Integrated Sensing, Communication, and Computation (ISCC) has the potential to meet diverse requirements of Internet of Vehicles (IoV), such as high reliability and low power consumption. However, existing works have not fully considered the problems of unreliable communication links and inefficient data processing under resource constraints in non-ideal environments. To address these issues, this paper proposes a predictive Integrated Sensing, Communication and Computation Over-the-Air (ISCCO) approach based on Orthogonal Time Frequency Space (OTFS) modulation. It takes high Doppler shifts, network dynamics, and resource constraints into account. In particular, the Road Side Unit (RSU) performs target tracking while communicating with the downlink users through Space Division Multiplexing (SDM), and receives the transmission results of the uplink. For the downlink, a predictive beamforming approach based on Extended Kalman Filtering (EKF) is employed, while Over-the-Air computation (AirComp) is utilized for the uplink. The transmit power and receive beamformer at the RSU, along with the transmit power of the uplink users, are jointly optimized through two formulated optimization problems: sensing performance maximization and power consumption minimization. To solve these problems, we adopt an Alternating Optimization (AO)-based algorithm for finding the local optimal solution. Simulation results validate the effectiveness of the AO-based algorithm, and the analysis of the trade-offs between multi-dimensional performance of ISCC and power consumption is conducted.

The vehicular metaverse is a novel physical-virtual fusion realm that aims to disrupt the current transportation paradigm. Within this landscape, the coexistence of moving vehicles and their digital counterparts inevitably brings new privacy concerns. Pseudonym exchange, where vehicles exchange temporary identifiers with neighbors to enhance anonymity, offers an affordable solution to protect the location privacy of vehicles. However, existing pseudonym exchange schemes primarily focus on physical vehicles, limiting their effectiveness across physical and virtual spaces in the vehicular metaverse. Furthermore, studies have shown that many vehicles care little about their location privacy, so incentivizing more vehicles to participate in pseudonym exchanges remains a challenge. Motivated by these issues, we propose a physical-virtual dual pseudonym exchange scheme, incorporating an Attribute-Matched Double Dutch Auction (AMDDA) incentive mechanism to facilitate pseudonym exchange transactions. We use a trajectory prediction model to evaluate vehicle attributes, ensuring pseudonym exchange between vehicles with high trajectory similarity to enhance location privacy preservation. Furthermore, we devise a Generative Diffusion Model (GDM)-based approach to derive the optimal pricing strategy in the AMDDA market. Extensive experiments on real-world datasets demonstrate that the proposed scheme significantly improves both the efficiency and degree of location privacy protection.

Integrated sensing, communication, and computation (ISCC) in Internet of Vehicles (IoV) confronts cross-domain interference, limited computing capacity and stringent Quality of Service (QoS) requirements. To address these challenges, this paper proposes a Non-Orthogonal Multiple Access (NOMA)-enhanced cloud-edge collaborative framework for ISCC, which achieves multi-dimensional resource synergy through three key innovations. First, a two-tier task offloading architecture is designed, where computational tasks are dynamically allocated to mobile edge computing (MEC) servers and cloud server (CS), breaking the computing capacity bottleneck of standalone edge nodes. Second, leveraging successive interference cancellation (SIC), we develop a dual-domain interference suppression mechanism: intra-functional NOMA decoding eliminates uplink multi-user interference, while coordinated beamforming mitigates cross-functional impacts between communication and sensing signals. Third, we formulate the joint beamforming and resource allocation problem as a mixed-integer nonlinear programming (MINLP) problem, and propose an alternating direction method of multipliers with alternating optimization (ADMM-AO) algorithm. The algorithm decomposes the NP-hard problem into tractable subproblems via MMSE beamforming, convex-relaxed offloading, and closed-form resource allocation. Simulation results demonstrate that the proposed scheme improves the average computation rate by 29.45% compared to the traditional space division multiple access (SDMA) architecture.

As a privacy-preserving collaborative framework, federated learning (FL) enables connected and autonomous vehicles (CAVs) to achieve cooperative environmental perception and decision-making. However, in Internet of Vehicles (IoV) scenarios, multiple concurrent tasks with weak inter-task correlations and negative transfer make traditional FL inapplicable. To mitigate task correlation deficiencies and solve negative transfer, this paper proposes a hierarchical FL framework with personalized edge aggregation for multi-task scenarios. Specifically, we first decentralize the model aggregation process to CAV edges, and divide the convolutional neural network (CNN) model into a shared feature extraction layer and personalized decision layer based on task types, maintaining model accuracy in collaborative training. Next, to eliminate negative transfer during aggregation, we propose a representation similarity-based personalized model aggregation weight allocation algorithm. Extensive simulations demonstrate that the proposed algorithm improves model accuracy and convergence speed while reducing energy and time costs in multi-task IoV scenarios.

Overcoming the limitations of individual-vehicle line-of-sight (LOS) sensing holds significant importance for guaranteeing the safety of driving. With a wider perception field, vehicle-infrastructure (VI) collaborative perception can provide vehicles with more comprehensive perception assistance, which has received widespread attention in recent years. However, the perception data fusion between infrastructure and vehicles is still impeded by issues such as large data volume and complex processing procedures, constituting a threat to driving safety. To deal with these issues, this paper proposes a VI collaborative environment perception approach based on sparse bird's eye view (BEV) features. By leveraging the representation of sparse BEV, features can be fused within a unified perspective in a lightweight manner, thereby enhancing the efficiency of feature fusion and reducing redundancy. Additionally, we present a solution for processing the overlapping features between the EGO-vehicle and road side unit (RSU) by taking the union of the coordinate points. Finally, the applicable vehicle and RSU datasets are collected through Carla. The experimental results demonstrate that the proposed approach can effectively mitigate the limitations of individual-vehicle perception by compensating for occluded information and provide a more comprehensive perception field.

In vehicular edge computing networks, the realtime task processing for different vehicles by determining task offloading paths and allocating offloading resources is crucial. However, existing studies often overlook the impact of air-ground cooperation, the task burden on offloading relay nodes, and the limited resources on network performance. These oversights can lead to traffic congestion and performance degradation. To address these issues, this paper proposes a novel integrated sensing and communication (ISAC)-enabled unmanned aerial vehicle (UAV)-assisted task offloading strategy, where tasks are relayed and processed by ground vehicles and multiple UAVs based on the task load rate. Specifically, we first analyze the differences between offloading paths for ground vehicles and UAVs, the coupling relationship between communication, sensing, and computing resources, and the conflicts between UAV self-sensing and ground vehicle offloading assistance. We then formulate the offloading path determination and resource allocation problem as an optimization problem, to minimize overall offloading delay and UAV energy consumption. Subsequently, we propose a novel offloading algorithm based on deep reinforcement learning to schedule offloading paths and network resources intelligently. Finally, simulation results demonstrate the effectiveness of our proposal in reducing offloading delay and UAV energy consumption.

Currently, end-to-end autonomous driving systems that employ imitation learning effectively learn and optimize driving strategies by integrating the driving behaviors of human experts with modern deep learning techniques. However, challenges such as scene diversity, data security, and training time must still be addressed to develop a model that is applicable across various traffic scenarios while maintaining high accuracy. To tackle these issues, this paper proposes a personalized feder-ated imitation learning algorithm that aggregates locally trained imitation learning decision models from vehicles operating in different scenarios through a distributed training approach, thereby enhancing training efficiency and model accuracy. Specifically, considering the variability in communication link quality and potential disconnections caused by the mobility of vehicles in a connected vehicle network, we introduce a personalized user selection algorithm. Building on this foundation, we employ a federated imitation learning method to efficiently and rapidly train a driving decision model with comparable performance while safeguarding data privacy. Extensive simulation results confirm the superiority of the proposed algorithm in terms of training speed and model accuracy.

The perception of a single vehicle has limitations. In contrast, vehicle-infrastructure cooperative perception can share perception information among nodes, overcoming view limitations and occlusion for more comprehensive environmental awareness. However, vehicle-infrastructure cooperative perception encounters two main challenges: the trade-off between perception performance and communication bandwidth, and the negative impact of communication delay on perception. To address these challenges, this paper devises a cooperative data transmission algorithm with delay compensation that innovatively combines feature selection and delay compensation to reduce data volume and offset delays. The algorithm exploits spatial value differences for dynamic feature selection, reducing data transmission while maintaining key performance, and has a receiving-end designment to synchronize the asynchronous features. Simulation results show that the proposed a Sparse BEV Feature Transmission Algorithm with Delay Compensation (DC-SBEVTx) significantly reduces data transmission volume in bandwidth-limited scenarios while maintaining acceptable Average Precision (AP). It also maintains high AP under communication delays, outperforming baseline methods in terms of AP across various conditions, such as different average delay and position noise levels.

Federated Learning (FL) enables the collaborative training of models by users distributed across various locations, transforming traditional data sharing into model sharing. This paradigm holds the promise of facilitating the development of safe, reliable, and accurate driving models within Internet of Vehicles (IoV), with its performance contingent upon the stability of the training process. However, traditional FL relies on a central server for aggregation, which is susceptible to malicious attacks. Moreover, limited communication resources prevent the inclusion of all users in the training process. To resolve issues related to reliability and resource utilization, this paper proposes a reliable Rotating Server Federated Learning (RSFL) algorithm to enhance the security and efficiency of FL. Specifically, we first consider the vehicular topology and participation in FL during their transition, and introduce a server rotation algorithm that incorporates a weighted sum of multiple factors including model training activity, vehicle credibility, speed stability, and distance to augment system security. Additionally, addressing the limitation of server channel resources that can impede FL efficiency, this paper proposes a method to select high-quality users for channel resource allocation by comprehensively considering participation latency, contribution, energy, and channel state during the FL process. This optimizes resource usage at the FL server side and constructs an efficiency-maximization problem for FL to improve the convergence rate. Simulation results confirm that the proposed RSFL algorithm can significantly enhance the security and system efficiency of FL.

Federated learning (FL), as a typical distributed machine learning framework, has been effectively applied to traffic flow optimization, driving behavior analysis, and other areas. However, the stability and efficiency of FL systems heavily rely on the quality and cooperation of participants. If participants find no profit in the FL process, they may reduce their willingness to participate due to energy consumption and limited resources. To bridge these gaps, this article proposes a demand-balanced incentive mechanism for multiple FL tasks. First, considering the time-varying channel characteristics in the Internet of Vehicles (IoV) scenario, two optimization problems are constructed: 1) maximizing task-matching satisfaction and 2) minimizing communication energy consumption. Second, these problems are transformed into a distributed incentive mechanism based on a multileader-multifollower (MLMF) Stackelberg game, and a bi-level alternating direction method of multipliers (ADMM) algorithm is proposed to solve for the optimal resource allocation and reward schemes that balance the demands of all parties. Furthermore, this article designs a multiagent deep reinforcement learning-based method to solve the incentive problem, thereby avoiding the impact of information asymmetry. Simulation results verify that the proposed scheme not only balances the demands of all parties but also enhances user participation without being affected by the number of participants, making it suitable for IoV environments.

In the Internet of Vehicles (IoV), centralized transmission of vehicle data poses significant privacy risks. Applying federated learning (FL) to vehicular networks enables collaborative model training while preserving data privacy. However, due to heterogeneous computational capabilities across devices, some users may drop out due to insufficient computing resources, resulting in slow convergence and degraded model accuracy. Furthermore, the traditional sequential transmission of model parameters creates communication bottlenecks and increases training latency, particularly when dealing with a large number of participating vehicles. Over-the-air computation (AirComp) provides an innovative solution by exploiting the natural super-position property of wireless channels to enable simultaneous transmission and aggregation of signals from multiple users, significantly reducing communication rounds and system latency compared to conventional sequential approaches. In order to solve the above problems, this paper combines AirComp with FL to form an adaptive OA-FL algorithm that addresses computing resource heterogeneity and improves communication efficiency through parallel signal processing. Specifically, we first adaptively adjust the number of local iterations based on the assessment of users’ available remaining computational resources to improve user participation rates. Subsequently, we formulate and solve an optimization problem to minimize model parameter distortion caused by AirComp aggregation, thereby reducing communication overhead while accelerating model aggregation and enhancing model accuracy. Simulation results demonstrate that the proposed OA-FL method effectively reduces client unavailability, improves FL training efficiency, and achieves faster convergence compared to conventional FL approaches.

Federated learning (FL), as a distributed machine learning paradigm, facilitates collaborative training without sharing raw data and holds promise for effective application in the Internet of Vehicles (IoV) for tasks, such as traffic flow prediction and driving behavior analysis. However, the efficiency of FL systems relies on the integrity of the local dataset and the level of user contribution. Vulnerabilities to attacks by malicious users and suboptimal aggregation methods can compromise system performance. To address these issues, this article proposes a blockchain-based FL secure aggregation algorithm to bolster FL robustness. Specifically, in the absence of a centralized trust authority in the IoV, we establish a hierarchical blockchain-empowered IoV reputation management framework that leverages smart contracts to create a trustworthy environment for reputation sharing. Additionally, a lightweight consensus protocol tailored for blockchain efficiency is proposed, thus facilitating a flexible and effective implementation of FL in the IoV. Furthermore, we introduce a reputation-based model selection evaluation scheme and, based on this, a robust FL secure aggregation algorithm. This novel reputation assessment strategy mitigates the effects of interaction uncertainties and integrates a broader spectrum of IoV-specific reputation determinants, thereby enhancing the precision of model selection. The simulation results validate the proposed framework’s superiority in terms of robustness, adaptability, and security.

Effective sensing capabilities are crucial for the safe and reliable operation of Connected and autonomous vehicles (CAVs). While traditional approaches focus on enhancing onboard sensors, the integration of road sensor networks (RSNs) into the CAV ecosystem presents a promising solution to improve sensing performance, but also introduces significant challenges, including heterogeneous sensing requirements, inconsistencies in multisource sensor data, and efficient resource utilization. To address these challenges, this article proposes a novel cooperative sensing framework that leverages multisource and multilevel sensing information from RSNs to optimize CAV sensing performance in resource-constrained scenarios. We develop an improved decision transformer (DT)-based approach that dynamically adapts to diverse driving conditions and efficiently fuses sensor data at various abstraction levels. To tackle the issue of long-delayed rewards, we introduce a reshaped reward function and a bi-level optimization framework that enables effective propagation of rewards along decision sequences. An advanced gradient approximation technique is employed to efficiently solve the optimization problem. Extensive simulations demonstrate the superior performance of our improved DT approach compared to state-of-the-art reinforcement learning (RL) methods in terms of sensing accuracy, coverage, and data efficiency under various traffic conditions.

With the rapid evolution of vehicular network technology, the integration of Machine Learning (ML) with Connected and Autonomous Vehicles (CAVs) presents both remarkable opportunities and formidable challenges. This paper addresses the crucial need for efficient ML model training in the context of Federated Learning (FL) within vehicular networks. Recognizing the limitations imposed by the tradeoff between the high energy cost at the local level with the performance problem at the global level, we propose an innovative approach that harmonizes cost optimization with strategic model selection. Our strategy primarily focuses on optimizing energy consumption during model training and updating at the vehicle end, thereby resolving the prevalent issue of limited end-user participation in FL due to high energy demands. Additionally, we introduce an advanced model selection method, prioritizing local model uploads and adaptively allocating bandwidth to clients with more extensive training data. This method enhances the efficiency and reliability of model updates, ensuring robust global model performance. We validate our approach through extensive simulations, demonstrating not only improved learning performance but also a significant reduction in energy consumption among participating clients.

Vehicular cooperative perception (VCP) facilitates the exchange of sensing data among vehicles through vehicle-to-everything (V2X) communication, significantly increasing the sensing range and precision of individual autonomous vehicles (AVs). However, efficiently managing the sharing and processing of large volumes of sensing data presents challenges due to restricted communication and computation resources. This study introduces an integrated sensing, communication, and computation (ISCC)-based task offloading and resource allocation (ITORA) framework, which optimizes cooperative perception by determining what data to share, which vehicles to involve, and how to process the data effectively. We develop an information value function to evaluate the data quality for each vehicle. Subsequently, we design strategies for sensing task allocation, task offloading, and resource allocation to enable value-driven data selection at a subregion level, facilitating collaborative computing among edge servers and vehicles. Additionally, we formulate an optimization problem aimed at maximizing information value while minimizing delay and energy consumption, subject to constraints on a full region of interest (RoI) coverage, delay, wireless bandwidth, and computational resources. We decompose the mixed-integer nonlinear programming (MINLP) problem into two subproblems, devising a sensing task allocation algorithm and a proximal policy optimization (PPO)-based task offloading and resource allocation (PTORA) algorithm to address them. Comprehensive simulations validate the effectiveness of the proposed PTORA in optimizing information value, reducing task execution delay, and minimizing energy consumption.

Connected and Autonomous Vehicles (CAVs) increasingly leverage sophisticated sensor systems integrated with emerging technologies like the sixth generation (6G) for enhancing driving safety and efficiency. Despite the potential of utilizing the advanced communication technology to enhance driving reliability, conficts between high-quality sensing needs of CAVs and insufficient sensing sharing wellness present significant challenges. To bridge the gaps, this paper proposes a novel cooperative sensing sharing framework that utilizes vehicle-to-vehicle (V2V) communication to extend the effective sensory range of CAVs, thereby reducing perception gaps and enhancing driving efficiency in complex driving environments. Aiming at incentivizing cooperative sensing sharing ecosystem within this decentralized framework, we first introduce a multi-tier blockchain architecture that ensures secure and transparent data sharing among CAVs. Concurrently, a custom-designed efficient consensus algorithm is proposed to minimize the overhead while guaranteeing transaction throughput. To tackle issues related to trust and motivate long-term cooperative behavior, we introduce a supervision-oriented model that utilizes evolutionary game to formulate incentive mechanisms discouraging malicious participation and promoting honest, active engagement. Finally, theoretical analysis and extensive simulations demonstrate that our system not only ensures healthy sensing sharing performance but also maintains system security.

Currently, heterogeneous driving scenarios and complex traffic conditions challenge connected and autonomous vehicles (CAVs) to achieve accurate sensing of road conditions. Existing research on the sensing capabilities of vehicles only relys on adding more onboard sensors, which makes the driving safety unable to be guaranteed due to the installment and cost limit of various sensors. Therefore, this paper proposes an enhanced 3D sensor deployment method to break through the sensing capabilities of CAVs’ own equipment limitations. By efficiently utilizing road infrastructure, reasonable roadside sensor deployment will effectively assist CAVs to expand the sensing range and improve overall sensing accuracy. Firstly, in order to address the limitations of existing works that often rely on simplified sensor models and idealized road conditions, we propose a Bresenham-based sensor and environment model that can be used to construct realistic road environments. Secondly, a decision transformer (DT)-based method is adopted to solve the problem of optimal deployment of sensors in road environments. Our approach effectively addresses the limitations of traditional static deployment methods, which often fail to consider the complexities of real-world driving conditions and the diverse factors influencing optimal sensor deployment. Finally, in order to solve the problem of DT delayed rewards, we propose a two-layer optimization method to redistribute the reward function to solve the challenge of local optimization. A large number of simulations oriented to sensing effects not only verify the effectiveness of the sensor deployment method but also ensure the reliability of sensing assistance.

Wireless Traffic Prediction (WTP) plays a significant role in achieving intelligent resource management for communication systems. However, WTP still faces challenges such as inaccurate prediction resulting from the complex spatial-temporal characteristics due to user mobility, high communication overhead caused by the complexity of the prediction model, and user privacy issues stemming from Centralized Learning (CL). To address the aforementioned issues, this paper proposes a WTP framework under the Federated Learning (FL) strategy called Federated Spatial-Temporal Dual-attention based Network (FedSTDN). Aiming at improving communication efficiency and simultaneously representing various wireless traffic patterns, a data augmentation-based clustering algorithm is adopted, which groups cells into different regions using a small augmented dataset, facilitating subsequent processing. To improve prediction performance, a local prediction model based on Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) is proposed to capture the short- and long-term dependencies of traffic. Additionally, a novel Kolmogorov-Arnold Network (KAN) layer is introduced to replace the traditional Multi-Layer Perceptron (MLP) layer, further enhancing prediction performance. Simulations on two different real-world datasets verify the effectiveness and efficiency of FedSTDN. Compared to the well-performing baseline, the proposed FedSTDN achieves up to 32.83% and 24.30% improvements in Mean Square Error (MSE) and Mean Absolute Error (MAE) on the Milan dataset, respectively. For the Trentino dataset, FedSTDN achieves up to 17.25% and 5.86% improvements in MSE and MAE, respectively.

The advent of deep learning (DL) technology has increasingly captivated the research community’s interest in harnessing DL to enhance data transmission efficiency. Notwithstanding, prevalent methodologies often overlook the computation delay of DL processing data during the inferencing procedure, and fail to adjust intelligent algorithm complexity based on user features. To bridge this gap, we introduce $\mathbf{C o m}^{2}$ (Communication-Computation) framework, to synergize the optimization of communication and computational delays. $\mathrm{Com}^{2}$ adeptly navigates the trade-offs between communication and computation delays, facilitated by autoencoders of varying depths, thus one user can reduce communication delay through more computation latency, and vice versa. Further enhancing this framework, we present an optimization algorithm that marries QMIX with a cascaded graph neural network (GNN), designed to select the optimal autoencoder depth and optimize transmission resources in a distributed manner. This algorithm pioneers a label-free training regime, employing reinforcement learning and unsupervised learning to adaptively improve without the need for high-quality labels. Simulation results show that $\mathrm{Com}^{2}$, alongside the proposed optimization algorithm, maximizes the utility of users’ computing and transmission resources, significantly curtailing the overall data transmission delay by intelligently managing delay trade-offs.

FL enables collaborative training of autonomous driving models without sharing the original data. It enhances the model’s environmental adaptability and establishes an effective distributed paradigm for connected and autonomous vehicles (CAVs) to share driving experiences as well as make collaborative decisions. However, participants’ negative behavior, such as free riding due to selfishness, can significantly reduce federated learning (FL) training efficiency and model accuracy. Unlike previous studies that focused solely on a single FL task, this article proposes an incentive mechanism for long-term driving model training, which models the interactions between participants and the server during the long-term FL process as an infinitely repeated game. The incentive mechanism considers the relationship between participants’ historical behaviors and their future incomes, motivating participants to maintain positive behaviors throughout the long-term FL process and ensuring the efficient operation of the training process. Furthermore, in order to increase CAVs’ enthusiasm, we design reward rules that attract new participants and encourage sustained engagement. The simulation results demonstrate that the proposed incentive mechanism maximizes the profits of both CAVs and the server in long-term FL, which effectively reduces negative CAVs’ behaviors and improves the efficiency of FL training.

Federated learning (FL) is a promising technology for autonomous driving, enabling connected and autonomous vehicles (CAVs) to collaborate in decision-making and environmental perception while preserving privacy. However, traditional FL algorithms face challenges related to imbalanced data distribution, fluctuating channel conditions, and potential security risks associated with malicious attacks on local models. This paper proposes a fair and secure FL algorithm that not only addresses the challenges arising from imbalanced data distribution and fluctuating channel conditions, but defends against malicious attacks. Specifically, we first propose a personalized local training round allocation algorithm to balance energy costs and accelerate model convergence. Next, in order to further guarantee security, we embed an attack module based on Gini impurity. Extensive simulations demonstrate that the proposed algorithm achieves energy fairness, reduces global iteration time, and exhibits resistance against malicious attacks.

Unmanned aerial vehicle (UAV) relay networks with flexible and controllable characteristics are expected to complement the capacity of the gNB. This paper studies the multiplexing of enhanced Mobile BroadBand (eMBB) and Ultra-Reliable Low-Latency Communications (URLLC) in a multi-UAV relay network, where the strict latency requirement of URLLC can be achieved by the preemptive multiplexing of eMBB resources. However, this may affect eMBB reliability due to the transmission interruptions. Moreover, given the limited energy resources of UAVs, there is an inherent tradeoff among reliability, delay, spectral efficiency, and energy efficiency. To address these challenges, this paper develops a hierarchical UAV-assisted eMBB/URLLC multiplexing scheduling framework. For the eMBB scheduler, we first utilize multiple UAVs to assist the gNB in relaying eMBB traffic and formulate the eMBB resource allocation problem as an optimization problem. Then, we propose a decomposition-relaxation-optimization algorithm to maximize eMBB data rates while considering the personalized fairness of resource allocation and UAV power consumption. For the URLLC scheduler, we further consider the multiplexing of eMBB/URLLC traffic based on the optimization of eMBB resources. To reduce the performance fluctuations of eMBB, we propose a novel cross-slot strategy to schedule URLLC within two time slots rather than one time slot as in existing works. With this strategy, a deep reinforcement learning-based algorithm is proposed to obtain the optimal strategy for the preemption of URLLC on eMBB. Simulation results show that the proposed algorithms outperform the benchmark schemes in terms of convergence rate, eMBB reliability, personalized resource fairness, UAV consumption, and URLLC satisfaction.

Preemptive scheduling efficiently addresses the coexistence of enhanced Mobile Broad Band (eMBB) and Ultra-Reliable Low-Latency Communications (URLLC). While URLLC puncturing influences eMBB performance, further investigation is necessary to study the trade-offs between stability, delay, and efficiency. However, existing studies overlook the imbalance in eMBB/URLLC load distribution and personalized fluctuations in eMBB performance, leading to sub-optimal results. To tackle this, we propose an unmanned aerial vehicle (UAV) relay-assisted eMBB/URLLC multiplexing framework. Specifically, considering the utilization of UAVs for connecting separated next-generation Node Bs (gNBs) and the individual subject experience of services, we first formulate the multiplexing problem as an optimization problem. The objective is to maximize eMBB throughput and minimize personalized fluctuations in eMBB performance and UAV consumption, subject to URLLC constraints. Then, the challenging problem is decomposed into the eMBB problem and the URLLC problem. For the former, we further decompose it into three sub-problems and solve them using optimization methods. For the latter, we propose a deep reinforcement learning-based algorithm to obtain an optimal strategy for relaying and puncturing URLLC into eMBB intelligently. Simulation results demonstrate that our proposals outperform benchmark schemes regarding eMBB throughput, UAV consumption, eMBB performance fluctuation, URLLC satisfaction, and learning efficiency.

Cooperative perception is a promising approach to improve safety in autonomous driving by utilizing sensing data from cooperative devices. However, the real-time transmission and processing of large amounts of sensing data with limited network resources and different vehicle requirements pose significant challenges. To address this issue, we propose a joint sensing tasks and communication-computation resource allocation approach. The proposed approach considers a multi-objective optimization problem of total value of information and delay-energy consumption under resource-constrained and differentiated information quality conditions. To solve the formulated problem, we decompose it into two stages. In the first stage, the sensing tasks allocation algorithm is proposed to select optimal sensing data for vehicle requirements based on differences in information quality. In the second stage, the communication-computation resource allocation algorithm is proposed to balance the delay and energy consumption of sensing tasks execution. Simulation results demonstrate that the proposed scheme is more effective than the benchmark schemes in addressing the challenges posed by cooperative perception with limited resources.

Task offloading is a potential solution for computation-intensive vehicular applications due to limited on-board computing resources. However, traditional model-driven methods are hindered by long online processing time, while data-driven methods are deficient in interpretability and generalizability. To overcome this challenge, this paper formulates the resource allocation for task offloading in connected autonomous vehicles (CAVs) as a multi-objective optimization problem, and proposes a novel knowledge-driven algorithm that integrates both model-driven and data-driven methods. Specifically, the framework of a model-driven alternating minimization (AM) algorithm, which solves the formulated problem via alternatively optimizing power allocation subproblem and bandwidth and CPU frequency allocation subproblem, is regarded as knowledge. Inspired by such knowledge, our proposed knowledge-driven neural network consists of two long short term memory networks (LSTMs) to alternatively updating these two subproblems. Furthermore, to get away from the local optimum usually occurred in the AM algorithm, our proposed knowledge-driven neural network updates network parameters with the global loss function. Simulation results demonstrate that our method outperforms both the AM algorithm and the LSTM without knowledge.

Edge intelligence and federated learning (FL), as key enablers of 6G, is a promising solution for networked Autonomous Driving (NAD). However, traditional federated learning is a server-client architecture, which makes the model training overly dependent on a fixed single aggregation server and makes the FL process insecure and unreliable due to the vulnerability of the aggregation server to a single point of failure. In this paper, we propose a rotating server FL scheme (RSFL) to solve the problem of single point of failure and limited resources and improve environmental adaptability. Specifically, we consider multiple factors to measure the vehicle performance and find the vehicle with the highest performance score in this round as the server for the next round while setting weights that are randomized in each round, which reduces even more the likelihood that a malicious user will recognize the regularity of the chosen server. Finally, the performance of RSFL is evaluated through a large number of experiments, and the results show that compared with baseline FL, FL with randomly selected servers, and peer-to-peer decentralized FL, RSFL can effectively reduce the cases of servers being detected and attacked by malicious adversaries, and improve the accuracy of the model.

Millimeter wave (mmWave) communication requires huge beam training overhead, which is highly undesirable in vehicle-to-infrastructure (V2I) communication, due to the requirement for low latency and high reliability. Sensory information can be utilized to reduce the beam training overhead. However, single-type sensors have limitations that result in inadequate performance when used independently for assistance, while employing multi-type sensors sensors for assistance presents challenges such as data redundancy and a large volume of data. To tackle the aforementioned issues, we propose a multisource low redundancy data-aided beam prediction (MLRDBP) scheme. Specifically, we first extract and fuse features from LiDAR, GPS, and camera data. Then, we employ the principal component analysis (PCA) algorithm to reduce the dimensionality and redundancy of the fused features. Finally, we design a classification model based on a multi-layer perceptron (MLP), training it with the fused low redundancy features to predict the optimal beam direction for communication parties. The simulation results indicate that the proposed scheme achieves the accuracy exceeding 76.9% for top-1 beam prediction, offering satisfactory performance with lower data redundancy compared to single-sensor-aided schemes and other existing schemes.

With the dispersed and privacy-preserving features, federated learning (FL) enables connected and autonomous vehicles (CAVs) to achieve cooperative perception, decision-making, and planning by utilizing the learning capabilities and sharing model parameters. However, the discrepancies in local training cost and model upload durations between various CAVs make the energy and time costs caused by traditional FL algorithms unfair. In this paper, a fair and efficient FL algorithm is proposed with to address the challenges arising from imbalanced data distribution and fluctuating channel conditions. Specifically, to achieve uniformity in total time and energy cost among CAVs, a personalized approach is employed for the local training rounds of each CAV. This approach ensures fairness and training effectiveness while reducing the local training time in each round of global iteration. Furthermore, it enhances the convergence speed of the global model. Extensive simulations demonstrate that the proposed algorithm achieves fairness in energy cost while reducing the duration of each round of global iteration.

Integrated sensing, communication, and computation (ISCC) has become one of the research hotspots focused on the sixth generation (6G) communication systems. However, due to the demand for the coexistence of sensing, communication, and computing functions, there is uneven scheduling of resources among all parties, resulting in difficulties in accurately perceiving the environment, processing massive data efficiently in real-time, and experiencing large latency in task processing in the Internet of Vehicles (IoV). In this work, we propose a novel wireless scheduling architecture to enhance the coordination gains of sensing, communication, and computation from a perspective of joint optimization, enabling true on-demand services. Specifically, we first adopt the modified Cobb-Douglas utility function, the communication rate, perception of mutual information (MI), and calculation delay as coordinated gains. Next, we formulate a joint user association and subchannel assignment problem to capture the network externalities induced by resource competition among vehicle user devices (VUEs) with multi-functional requirements. To achieve a mutually satisfactory solution, we propose the dung beetle optimizer (DBO) algorithm to maximize the average utility of all VUEs in the network. Simulation results show that, compared with the baseline algorithm, the average utility gain of the proposed algorithm can reach up to 7.21%.

Federated learning (FL), as a distributed technology, has great application potential in autonomous driving. However, due to the lack of a quality verification mechanism for the client, it faces the problem of malicious users attacking the global model, which reduces the accuracy of FL model. In response to this problem, this paper proposes a hierarchical blockchain-enabled FL with reputation management scheme, which improves the efficiency and accuracy of FL while ensuring privacy and security. In this paper, we first propose a hierarchical blockchain framework and design a blockchain consensus algorithm based on parameter proof of quality (PoQ), which can provide FL workers with a secure and efficient data storage environment in a decentralized manner, while making up for the poor scalability of traditional single blockchains. On this basis, we design a reputation management method based on Bayesian theory and multiple subjective logic models to select high-quality local participating users. In particular, the weights of factors such as interactive activity and interactive position are taken into account to improve the accuracy of reputation calculations. Extensive simulations validate the performance of our scheme in improving FL accuracy and efficiency.

The virtual world created by the development of the Internet, computers, artificial intelligence (AI), and hardware technologies have brought various degrees of digital transformation to people’s lives. With multiple demands for virtual reality increasing, the metaverse, a new type of social ecology that can connect the physical and virtual worlds, is booming. However, with the rapid growth of data volume and value, the continuous evolution of the metaverse faces the demands and challenges of privacy, security, high synchronization, and low latency. Fortunately, the ever-evolving blockchain and intelligent networking technologies can be used to satisfy the trusted construction, continuous data interaction, and computing demands of the metaverse. Therefore, it is necessary to conduct an in-depth review of the role and gains of blockchain, intelligent networking, and the combination of both in providing the immersive experiences of the metaverse. In this survey, we first discuss the development trend, characteristics, and architecture of the metaverse. Then, the existing work on blockchain, networking, and the combination of the two technologies are reviewed, including overviews, applications, and challenges. Next, applications of the metaverse are summarized, emphasizing the importance of the metaverse and the fields of development. Finally, we discuss some open issues, challenges, and future research directions.

Currently, the complex traffic environment challenges the fast and accurate response of a connected autonomous vehicle (CAV). More importantly, it is difficult for different CAVs to collaborate and share knowledge. To remedy that, this paper proposes a selective federated reinforcement learning (SFRL) strategy to achieve online knowledge aggregation strategy to improve the accuracy and environmental adaptability of the autonomous driving model. First, we propose a federated reinforcement learning framework that allows participants to use the knowledge of other CAVs to make corresponding actions, thereby realizing online knowledge transfer and aggregation. Second, we use reinforcement learning to train local driving models of CAVs to cope with collision avoidance tasks. Third, considering the efficiency of federated learning (FL) and the additional communication overhead it brings, we propose a CAVs selection strategy before uploading local models. When selecting CAVs, we consider the reputation of CAVs, the quality of local models, and time overhead, so as to select as many high-quality users as possible while considering resources and time constraints. With above strategic processes, our framework can aggregate and reuse the knowledge learned by CAVs traveling in different environments to assist in driving decisions. Extensive simulation results validate that our proposal can improve model accuracy and learning efficiency while reducing communication overhead.

Federated learning (FL), as a distributed machine learning technology, allows large-scale nodes to utilize local datasets for model training and sharing without revealing privacy, which has significant efficiency and advantages in artificial intelligence (AI)-based knowledge sharing of connected and autonomous vehicles (CAVs). However, for FL, there are challenges to ensure the security of knowledge, deal with the lazy behavior of participants, and enforce effective incentives. To bridge the gaps, in this paper, we first propose a hierarchical blockchain-supported FL architecture that utilizes the immutable and transparent properties of blockchain to enable secure storage and sharing of knowledge and transaction information with scalability. Then, considering the cost and laziness of the participants in the FL process, we propose an incentive mechanism combined with the supervision game to attract high-quality participants based on a comprehensive evaluation of model quality and participants’ reputation. Extensive simulation results validate that our proposal can improve learning accuracy and efficiency while ensuring security.

With accurate network traffic prediction, communication systems can make self-management and embrace efficient automation. However, due to the lack of consideration of dynamic spatial interactions between regions in existing methods, the performance of network traffic prediction still needs to be improved. To solve the above problem, this paper proposes a spatiotemporal dynamic relative-flow network (STDRN) to capture the dynamic spatial dependency, thereby improving the accuracy of urban network prediction. In the proposed STDRN, we take both spatial and temporal dependence of network traffic into consideration. First, we propose relative-flow gating mechanism (RGM) combined with convolutional neural network (CNN) to learn the dynamic spatial dependency. Then, we adopt the periodic shifting attention mechanism to capture the long-term periodic temporal dependency while long short-term memory (LSTM) for the short-term temporal dependency. The STDRN is tested on real-world network traffic dataset. Experimental results demonstrate that compared with other benchmark methods, STDRN can reduce RMSE by up to 48.99% and MAPE by 13.61%, which proves the effectiveness of our proposal.

Accurately discovering hazards and issuing appropriate warnings to drivers in advance or performing autonomous control is the core of the Collision Avoidance (CA) system used to solve traffic safety problems. More comprehensive environmental awareness, diversified communication technologies, and autonomous control can make the CA system more accurate and effective, thereby improving driving safety. In addition, the assistance of Artificial Intelligence (AI) technology can make the CA system adapt to the environment and facilitate fast and accurate decisions. Considering the current lack of a thorough survey of driving safety with sensing, vehicular communications, and AI-based collision avoidance, in this paper, we survey existing researches for state-of-the-art data-driven CA techniques. Firstly, we discuss the major steps of CA and key research issues. For each step, we review the existing enabling techniques and research methods for CA in detail, including sensing and vehicular communication for safe driving, as well as CA algorithm design. Particularly, we present a comparison between the most common AI algorithms for different functions in the CA system. Testbeds and projects for CA are summarized next. Finally, several open challenges and future research directions are also outlined.

The complex traffic and road environment pose considerable challenges to the accuracy, timeliness, and adaptive ability of connected and autonomous vehicles (CAVs) in making driving decisions. This paper uses vehicle collaboration and integrates the adaptive learning capabilities of machine learning and the interpretation capabilities of expert systems (ESs) in a unified architecture to form a hybrid autonomous driving guidance system, which not only solves the “bottleneck” of knowledge acquisition during the construction of expert systems but also solves the “black box” phenomenon of machine learning in the decision-making process. First, an autonomous driving strategy based on deep reinforcement learning (DRL) is proposed for CAVs to make decisions and extract corresponding rules. Next, we design an ES knowledge base expansion method including rule extraction, rule sharing, and rule test. Particularly, vehicular blockchain is adopted to ensure user privacy and data security during the rule-sharing process. Third, hybrid autonomous driving guidance combining ES and machine learning is proposed for CAVs to make accurate and efficient decisions in different driving environments. Once the strategy is well trained, it can effectively guide CAVs to cope with the complex traffic environment. Extensive simulations validate the performance of our proposal in terms of decision-making accuracy, effectiveness, and safety.

Recent advancements in edge computing and edge caching provide a feasible solution to support a plethora of new applications such as on-demand videos, AR/VR, road surveillance. However, to apply edge caching in vehicular scenarios is still difficult due to the unkonwn request pattern of vehicular users and intermittent service links between vehicles and edge servers (e.g., Road Side Units, RSUs). In this paper, we aim to investigate the vehicular edge caching problem in practical vehicular scenarios by considering higher hit ratio, while avoiding interruption of caching services. Specifically, to obtain a higher hit ratio, we firstly propose an on-demand adaptive cache algorithm. The algorithm can adjust the eviction time of cached contents by tracking the dynamics of requests and content popularity. We then develop an analysis framework to model the interruption performance of caching services from RSUs. Through diffraction approximation theory, the service process can be modeled as a joint process of the movement and stopping of vehicles to deduce the interruption ratio. To apply the on-demand adaptive cache algorithm in practical scenarios, the final caching decisions should be corrected by incorporating the interruption performance. Therefore, a$\alpha $-fair utility-oriented vehicular edge caching scheme is developed, which can achieve the tradeoff of hit ratio and interruption ratio. Performance evaluation shows the advantages of our proposed vehicular caching scheme in hit ratio, accuracy of analysis model, utility, respectively.

The rapid growth of connected and autonomous vehicles (CAVs) shows an urgent demand for driving and transportation-related data, which gives rise to vehicular crowdsensing systems (VCSs). Nevertheless, the existing centralized VCS framework mainly faces the system reliability problem while the decentralized one cannot satisfy the management flexibility. In addition, when the privacy preservation scheme that prevents information leakage encounters the user selection scheme that desires detailed information of participants, how to balance this seemingly irreconcilable contradiction is inevitable for VCS. To remedy that, we take the first research attempt and explore the balance point between the system management, privacy preservation, and quality of experience (QoE) of participants. By fully exploiting the characters of participating entities, a blockchain-enabled conditional decentralized VCS is proposed in this paper. Firstly, we propose a privacy-preserving scheme where the zk-SNARK proof combines with the mixed-task smart contract to guarantee the interaction process will not reveal any private information of participants. Secondly, we propose an efficient reputation management mechanism that renders certain the participants can get a satisfactory QoE even under the condition that the private information of users is secured. And also, the malicious operations in the system will be effectively supervised. Theoretical analysis and extensive simulations demonstrate the security and efficiency properties of privacy preservation and indicate the effectiveness of reputation management.

Realizing driving safety is the fundamental goal pursued by artificial intelligence (AI)-enabled autonomous driving. However, due to the limited capacity of vehicles and the limited scenarios involved, the reliability and environmental adaptability of the current single-vehicle intelligence still need to be improved. In addition, driving knowledge only exists locally in each connected autonomous vehicle (CAV) and cannot be effectively reused or shared with other CAVs. To solve the above problems, this paper proposes to use federated learning (FL) to realize the collaboration of CAVs without revealing local data, thereby improving the accuracy of CAVs decision-making and driving safety. First, for the typical rear-end collision scenario, we propose a local decision-making model that comprehensively considers multiple influencing factors to fit the actual traffic environment. Then, we design a federated learning process for knowledge sharing. In particular, we propose a model similarity method to select high-quality local models for upload, thereby reducing communication overhead while improving the accuracy of the global model. Extensive simulations validate the performance of our proposal in reducing communication overhead and improving decision accuracy.

Recently, with a large number of on-board sensors, vehicles have been widely used for Vehicular Crowdsensing (VCS). Appropriate multi-task assignment strategy is crucial for V CS. However, sensing efficiency and benefit of the system of the existing works need to be improved due to the following challenges. On one hand, many sensing tasks have clustering characteristics in terms of their geographic distribution and sensing requirements, but current works are often ignored. On the other hand, existing multi-task assignment strategies often only design optimization problem for the benefit of one of the platform or participants, and fail to maximize the overall benefit of the system. To remedy that, this paper proposes a multitask assignment for tasks with clustering characteristics. First, we propose a task combination algorithm, which can greatly improve the task assignment efficiency and reduce the sensing cost. Next, we design a two-stage task assignment scheme, in which the benefits of the platform and participants are optimized respectively in two stages to maximize the benefit of the system. Finally, we carry out extensive simulations, and the simulation results verify the effectiveness of our proposal from clustering validity and sensing cost.

With the development of communication and Internet of Vehicles (IoV) technology, a large number of high precision sensors and computing units are widely used and deployed on vehicles. With the vehicles work as users, Mobile Crowdsensing (MCS) system has a broad application prospect in traffic planning, environmental monitoring and so on. The realization of these applications needs a large amount of data. However, in the process of crowdsensing, users are often faced with the consumption of computing, communication and energy and the risk of privacy leakage, so they are reluctant to actively participate. Therefore, we need to design a safe and reasonable incentive mechanism. In this paper, we focus on privacy protection and user incentive, and propose a framework of the vehicular crowdsensing with blockchain, as well as the smart contacts deployed on the blockchain. The characteristics of the blockchain are used to solve the security problems in the crowdsensing process. In addition, we propose a reverse auction-based incentive mechanism. A group of users with the highest reputation value are selected to complete the sensing tasks, and the payoffs are assigned according to the quality of the sensing data uploaded by the selected users. Finally, Matlab-based simulation verifies the effectiveness of the incentive mechanism proposed in this paper.

The positioning accuracy of the existing vehicular Global Positioning System (GPS) is far from sufficient to support autonomous driving and ITS applications. To remedy that, leading methods such as ranging and cooperation have improved the positioning accuracy to varying degrees, but they are still full of challenges in practical applications. Especially for cooperative positioning, in addition to the performance of methods, cooperators may provide false data due to attacks or selfishness, which can seriously affect the positioning accuracy. By fully exploiting the characteristics of blockchain and edge computing, this paper proposes a vehicular blockchain-based secure and efficient GPS positioning error evolution sharing framework, which improves vehicle positioning accuracy from ensuring security and credibility of cooperators and data. First, by analyzing the GPS error, a bridge can be established between the sensor-rich vehicles and the common vehicles to achieve cooperation by sharing the positioning error evolution at a specific time and location. Particularly, the positioning error evolution is obtained by a deep neural network (DNN)-based prediction algorithm running on the edge server. We further propose to use blockchain technology for storage and sharing the evolution of positioning errors, mainly to guarantee the security of cooperative vehicles and mobile edge computing nodes (MECNs). In addition, the corresponding smart contracts are designed to automate and efficiently perform storage and sharing tasks as well as solve inconsistencies in time scales. Extensive simulations based on actual data indicate the accuracy and security of our proposal in terms of positioning error correction and data sharing.

Three-dimensional (3D) highly dynamic unmanned aerial vehicle networks (UAVNets) could serve as a pivotal intermediate architecture in air and space integration networks. For UAVNets, efficient routing protocols for data packet delivery are crucial to its wide use. However, communication in UAVs has been a challenging project because of frequent failures at forwarding nodes. In this paper, we propose a localized heuristic solution, called the reliability-aware adaptive greedy-multicast routing (RAGM-3D), to reduce the negative impact of failure on route forwarding. RAGM-3D dynamically adjusts the next-hop forwarding node set which, initially selected by a new multi-factor hybrid greedy strategy, are based on the reliability evaluation to route packets to the destination efficiently. Simulation results show that comprehensive performance of RAGM-3D in terms of packet delivery ratio, delay, and routing overhead outperforms other compared protocols.

Leveraging the Internet of Vehicles (IoV) to accurately and timely disseminate traffic information, especially for emergency information, is an important way to improve traffic safety and efficiency. However, privacy and security issues in the information transmission process will seriously affect the reliability of the information dissemination system. In this paper, we propose a decentralized targeted information dissemination framework in vehicular networks based on blockchain techniques. In this framework, the information collected by users is uniformly judged and identified by Roadside Units (RSUs), and finally packaged and uploaded to the blockchain that makes the system run more stable and reliable. Further more, we utilize reputation evaluation algorithm to comprehensively process the collected information, and we design the corresponding reputation management system to stimulate more users to participate in the system and provide as accurate information as possible. Extensive simulation results reveal that the proposed framework is effective and feasible in collecting, filtering, conducting, and disseminating in vehicular networks.

Inappropriate lane following and changing behaviors of connected and autonomous vehicles (CAVs) can result in accidents, such as rear-end collision and side collision. To remedy that, the use of deep reinforcement learning (DRL) for autonomous driving decisions is currently a widely used promising solution. In this case, the accuracy and effectiveness of such a machine learning (ML) model is quite essential for this artificial intelligence (AI)-enabled CAVs. This article proposes a blockchain-based collective learning (BCL) framework for autonomous lane-changing systems. Four key issues, namely, learning efficiency, data security, users' privacy, as well as communication burden, are addressed by applying collective learning, vehicular blockchain, and knowledge transfer. First, we model the lane-changing problem as a DRL process and learn the autonomous lane-changing strategy through the deep deterministic policy gradient (DDPG) algorithm. Second, a single CAV involves a limited number of driving scenarios, and the independent learning method has the problem of inefficiency. Therefore, we propose a collective learning framework to utilize the “collective intelligence” shared by CAVs. Third, a vehicular blockchain is then applied to ensure the security and privacy of the user and data. In addition, the introduction of the blockchain can incentivize more users to participate in collective learning. Finally, in order to accelerate the learning process and achieve higher level performance while further reducing the communication burden, we use the corresponding knowledge extracted from the ML model such as human learning, as privileged information for sharing instead of directly sharing local ML models. Extensive simulation results validate the effectiveness and efficiency of our proposal in terms of learning efficiency, driving safety, as well as system security and robustness.

Although vehicular global positioning system (GPS) has been widely applied in many traffic scenarios, it is far from achieving lane-level positioning due to its low accuracy. Existing cooperative positioning (CP) methods have improved vehicular positioning accuracy to varying degrees, which still have challenges in further improving the system's robustness and security. In this article, we propose a novel framework of blockchain-enabled Internet of Vehicles (IoV) with CP for improving vehicular GPS positioning accuracy, system robustness, and security. First, a self-positioning correction scheme for the intelligent vehicles is proposed to improve their positioning accuracy, which uses the multitraffic signs as benchmarks to correct the vehicular position (given by GPS) by deep neural network (DNN) algorithm. We further design a multi-intelligent vehicle positioning error sharing model to reduce GPS positioning error of common vehicles (CoVs) in the same segment or area. In addition, to realize information sharing between vehicles and ensure system security, the connections among intelligent vehicles, CoVs, and roadside units are built by proposing a blockchain-enabled architecture that includes IoV subsystem and blockchain subsystem, where the corresponding mechanism of the information choosing, information sharing, and penalty is designed. Extensive simulation results show the accuracy, robustness, and security of our proposal in terms of vehicular positioning, information transferring, and sharing.

Realizing the ultra-low latency and high-accuracy solutions for rear-end collision is still challenging, especially under the condition in which many uncertainties exist. This paper proposes an artificial intelligence-based warning algorithm for rear-end collision avoidance. Three key issues are addressed by applying the neural network approach, including noises in positioning, inaccurate risk assessment, and enhanced comfort level of passengers. First, to filter the noises in positioning, wireless vehicular communications are leveraged; accurate relative lane positioning can be achieved to justify when two vehicles are in the same lane. Second, an online neural network model is developed to assess the risk of collisions in real time while driving. The algorithm can converge fast to a globally optimal solution and adapt to different traffic environments. Third, to maximize the comfort of passengers during the braking process, a graded warning strategy is developed at the prerequisite of guaranteed safety. With the above schemes sewed in to one framework, our proposal can achieve rear-end warning with reduced missing alarm rate, accurate risk assessment and enhanced comfort to passengers. The extensive simulations validate the effectiveness and accuracy of our proposal in terms of relative lane positioning, risk assessment, and collision avoidance.

Collision on road is a classic and important problem as it brings about great loss on humans' safety and the efficiency of the traffic system. Numerous algorithms have been proposed to address the issue, and most of the existing researches are focused on rear-end, overtaking and lane change scenarios. However, due to the massive computing process, limitation of prediction time and complex layouts at intersections, most conventional algorithms are not suitable for intersection collision avoidance. This paper makes a theoretical analysis on the variations of vehicle states taking advantage of the Dynamic Bayesian Networks (DBNs). Based on the analysis, the risk assessment process is made out to identify a dangerous situation. Different collision avoidance strategies are implemented to avoid accidents if a potential danger is detected and the driver is informed of warning. Simulations are carried out to evaluate the ability of the proposed algorithms on detecting and mitigating a vehicle collision. Results show that the proposed algorithms have great performance in handling the vehicle collisions at intersections.

Mobility models play a vital role in Vehicular Ad Hoc Networks (VANETs) simulations. Moreover, mobility models with higher extent of reality to fit into the characteristics of VANETs better make simulations more credible and accurate. However, most of traditional mobility models only devote to planar and ideal scenarios. It is rare for them to reflect more realistic environments, such as ubiquitous 3D scenarios where accidents occur frequently because of the complex vehicle motion and human factors. To address these issues, a Three-dimensional Accident Driver Model (T-ADM) is proposed for VANETs in this paper to reflect the real world more realistically. With characteristics based on the combination of plane and space in VANETs, T-ADM can produce 3D scenarios like viaducts in VANETs. Furthermore, T-ADM can mimic the non-standard driver behavior and generate accident scenarios. Finally, a comparison among T-ADM and other mobility models is generated by Matlab and VanetMobiSim. It demonstrates that T-ADM is able to not only reflect the corresponding realistic characteristics mentioned above but also give an objective description of vehicle density and velocity in VANETs.