAR data for autonomous driving using real vehicles is costly, scenario-limited, and challenging to annotate. Simulated LiDAR point clouds offer flexible configurations, reduced costs, and readily available labels but often lack the realism of real-world data. This study provides a comprehensive review of methods to enhance the authenticity of simulated LiDAR data, focusing on simulation scenarios, environmental conditions, and point cloud features. Additionally, we discuss verification techniques, including direct and indirect methods, to assess authenticity improvements. Experimental results demonstrate the effectiveness of these techniques in enhancing perception algorithm performance. The paper identifies challenges in simulating LiDAR data, such as accuracy discrepancies, brand adaptability, and the need for comprehensive evaluation metrics. It also proposes future directions to bridge the gap between simulated and real-world data, aiming to optimize hybrid training models for improved autonomous driving applications.

Monocular 3D object detection remains a challenging task due to the inherent limitations of single-view depth perception. While conventional methods treat all parts of the Region of Interest (RoI) uniformly, we argue that different RoI regions hold varying importance for accurate detection. This study introduces the Multi-Scale Grid Attention (MSGA) mechanism to investigate the significance of RoI regions at multiple scales. Furthermore, we propose a novel probabilistic post-processing method to enhance detection robustness by effectively utilizing the probabilistic properties of depth estimation during inference. Our approach achieves state-of-the-art performance on the KITTI and Waymo datasets, demonstrating significant improvements in detection accuracy and robustness.

In this article, we propose a dual-driven modeling method for vehicle-mounted LiDAR sensors. The method has a two-stage modeling framework comprising point cloud position modeling and intensity modeling, respectively. In the spatial position modeling stage, we generate ideal LiDAR point clouds by employing the geometric relationships of spatial rays. Subsequently, we integrate the LiDAR detection equation with a probability model to simulate the attenuation and noise. In the intensity modeling stage, a network InPNet is leveraged to train an intensity model. This model is able to predict accurate reflection intensity for point clouds generated in the previous stage. Experiments have shown that the proposed method is able to simulate point clouds within +/- 10% errors on various driving scenarios. We also mix the simulated point clouds as augmentation data with the real scanning point clouds and employ them to train several representative 3-D object detection models under clear and adverse weather conditions. The results demonstrate promising prospects for engineering applications.

This study explores the dynamics of a gated memory car-following system, with a focus on the challenges encountered when training models using fine-grained spatiotemporal data. To address the issues of redundant gradient updates and limited generalization inherent in traditional sequential training methods, a novel Spatiotemporal-Decoupled Training (SDT) method is proposed. This method enhances gradient variance by decoupling temporal dependencies and mixing trajectory segments from different vehicles, thereby improving model generalization performance and achieving a zero collision rate on test dataset. Experimental validation is carried out using three datasets (HighD, NGSIM-I80 and Lyft) and two basic models (GRU and LSTM) to assess the effectiveness of the proposed method. The results demonstrate significant improvements in model performance, including an 80% reduction in generalization error on the HighD dataset, a 14% reduction on the NGSIM-I80 dataset a 57% reduction on Lyft dataset, and the achievement of a Zero-collision rate on all test datasets, showcasing the potential of the SDT method for intelligent driving systems.

Complex traffic scenarios at uncontrolled intersections are crucial for the test validation of autonomous driving systems. The core of the test scenario construction lies in the accurate modeling of the complex interaction behaviors between vehicles in dynamic traffic. Data-driven models are difficult to support long-term simulation due to the existence of cumulative errors. In addition, existing mechanistic models usually assume rational driver behavior and focus mainly on improving efficiency and safety, thus simplifying vehicle interactions. To overcome the limitations of existing studies, we construct a complex traffic interaction model based on social force theory. This model captures the intricate interactions among vehicles at uncontrolled intersections by introducing the concepts of driving and repulsive forces. In particular, we propose a novel concept of segmented conflicting repulsion, an approach that can accurately model high-risk scrambling interactions between vehicles at intersections. Validation of the model using real data sets demonstrates its ability to accurately reproduce complex interaction behaviors at real-world intersections. Further, simulation analysis and application results reveal that our model-generated scenarios significantly outperform those created by SUMO in terms of complexity, thereby effectively enhancing the safety assessment of the autonomous driving system, Apollo.

In this paper, a radio frequency (RF) stealth wave-form design based on orthogonal frequency division multiplexing-linear frequency modulation (OFDM-LFM) for airborne network radar under spectral coexistence is proposed. We adopt signal-to-interference plus noise ratio (SINR) to characterize the detection performance of the airborne network radar with one transmitter and multiple receivers. With the constraints of SINR reaching the threshold and ensuring non-interference with communication spectral, an optimization model is formulated to minimize the radiated energy of airborne network radar. This model is subsequently tackled using the Particle Swarm Optimization (PSO) algorithm. On this basis, the echo model of RF stealth waveform based on OFDM-LFM is derived and the detection performance and anti-multipath effect performance of the waveform are analyzed. The simulation results illustrate the effectiveness of the proposed strategy.

Connected and Automated Vehicle (CAV) is a newgeneration vehicle equipped with advanced on-board sensors, controllers, actuators, and other devices. In recent years, CAVs have gradually become the main trend of vehicle development, and people’s choice of travel mode has begun to change from traditional cars to CAVs. Cellular Vehicle-to-Everything (C-V2X) connects vehicles to everything and allows transportation participants to interconnect through modern communication technologies. In C-V2X method, cooperative lane change is one of the important parts. The challenge of cooperative lane change has two main parts, one is how to determine a safe and efficient passing strategy, and the other is how to determine a reasonable communication method. To solve the challenge, in this paper, we use V2X communication as the basis of vehicle information exchange, transform the two-vehicle lane-changing problem into a Markov Decision Process (MDP), and then solve it through Q-learning and DQN to obtain the ideal lane-changing decision.

Vehicular edge computing (VEC) is emerging as a promising architecture of vehicular networks (VNs) by deploying the cloud computing resources at the edge of the VNs. However, efficient resource management and task offloading in the VEC network is challenging. In this work, we first present a hierarchical framework that coordinates the heterogeneity among tasks and servers to improve the resource utilization for servers and service satisfaction for vehicles. Moreover, we formulate a joint resource allocation and task offloading problem (JRATOP), aiming to jointly optimize the intra-VEC server resource allocation and inter-VEC server load-balanced offloading by stimulating the horizontal and vertical collaboration among vehicles, VEC servers, and cloud server. Since the formulated JRATOP is NP-hard, we propose a cooperative resource allocation and task offloading algorithm named BARGAIN-MATCH, which consists of a bargaining-based incentive approach for intra-server resource allocation and a matching method-based horizontal-vertical collaboration approach for inter-server task offloading. Besides, BARGAIN-MATCH is proved to be stable, weak Pareto optimal, and polynomial complex. Simulation results demonstrate that the proposed approach achieves superior system utility and efficiency compared to the other methods, especially when the system workload is heavy.

Vehicle-to-Everything (V2X) communication has the potential to revolutionize the travel experience in intelligent transportation, which has received the great attention recently. However, ensuring the freshness of information from multiple sources is critical for the real-time and reliable communication in vehicular networks, especially for timely updates of service centers. To address this issue, we use a promising metric called Age of Correlated Information (AoCI), which can characterize the freshness of multi-source information. Therefore, we propose a novel model that can dynamically regulate the channel activation matching and edge computing collaboration strategy to minimize AoCI in V2X vehicular networks. Firstly, we describe the system model of a V2X network with edge computing, including definitions and assumptions for freshness of information, edge co-computing, etc. Secondly, we formulate the joint optimization problem as a source-related age minimization (SRAM) problem, which is NP-complete. A heuristic algorithm is proposed to solve it under fast-fading channel. Finally, since traditional graph models cannot capture the changing correlation between nodes in dynamic networks, we use graph convolutional networks(GCN) to extract the features of multi-source correlation. The features extracted by GCN include relevant attributes of the sources and its communication links. The features are provided as input to a double deep Q network (DDQN) for training the model that can adapt to a dynamic network environment. Extensive simulation experiments in different network scenarios validate that our proposed method can effectively and efficiently reduce the average AoCI and the computational resources.

Abstract In this paper, we use the ant colony algorithm(ACO) and the river formation dynamics(RFD) algorithm to solve the path optimisation problem of unmanned vehicle in grid models. The traditional ACO algorithm only considers the relationship between the current point and the next point in the probability selection, but the optimised ACO algorithm takes the relative relationship between the next point and the target point into account, which effectively avoids local stagnation and improves the search speed. Aiming at the problems of mutual interference of paths and slow reinforcement of new paths that may occur in the routing process of ACO algorithm, we introduced the river formation dynamics algorithm. The RFD algorithm achieves gradient-directed optimisation of ACO algorithm by adding height attributes to the nodes in the graph and deciding the selection probability according to the gradient between two points. Experimental results show that the hybrid algorithm combining the ACO and RFD algorithms exhibits stronger optimisation finding ability in path optimisation problems. We applied the ACO, RFD algorithm, and the hybrid algorithm to these complex path optimisation problems and achieved significant results.

In order to improve the autonomous lane-changing performance of unmanned vehicles, this paper aims to solve the problem of inaccurate decision classification in traditional support vector machine (SVM) algorithms applied to the lane-changing decision-making stage of intelligent driving vehicles. By using game theory-related theories and combining the improved support vector machine (SSA-SVM) method, a vehicle autonomous lane-changing strategy based on game theory is established. The optimized SVM method has certain advantages for vehicle lane-changing decision-making with a small sample size in actual production processes. The lane-changing decision judgment accuracy rate of the SSA-SVM algorithm model can reach 93.6% compared with the SVM algorithm model without algorithm optimization; the SSA-SVM algorithm model has obvious advantages in decision performance and running speed. Therefore, the proposed new algorithm can effectively solve the problem of the objective consideration of the payoff function in conventional decision game theory.

In recent years, point cloud-based 3D object detection has seen tremendous success. Previous point-based methods use Set Abstraction (SA) to sample the key points and abstract their features, which did not fully take density variation into consideration in point sampling and feature extraction. The SA module can be split into three parts: point sampling, grouping and feature extraction. Previous sampling methods focus more on distances among points in Euclidean space or feature space, ignoring the point density, thus making it more likely to sample points in Ground Truth (GT) containing dense points. Furthermore, the feature extraction module takes the relative coordinates and point features as input, while raw point coordinates can represent more informative attributes, i.e., point density and direction angle. So, this paper proposes Density-aware Semantics-Augmented Set Abstraction (DSASA) for solving the above two issues, which takes a deep look at the point density in the sampling process and enhances point features using onefold raw point coordinates. We conduct the experiments on the KITTI dataset and verify the superiority of DSASA.

With the explosive growth of mobile devices at the edge of mobile networks, the amount of content that needs to be transmitted is exploded. As it takes resources (cache, bandwidth, and power) for the edge server and nearby devices to deliver content, the incentive mechanism with the optimal pricing and content delivery strategy needs to be studied without relying on the knowledge of network parameters in a competitive environment. In this paper, built on the framework of content delivery with the Stackelberg game, we have proposed a robust deep reinforcement learning method based on adversarial training to learn price strategy for lack of knowledge of private information. Specifically, the Stackelberg game is constructed to describe the interaction between different service providers and service demanders, and a deep adversarial reinforcement learning method is proposed to approximate the opponent’s decision in the worst case, where the price strategy can be trained end-to-end in the competitive environment. The simulation results show that the proposed algorithm can form an effective price strategy and improve the utility of service providers.