Automated vehicles (AVs) are transforming urban transportation systems, as end-to-end autonomous driving models show great promise in enhancing traffic safety and operational efficiency. Despite these advances, their performance in highly interactive driving scenarios remains limited due to insufficient decision-making diversity and the absence of explicit safety guarantees. To address these challenges, we propose NavDrive, a safety-enhanced end-to-end autonomous driving framework that formulates planning as a multi-modal generative process.Specifically, NavDrive integrates navigation-based guidance into a diffusion policy. To focus on decision-critical information, a Decision-Aware Channel Fusion (DCF) module adaptively emphasizes regions involving key interactions between the ego vehicle and surrounding agents. Furthermore, a safety-aware generative planner refines trajectory samples toward feasible regions via the Target-Prior Diffusion Transformer (TDiT), which explicitly embeds physical constraints to ensure safe and human-aligned driving behaviors. Extensive experiments on the NAVSIM and nuScenes benchmarks demonstrate that NavDrive consistently outperforms existing baselines, delivering substantial gains in planning quality, safety, and robustness under complex and adverse conditions. The details will be available athttps://github.com/zgchongbo/NavDrive

Unmanned aerial vehicles (UAVs) play a pivotal role in air-ground collaborative mobile edge computing (MEC) systems. They function as aerial cloudlets, deploying flexibly closer to ground users (GUs) to provide enhanced computational capacity in edge computing scenarios. While extensive studies have optimized resource allocation and UAV trajectories collaboratively to improve energy and offloading efficiency, few have simultaneously addressed the system's communication security and reliability. This paper proposes a joint optimization model to ensure both security and reliability in an energy-efficient UAV-assisted MEC system. Specifically, we introduce an artificial noise generation technique to enhance system security and derive a closed-form expression for the optimal ratio between the generated noise and the data transmission power to ensure secure communication. Additionally, we propose a probabilistic model to characterize the reliability of data transmission and derive the worst-case transmission rate. Furthermore, we present an energy-efficient model for optimizing resource allocation and UAV trajectory planning, with the goal of improving the overall energy efficiency of the UAV-assisted MEC system. Finally, we design an optimization algorithm with polynomial-time complexity based on the augmented Lagrangian multiplier method. Simulation results demonstrate that the proposed method outperforms existing approaches in terms of both global secure energy efficiency and average secure energy efficiency.

Multimodal Large Language Models (MLLMs) possess extensive knowledge and strong reasoning capabilities, achieving remarkable performance in knowledge-based visual question answering, significantly surpassing traditional small-scale Vision-Language Models (VLMs). However, the distinct training paradigms of MLLMs and small-scale VLMs result in misaligned feature representation spaces and divergent answer prediction distributions. To bridge this gap, we propose a novel end-to-end large-small model synergy framework, where small VLMs and MLLMs collaborate via synergistic optimization of shared objectives while maintaining their co-evolving complementary specializations. Specifically, multimodal fine-grained heuristics are extracted from well-tuned small VLMs and subsequently projected into the textual space of MLLMs through dedicated visual and textual collaboration modules. This enables cross-modal guidance for both visual and textual inputs. Finally, a dual-objective synergy loss promotes alignment toward shared goals, while a visual discrepancy loss preserves specialization diversity. Extensive experiments demonstrate that our framework achieves state-of-the-art performance on both the OK-VQA and A-OKVQA benchmarks.

Trajectory planning and obstacle avoidance technologies for unmanned aerial vehicles (UAVs) are widely applied in Internet of Things-based intelligent urban management, data collection, and related fields, and are increasingly becoming a global research hotspot. However, uncertainties in trajectory planning caused by factors such as sensor measurement noise, model mismatch, and environmental disturbances can compromise the safety and robustness of UAV flights. While existing optimization-based methods build complex nonlinear models, they are often computationally expensive and inefficient. Learning-based methods, on the other hand, demand substantial computational resources. In this paper, we develop a nonlinear chance-constrained trajectory planning model that explicitly accounts for uncertainties, enabling autonomous obstacle avoidance and landing of UAVs on a dynamic platform. We derive the robust equivalent form of the chance constraints to address the solvability of models that include uncertainty factors. We develop a method that combines lossless convexification with the sequential convex programming (SCP) algorithm to achieve low complexity and high-efficiency solutions. Additionally, a real-time planning framework is proposed to address uncertain dynamic environments. We validate the robustness and safety of the proposed algorithm under various dynamic and uncertain scenarios, including different levels of disturbance, moving platforms, and unpredictable obstacles.

Virtual coupling (VC) is perceived to be promising in raising rail traffic capacity. In a train-to-train (T2T) based VC system, a communication network that ensures high quality of service (QoS) plays a critical role in enhancing both the coupling efficiency and the safety of the train platoon. However, unreliable communication environments characterized by issues such as time delays, packet loss, and network attacks present significant security risks to virtually coupled train sets (VCTS). How to cope with the impact caused by unstable communication and realize safe and stable VCTS formation are an important challenge for the VC system. In this paper, we propose a model predictive control (MPC) based distributed bidirectional control (DBC) strategy to tackle these challenges. We propose a control framework that integrates MPC with linear feedback-feedforward control to achieve real-time optimal control of the VC system, utilizing a bidirectional communication topology. To stabilize the VCTS, we derive local and string stability conditions to be satisfied by the controller parameters under asymmetric time-lagged unreliable networks, and utilize them as real-time constraints for the MPC controller. Furthermore, an analysis of the scalability of the proposed strategy has been conducted to improve its adaptability. Simulation results demonstrate that the proposed MPC-based DBC strategy significantly reduces the VCTS formation time and the maximum fluctuation of VCTS by 28.57% to 41.86%, and 28.84% to 52.10%, respectively, across various unreliable communication scenarios.

Unmanned aerial vehicles (UAVs) have rapidly advanced in applications such as disaster response, infrastructure inspection, and smart city systems. However, cooperative coverage mission planning in dynamic environments poses a persistent challenge in balancing global optimization with real-time responsiveness. To address this, we propose a two-stage task allocation framework based on a dual-ring dynamic scheduler. In the centralized planning phase, an enhanced NSGA-II algorithm is developed, incorporating dual-population initialization, path-exchange crossover, and multi-strategy mutation. Experimental results demonstrate a 49% improvement in the hypervolume indicator over the baseline NSGA-II, with average reductions of 13.33% and 23.71% in total and maximum execution times, respectively. In the dynamic scheduling phase, we design a distributed auction mechanism leveraging a dual-ring communication topology, capable of handling six types of events: UAV failure, UAV addition, node cancel exploration, node urgent exploration, node re-exploration and node in-depth exploration. Through event-driven auctions and group-based bidding, the system maintains a load imbalance under 28% and achieves effective rebalancing even under scenarios with over 50% UAV loss. These results validate the robustness and adaptability of the dual-ring dynamic scheduler in real-time collaborative coverage missions. The proposed method demonstrates significant potential in dynamic, large-scale UAV applications. Source code will be available at: https://github.com/GradualScholar/CoverageMissionPlannin.git

Vision-centric motion prediction concentrates on accurately determining the instance mask and its future trajectory from surround-view cameras, which manifests inherent merits such as holistic perspective and fully-differentiable spirit. Nonetheless, it is still impeded by sparse bird’s-eye view (BEV) representation and unfavorable temporal context across frames, resulting in a sub-optimal solution to decision-making and vehicle navigation. In this work, we propose a novelDifference-guideMotionPrediction for vision-centric autonomous driving, that is DMP, where it integrates BEV map refinement with spatial-temporal relation modeling in a hierarchical manner. Specifically, a bidirectional view projection strategy is introduced for the complementary BEV feature generation via depth-consistency correction. To promote spatiotemporal context aggregation, we design a difference-guided motion approach by offset approximation to align motion-aware cues between adjacent frames, and a dual-stream pyramid module is further developed for historical information fusion and future instance segmentation during specific durations. Extensive experiments on the large-scale nuScenes dataset demonstrate that it outperforms the baselines by a remarkable margin and delivers competitive motion prediction across diverse scenarios and range settings, suggesting its effectiveness and superiority. The details will be available athttps://github.com/pupu-chenyanyan/DMP-VAD.

Unsignalized intersections represent a typical societal road scenario, where severe spatio-temporal conflicts occur in the central area. The indiscriminate competition for spatio-temporal resources by vehicles at intersections leads to low traffic efficiency and frequent accidents. This paper proposes a universal and unified multi-vehicle cooperative motion planning framework for intersections, coupling optimization scheduling with vehicle motion control tasks, with the aim of achieving more rational resource allocation and enhanced efficiency. Specifically, the proposed optimal control conflict-based search (OPC-CBS) algorithm constructs a conflict search tree for spatio-temporal conflict detection, and further formulates a multi-objective optimization control problem based on conflict objects. This effectively transforms the large-scale global optimization problem into a small-scale multi-stage optimization problem, achieving a balance between optimality and computational efficiency. The algorithm efficiently establishes the passing order and motion trajectories of connected and automated vehicles (CAVs) in continuous spatio-temporal domains. Simulation experiments demonstrate that the proposed algorithm can comprehensively address multiple objectives such as vehicle kinematic constraints, environmental constraints, and performance constraints in complex and dynamic scenarios. It achieves approximately an 89.06% improvement in solution efficiency while reducing energy consumption by around 17.11%.

With increasing emphasis on vehicular automation and traffic efficiency, the management and coordination of platoon-based systems have become important. This research introduces a unique control framework based on a behavioral stability strategy, designed to enhance the cohesion of vehicle platoons and improve their ability to resist disturbances. Our approach integrates a vehicle scheduling system with a real-time platoon control mechanism to enhance the behavioral stability, robustness, and safety of the platoon. Given the heterogeneous nature of vehicles, we propose an optimal platoon formation model. This model strategically determines the number of platoons, arranges the sequence of vehicles within each platoon, and selects optimal cruising speeds to maximize platoon cohesion. To further enhance system robustness, a centralized robust model predictive controller is deployed for each platoon, ensuring stability against stochastic perturbations in vehicle dynamics and guaranteeing platoon safety. Finally, we conduct a simulation study involving multiple platoons with 20 heterogeneous vehicles to validate the effectiveness of the multi-layer optimization model.

Platoon-based connected vehicles have recently received increasing attention from academia and industry since they are considered promising solutions to transform our mobility society into the next generation. Vehicular communication and platoon coordination are two aspects of enabling technologies for mobile edge computing (MEC)-enabled cooperative vehicle-infrastructure systems (CVIS), while few efforts have incorporated these two dimensions into a joint implementation framework. In this paper, we investigate the problem of joint car-following coordination and data transmission scheduling of vehicle platoons. We develop a two-tier hierarchical framework for vehicle platooning: a fuel-efficient mobility optimization layer for car-following coordination and a reliable vehicle-to-infrastructure (V2I) communication layer for data transmission scheduling. Specifically, we present a platoon-based fuel consumption minimization model and a car-following control protocol to derive fuel-efficient control inputs. We also propose a reliability-oriented and delay-constrained data transmission scheduling model that is driven by upper-layer car-following coordination. We derived a closed-form expression for the reliability-optimal data transmission scheduling solution, which incorporates platoon mobility, channel characteristics, and application requirements. With simulations, we show that our joint method improves fuel efficiency and communication reliability for platooning vehicles. In particular, the proposed method reduces the platoon’s fuel consumption per time slot by 16.4%, meanwhile making the communication reliability 1.31 times higher than other traditional methods.

Uncrewed aerial vehicles (UAVs) play a crucial role in mobile edge computing (MEC) within space-air-ground integrated networks. They serve as aerial cloudlets, enabling task processing in close proximity to ground users. While numerous joint trajectory design and resource allocation schemes aim to enhance energy efficiency or computation rate, few focus on improving system reliability, which is often challenged by stochastic channels and node mobility. This paper presents a stochastic modeling perspective to derive a system reliability expression. Our reliability formulation incorporates the impacts of stochastic Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) air-to-ground communication channels, application data load, available bandwidth, offloading time, and transmission power. This comprehensive approach leads to a reliability-oriented joint optimization model that considers not only resource allocation and user data transmission scheduling but also the motion of UAVs. To solve this problem, we propose a low-complexity algorithm. By utilizing augmented Lagrangian multipliers, the algorithm transforms nonlinear constraints into a tractable formulation, enabling the utilization of legacy unconstrained optimization techniques. We provide a proof of convergence for this algorithm. Through simulations, we demonstrate that our proposed method guarantees convergence within finite iterations and improves the average communication reliability in comparison with several other joint optimization schemes.

Recently emerged vehicle-to-everything (V2X) perception has revealed great potential to overcome the limitation of single-vehicle intelligence aided by vigorous interaction among on-road agents, while prior endeavors are practically developed on parameter-specific simulation or configuration-dynamic real-world setting, overlooking the transferability across various scenarios. In this article, we propose unsupervised domain-adaptive vehicle-to-everything collaboration framework dubbed CUDA-X, which is built on top of a de facto collective model with key-point information exchange and instance adaptation. Specifically, collaborative knowledge transfer (CKT) is responsible for domain-agnostic feature reconstruction from nearby car or infrastructure by spatial-channel pooling operation in an elementwise manner. To promote the candidate alignment, a brand-new bin-based location correction (BLC) provides an auxiliary supervision for cross-dataset box refinement via residual coordinate encoding (RCE), and category-aware pooling alignment (CPA) is further designed for pulling the category-specific instance closer between source and target samples. We benchmark CUDA-X against the counterparts on four prevalent cooperative perception datasets, i.e., OPV2V, V2X-Sim, V2V4Real, and DAIR-V2X: it establishes the new state-of-the-art vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) performances regardless of simulation or reality. We expect that this appealing attempt would provide an in-depth insight into domain generalization in the context of multiagent perception, and the code is publicly available soon.

Efficiently recognizing kilometer markers in railway systems is crucial for ensuring the safety and reliability of train operations, particularly within the Industrial Internet of Things (IIoT) framework where edge devices are often resource-constrained. This paper highlights the significance of a real-time AI-driven approach to railway kilometer marker recognition. We introduce an innovative method that employs spatio-temporal slimming and multi-view fusion techniques, elevating both precision and computational efficiency for real-time analytics in IIoT. Our approach begins with the implementation of an Adaptive Region of Interest (AROI) and a spatio-temporal calibration mechanism for effective marker detection in real-time. Furthermore, a multi-view fusion method addresses challenges such as occlusion, blurriness , and low-light conditions, common in real-world industrial environments, which includes a variation-aware memory bank for constructing informative views and a fusion network. Experimental results demonstrate the effectiveness of our method in a real-world rail transportation setting, significantly enhancing the accuracy and efficiency of kilometer marker recognition, thereby contributing to the safety and operational efficiency of rail systems.

Traffic video question answering (TrafficVQA) constitutes a specialized VideoQA task designed to enhance the basic comprehension and intricate reasoning capacities of videos, specifically focusing on traffic events. Recent VideoQA models employ pretrained visual and textual encoder models to bridge the feature space gap between visual and textual data. However, in addressing the unique challenges inherent to the TrafficVQA task, three pivotal issues must be addressed: (i) Dimension Gap: Between the pretrained image (appearance feature) and video (motion feature) models, there exists a conspicuous dimension difference in static and dynamic visual data; (ii) Scene Gap: The common real-world datasets and the traffic event datasets differ in visual scene content; (iii) Modality Gap: A pronounced feature distribution discrepancy emerges between traffic video and text data. To alleviate these challenges, we introduce the coarse-fine multimodal contrastive alignment network (CFMMC-Align). This model leverages sequence-level and token-level multimodal features, grounded in an unsupervised visual multimodal contrastive loss to mitigate dimension and scene gaps and a supervised visual-textual contrastive loss to alleviate modality discrepancies. Finally, the model is validated on the challenging public TrafficVQA dataset SUTD-TrafficQA and outperforms the state-of-the-art method by a substantial margin (50.2%compared to46.0%). The code is available at https://github.com/guokan987/CFMMC-Align.

Virtual coupling is expected to primarily improve the capacity of a railway system. Virtual coupled systems are affected by multi-source disturbances due to the complex operating environment. However, existing research only partially considers the effects of structural or external disturbances, which limits the stability and robustness of the virtually coupled train set (VCTS). In this paper, we aim to tackle the challenges arising from both structural and external disturbances in virtual coupling. We specifically propose a distributed robust model predictive control (DRMPC) solution based on a linearized model by joining linear feedback and feedforward control into a model predictive control (MPC) framework with a discrete Kalman filter (DKF). We also theoretically derive and prove a set of sufficient conditions for both local and string stabilities under structural uncertainty. The stability conditions are incorporated into the constraint space of the distributed MPC framework in order to guarantee system stability in the presence of structural and external uncertainties. The simulation results validate that our proposed control method can stabilize train platooning under both structural and external disturbances. Our control method particularly reduces the spacing and velocity tracking errors by approximately 97.55% and 99.97% on average, respectively, as compared to several baselines.

Vehicular fog computing (VFC) that supports inter-vehicular task offloading emerges as a promising complement to handle the explosive growth of computation-intensive tasks in Intelligent Transportation Systems (ITS). Nonetheless, as the fog access points (F-APs) in crowed areas are often overloaded, the conventional single F-AP VFC may become incompetent and energy-inefficient. To tackle the issue, a novel scheme of non-orthogonal multiple access (NOMA)-enabled multi-F-AP VFC with partial offloading is proposed in this work. However, the corresponding energy minimization turns out to be a highly non-trivial non-linear mixed-integer programming problem. To this end, the optimal power allocation is derived by exploiting monotonicity while good task splitting ratio and user association are found through successive convex approximation (SCA)-based interior-point method and game theoretic approach, respectively. Extensive simulations based on MATLAB show that, in the considered scenarios, the proposed scheme can fulfill a more balanced offloading and better exploit the available computing resources, thereby leading to an approximately 30% energy consumption reduction compared to the baselines.

Multi-vehicle cooperative perception has recently emerged for facilitating long-range and large-scale perception ability of connected automated vehicles (CAVs). Nonetheless, enormous efforts formulate collaborative perception as LiDAR-only 3D detection paradigm, neglecting the significance and complementary of dense image. In this work, we construct the first multi-modal vehicle-to-vehicle cooperative perception framework dubbed as V2VFormer++, where individual camera-LiDAR representation is incorporated with dynamic channel fusion (DCF) at bird’s-eye-view (BEV) space and ego-centric BEV maps from adjacent vehicles are aggregated by global-local transformer module. Specifically, channel-token mixer (CTM) with MLP design is developed to capture global response among neighboring CAVs, and position-aware fusion (PAF) further investigate the spatial correlation between each ego-networked map in a local perspective. In this manner, we could strategically determine which CAVs are desirable for collaboration and how to aggregate the foremost information from them. Quantitative and qualitative experiments are conducted on both publicly-available OPV2V and V2X-Sim 2.0 benchmarks, and our proposed V2VFormer++ reports the state-of-the-art cooperative perception performance, demonstrating its effectiveness and advancement. Moreover, ablation study and visualization analysis further suggest the strong robustness against diverse disturbances from real-world scenarios.

Energy-efficiency (EE) optimization of long-term evolution (LTE) networks dedicated to vehicle-to-vehicle communications (LTE-V2V) is critical for connected vehicles. In this paper, we integrate perimeter control methodologies from transportation science into EE optimization to make vehicular communications adaptive to temporal-spatial dynamics of macroscopic traffic flows in multiple urban regions. Specifically, we develop a hierarchical framework of joint LTE-V2V EE optimization and perimeter traffic flow control. Its goal is to minimize the total traffic network delay, defined as the integral of the vehicle accumulations in the urban regions over a prediction horizon time, meanwhile maximizing the energy efficiency of the LTE-V2V communications in the same regions. We propose a model predictive perimeter controller at a low level, using a macroscopic fundamental diagram (MFD) to capture the relationship between the traffic density and the outflow of each urban region. We also propose a high-level EE optimization model and an iterative algorithm, considering the multi-region coordinated traffic dynamics, to jointly optimize vehicular transmission power and beacon frequency. Simulation results validate our proposed models and show that our method outperforms the latest solutions by improving at least 9.57% EE of the multiple regions. Our method can also provide 27.69% improvement in resource utilization fairness, indicating a fairer EE performance distribution among these regions.

Energy efficiency is a significant requirement of resource management and design optimization in information networks. In this article, we propose an iterative fractional programming framework embedded with a distributed primal-dual extra-gradient projection algorithm, which addresses a wide class of the energy-efficiency optimization problems in wireless ad hoc networks with full-duplex radios and multi-packet reception capability. Specifically, we propose a model convexification mechanism by joining an affine transformation and an exponential transformation into the nonlinear fractional programming, which enables us to deal with the challenge arising from the complexity and non-convex structure of the original problem. With the model convexification, we can map the non-convex power control space into a convex space and equivalently derive a sequence of convex subproblems, which relaxes the convexity assumption widely adopted in the existing literature. We further propose a distributed primal-dual algorithm based on extra-gradient projection to solve the convex subproblem at each iteration of the fractional programming. The convergence of the proposed iterative fractional programming and the distributed optimization method is theoretically proven. Numerical results also verify the proposed method and demonstrate its superior performance over other representative distributed and centralized schemes in terms of achieving global energy efficiency.

Aerial unmanned vehicles (UAVs) play a significant role in improving the connectivity and coverage of terrestrial communication networks. However, UAV-assisted air-to-ground (A2G) data transmissions usually encounter several fundamental challenges, such as terminal mobility, random nature in channel fading and contention, resource constraints, and application-specific transmission requirements. To tackle these challenges, we formulate a bi-level optimization problem that jointly considers the control of the UAV mobility and transmission power and the scheduling of A2G data transmissions. The objective is to optimize energy consumption and maximize A2G transmission reliability. Particularly, we first theoretically characterize the A2G transmission reliability from a probabilistic perspective concerning the effects of channel fading, channel access contention, and application requirements. We then derive a closed-form expression for the optimal expected transmission reliability. Using the closed-form reliability, we transform the bi-level optimization into a mathematically-tractable optimal control problem and propose an efficient iterative algorithm to solve it. Simulation results show that our approach provides a comprehensive improvement in terms of both energy utilization and A2G transmission reliability, in particular, with a reduction of more than 12.1% in energy consumption and an increase of 7.53% in reliability on average, compared to several baselines.

Numerous interaction demands for smart cities have arisen due to the explosive growth of the Internet of Things and mobile communication. Due to its passive low energy consumption and affordable deployment cost, reconfigurable intelligent surface (RIS) is a potential key technology to develop a novel paradigm of wireless communication at unsignalized intersections. This article studies the signal interaction between multiple vehicle platoons in different paths before entering an unsignalized intersection supported by unmanned aerial vehicle, which is usually difficult to solve without the assistance of communication. Under the limitation of calculation and transmission resources, the objective is to optimize the system’s transmission efficiency. The joint resource scheduling model of communication time and transmission power includes the coupling effects of vehicle dynamics, onboard computing, signal transmission and reflection, and energy consumption. A method based on the quasi-Newton and sequential quadratic programming (SQP) algorithm is designed to carry out optimization iteration. Finally, the simulation results show that this method is generally efficient and outperforms the benchmark methods.

Multi-vehicle motion planning (MVMP) has become an emerging paradigm in connected and automated vehicles (CAVs). The cooperative lane-change movements with the coexistence of platoons and CAVs are typical scenarios on the muti-lane roads. This paper proposes an optimal control framework with the advantages of completeness and universality for platoons and CAVs’ cooperative lane-change motion planning in different task scenarios. Two typical cooperative scenarios are designed for the subsequent study of optimal modeling. The platoons’ reconfiguration and original shape maintenance are considered to reflect the universality of moving objects and the diversity of cooperative tasks. Approximately geometric contour models, dynamic externally tangent rectangle and inflated rectangle, are utilized to describe the platoon’s profile. Analytical complete collision avoidance constraints among different motion objects are constructed effectively. Other necessary constraints and the weighted cost function that minimizes lane-change time and motion energy are comprehensively considered. The optimal control models are established for the desired scenarios. Moreover, a numerical solution method combined with the simultaneous direct collocation method based on the trapezoidal rule and the barrier function method is proposed to obtain the optimal schemes. Simulation and contrast experiments are conducted for two scenarios. The results indicate that the cost function’s weight coefficients and specific lane-change tasks influence the cooperative motion planning effects and verify that the proposed optimal control framework is of reasonability, effectiveness, and unification.

The development and applications of mobile communication technologies in intelligent autonomous transportation systems have led to an extraordinary rise in the mount of connected and autonomous vehicles (CAVs). Ensuring the security of in-vehicle communication data is the basis for the safety of cooperative transportation systems. An in-vehicle controller area network (CAN) bus is an important issue in in-vehicle security, and some hackers have mastered remote vehicle control methods through the CAN bus network. This paper proposes an improved isolation forest method with data mass (MS-iForest) for data tampering attack detection, in which we use data mass instead of the number of divisions and give an anomaly score ranking to quantify the degree of anomalies. This method is promising to be used as part of the intrusion detection system, like a security component in the onboard gateway, which can effectively avoid the data tampering attacks. We compare the proposed method with other anomaly detection schemes based on the data collected from an in-vehicle simulated dataset and two standard datasets. The experiment results show that the proposed method performs better than the other anomaly detection schemes in terms of the area under the receiver operating curve (AUC).

This paper investigates cooperative adaptive cruise control (CACC) for mixed platoons consisting of both human-driven vehicles (HVs) and automated vehicles (AVs). This research is critical because the penetration rate of AVs in the transportation system will remain unsaturated for a long time. Uncertainties and randomness are prevalent in human driving behaviours and highly affect the platoon safety and stability, which need to be considered in the CACC design. A further challenge is the difficulty to know the exact models of the HVs and the exact powertrain parameters of both AVs and HVs. To address these challenges, this paper proposes a data-driven model predictive control (MPC) that does not need the exact models of HVs or powertrain parameters. The MPC design adopts the technique of data-driven reachability to predict the future trajectory of the mixed platoon within a given horizon based on noisy vehicle measurements. Compared to the classic adaptive cruise control (ACC) and existing data-driven adaptive dynamic programming (ADP), the proposed MPC ensures satisfaction of constraints such as acceleration limit and safe inter-vehicular gap. With this salient feature, the proposed MPC has provably guarantee in establishing a safe and robustly stable mixed platoon despite of the velocity changes of the leading vehicle. The efficacy and advantage of the proposed MPC are verified through comparison with the classic ACC and data-driven ADP methods on both small and large mixed platoons.

Recent advances on road damage detection relies on a large amount of labeled data, whilst collecting pavement image is labor-intensive and time-consuming. Unsupervised Domain Adaptation (UDA) provides a promising solution to adapt a source domain to the target domain, however, cross-domain crack detection is still an open problem. In this paper, we propose domain adaptive road damage detection termed as DA-RDD, by incorporating image-level with instance-level feature alignment for domain-invariant representation learning in an adversarial manner. Specifically, importance weighting is introduced to evaluate the intermediate samples for image-level alignment between domains, and we aggregate RoI-wise feature with multi-scale contextual information to recover the crack details for progressive domain alignment at instance level. Additionally, a large-scale road damage dataset (based on Road Damage Dataset 2020 (RDD2020)) named as RDD2021 is constructed with$100k$synthetic labeled distress images. Extensive experimental results on damage detection across different countries demonstrate the universality and superiority of DA-RDD, and empirical studies on RDD2021 further claim its effectiveness and advancement. To our best knowledge, it is the first time to investigate domain adaptative pavement crack detection, and we expect the contributions in this work would facilitate the development of generalized road damage detection in the future.

Recent advances in cross-modal 3D object detection rely heavily on anchor-based methods, and however, intractable anchor parameter tuning and computationally expensive postprocessing severely impede an embedded system application, such as autonomous driving. In this work, we develop an anchor-free architecture for efficient camera-light detection and ranging (LiDAR) 3D object detection. To highlight the effect of foreground information from different modalities, we propose a dynamic fusion module (DFM) to adaptively interact images with point features via learnable filters. In addition, the 3D distance intersection-over-union (3D-DIoU) loss is explicitly formulated as a supervision signal for 3D-oriented box regression and optimization. We integrate these components into an end-to-end multimodal 3D detector termed 3D-DFM. Comprehensive experimental results on the widely used KITTI dataset demonstrate the superiority and universality of 3D-DFM architecture, with competitive detection accuracy and real-time inference speed. To the best of our knowledge, this is the first work that incorporates an anchor-free pipeline with multimodal 3D object detection.

Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits. Although a number of surveys have reviewed research achievements in this field, they are still limited in specific tasks and lack systematic summaries and research directions in the future. Our work is divided into three independent articles and the first part is a survey of surveys (SoS) for total technologies of AD and IVs that involves the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions. This is the second part (Part I for this technical survey) to review the development of control, computing system design, communication, high-definition map (HD map), testing, and human behaviors in IVs. In addition, the third part (Part II for this technical survey) is to review the perception and planning sections. The objective of this article is to involve all the sections of AD, summarize the latest technical milestones, and guide abecedarians to quickly understand the development of AD and IVs. Combining the SoS and Part II, we anticipate that this work will bring novel and diverse insights to researchers and abecedarians, and serve as a bridge between past and future.

Due to the increased complexity of new in-vehicle networking architectures, which makes direct monitoring of internal network components intractable, alternative solutions are required to tackle this issue. One solution is to leverage the end-to-end measurements to estimate the internal network performance. To this end, we propose to employ network tomography as a monitoring approach for in-vehicle networks. Network tomography can infer the overall network performance by measuring only subset of the network. We investigate the use of network tomography in in-vehicle network by analysing network identifiability of three main architectures: bus-based, central-gateway, and Ethernet-based architectures. Our analysis results indicate the applicability of network tomography in in-vehicle networks based on certain topological and monitors' conditions. Furthermore, we validate our analytical results through simulation which shows a maximum error of only$174\mu s$. Moreover, we compare the proposed approach with one of existing solutions and show that network tomography achieves better bandwidth and latency performance with monitoring overhead saving up to 52.2% and$782.3\mu s$, respectively.

Vehicular networks are vulnerable to large scale attacks. Blockchain, implemented upon application layer, is recommended as one of the effective security and privacy solutions for vehicular networks. However, due to an increasing complexity of connected nodes, heterogeneous environment and rising threats, a robust security solution across multiple layers is required. Motivated by the Physical Layer Security (PLS) which utilizes physical layer characteristics such as channel fading to ensure reliable and confidential transmission, in this paper we analyze the impact of PLS on a blockchain-enabled vehicular network with two types of physical layer attacks, i.e., jamming and eavesdropping. Throughout the analysis, a Full Duplex Non-Orthogonal Multiple Access (FD-NOMA) based vehicle-to-everything (V2X) is considered to reduce interference caused by jamming and meet 5G communication requirements. Simulation results show enhanced goodput of a blockckchain enabled vehicular network integrated with PLS as compared to the same solution without PLS.

With the rapid development of mobile computing, mobile-edge computing (MEC) has increasingly become an essential means to meet the computing power requirements of intelligent networked vehicles. However, users with high mobility and coupled dynamics are rarely considered in the edge computing paradigms. In this article, we studied a UAV-assisted MEC system with multiplatoon vehicles. Our article aims to maximize the system’s weighted global energy efficiency, which can flexibly adjust each vehicle’s energy consumption according to user preferences and system needs. In particular, we design a controller for platooning vehicles based on a 2-D path-following model and Frenet frames, and model the coupled characteristics of air-to-ground communications and onboard computation. Furthermore, due to the nonconvexity of the objective function and constraints of the optimization problem, we propose an optimization algorithm based on the sequential quadratic programming (SQP) method. The simulation results show that the proposed method significantly surpasses conventional schemes.

Autonomous vehicles were experiencing rapid development in the past few years. However, achieving full autonomy is not a trivial task, due to the nature of the complex and dynamic driving environment. Therefore, autonomous vehicles are equipped with a suite of different sensors to ensure robust, accurate environmental perception. In particular, the camera-LiDAR fusion is becoming an emerging research theme. However, so far there has been no critical review that focuses on deep-learning-based camera-LiDAR fusion methods. To bridge this gap and motivate future research, this article devotes to review recent deep-learning-based data fusion approaches that leverage both image and point cloud. This review gives a brief overview of deep learning on image and point cloud data processing. Followed by in-depth reviews of camera-LiDAR fusion methods in depth completion, object detection, semantic segmentation, tracking and online cross-sensor calibration, which are organized based on their respective fusion levels. Furthermore, we compare these methods on publicly available datasets. Finally, we identified gaps and over-looked challenges between current academic researches and real-world applications. Based on these observations, we provide our insights and point out promising research directions.

Camera-LiDAR 3D object detection has been extensively investigated due to its significance for many real-world applications. However, there are still of great challenges to address the intrinsic data difference and perform accurate feature fusion among two modalities. To these ends, we propose a two-stream architecture termed as CL3D, that integrates with point enhancement module, point-guided fusion module with IoU-aware head for cross-modal 3D object detection. Specifically, pseudo LiDAR is firstly generated from RGB image, and point enhancement module (PEM) is then designed to enhance the raw LiDAR with pseudo point. Moreover, point-guided fusion module (PFM) is developed to find image-point correspondence at different resolutions, and incorporate semantic with geometric features in a point-wise manner. We also investigate the inconsistency between localization confidence and classification score in 3D detection, and introduce IoU-aware prediction head (IoU Head) for accurate box regression. Comprehensive experiments are conducted on publicly available KITTI dataset, and CL3D reports the outstanding detection performance compared to both single- and multi-modal 3D detectors, demonstrating its effectiveness and competitiveness.

Connected and autonomous vehicles (CAVs) are recently envisioned to provide a tremendous social impact, while they put forward a much higher requirement for both vehicular communication and computation capacities to process resource-intensive applications. In this paper, we study unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) for a platoon of wireless power transmission (WPT)-enabled vehicles. Our objective is to maximize the system-wide computation capacity under both communication and computation resource constraints. We incorporate the coupled effects of the platooning vehicles and the flying UAV, air-to-ground (A2G) and ground-to-air (G2A) communications, onboard computing and energy harvesting into a joint scheduling optimization model of communication and computation resources. To tackle the resulting optimization problem, we propose a successive convex programming method based on a second-order convex approximation, in which feasible search directions are obtained by solving a sequence of quadratic programming subproblems and used to generate feasible points that can approach a local optimum. We also theoretically prove the feasibility and convergence of the proposed method. Moreover, simulation results are provided to validate the effectiveness of our proposed method and demonstrate its superior performance over other conventional schemes.

Object detection is becoming increasingly significant for autonomous-driving system. However, poor accuracy or low inference performance limits current object detectors in applying to autonomous driving. In this work, a fast and accurate object detector termed as SA-YOLOv3, is proposed by introducing dilated convolution and self-attention module (SAM) into the architecture of YOLOv3. Furthermore, loss function based on GIoU and focal loss is reconstructed to further optimize detection performance. With an input size of$512\times 512$, our proposed SA-YOLOv3 improves YOLOv3 by 2.58 mAP and 2.63 mAP on KITTI and BDD100K benchmarks, with real-time inference (more than 40 FPS). When compared with other state-of-the-art detectors, it reports better trade-off in terms of detection accuracy and speed, indicating the suitability for autonomous-driving application. To our best knowledge, it is the first method that incorporates YOLOv3 with attention mechanism, and we expect this work would guide for autonomous-driving research in the future.

Virtual coupling is a promising innovation aimed at increasing railway capacity. Compared to current railway signaling systems, it allows two or more trains to run with reduced headway between them. However, such reduced headways are a challenge to safety. In this work we consider this challenge by formally describing and verifying an approach to virtual coupling. We propose a general modeling method based on topological manifolds to describe the protection logic for virtual coupling train control systems. We also describe the basic train control elements in topological terms and analyze the line condition of our virtual coupling logic. We establish that the line condition safety requirements and its representation as a manifold are equivalent and further provide a formal definition of the concept of a movement authority with manifold notations. This allows us to consider the dynamic behavior of trains and a series of theorems that establish the correctness of our protection logic for virtual coupling. Finally, we apply the presented methods to a case study. The results show that the proposed method provides a suitable way to realize a virtual coupling logic safely.

Platoon-based vehicular cyber-physical systems have gained increasing attention due to their potentials in improving traffic efficiency, capacity, and saving energy. However, external uncertain disturbances arising from mismatched model errors, sensor noises, communication delays and unknown environments can impose a great challenge on the constrained control of vehicle platooning. In this paper, we propose a closed-loop min-max model predictive control (MPC) with causal disturbance feedback for vehicle platooning. Specifically, we first develop a compact form of a centralized vehicle platooning model subject to external disturbances, which also incorporates the lower-level vehicle dynamics. We then formulate the uncertain optimal control of the vehicle platoon as a worst-case constrained optimization problem and derive its robust counterpart by semidefinite relaxation. Thus, we design a causal disturbance feedback structure with the robust counterpart, which leads to a closed-loop min-max MPC platoon control solution. Even though the min-max MPC follows a centralized paradigm, its robust counterpart can keep the convexity and enable the efficient and practical implementation of current convex optimization techniques. We also derive a linear matrix inequality (LMI) condition for guaranteeing the recursive feasibility and input-to-state practical stability (ISpS) of the platoon system. Finally, simulation results are provided to verify the effectiveness and advantage of the proposed MPC in terms of constraint satisfaction, platoon stability and robustness against different external disturbances.

Deep learning on 3D point clouds has drawn much attention, due to its large variety of applications in intelligent perception for automated and robotic systems. Unlike structured 2D images, it is challenging to extract features and implement convolutional networks over these unordered points. Although a number of previous works achieved high accuracies for point cloud recognition, they tend to process local point information in such a way that semantic information is not fully encoded. In this paper, we propose a deep neural network for 3D point cloud processing that utilizes effective feature aggregation methods emphasizing both generalizability and relevance. In particular, our method uses fixed-radius grouping for pooling layers and spherical kernel convolution for semantics mining. To address the issue of gradient degradation and memory consumption of a deep network, a parallel feature feed-forward mechanism and bottleneck layers are implemented to reduce the number of parameters. Experiments show that our algorithm achieves state-of-the-art results and competitive accuracy in both classification and part segmentation while maintaining an efficient architecture.

In the era of the Internet of Everything, autonomous driving has put forward a higher ambition for data transmission capabilities. This paper studies joint scheduling of computation and communication resources in the collaborative networking of unmanned aerial vehicles (UAV s) and platooning vehicles in mobile edge computing (MEC) framework to maximize the energy efficiency. Considering the movement characteristics of vehicles, we integrate mobility, communication, computation, and energy consumption to establish a collective optimization problem. Since this multivariate coupled model is non-convex, we further propose a joint optimization method (JOM) algorithm based on the convex approximation theory, particularly quadratic programming. Experimental results verify that this algorithm converges quickly within a dozen iterations and proves to be superior to several other benchmark schemes.

Blockchain applications in vehicular networks can offer many advantages, including decentralization and improved security. However, most of the consensus algorithms in blockchain are difficult to be implemented in vehicular ad hoc networks (VANETs) without the help of edge computing services. For example, the connectivity in VANET only remains for a short period of time, which is not sufficient for highly time-consuming consensus algorithms, e.g., Proof of Work, running on mobile-edge nodes (vehicles). Other consensus algorithms also have some drawbacks, e.g., Proof of Stake (PoS) is biased toward nodes with a higher amount of stakes and Proof of Elapsed Time (PoET) is not highly secure against malicious nodes. For these reasons, we propose a voting blockchain based on the Proof-of-Quality-Factor (PoQF) consensus algorithm, where the threshold number of votes is controlled by edge computing servers. Specifically, PoQF includes voting for message validation and a competitive relay selection process based on the probabilistic prediction of channel quality between the transmitter and receiver. The performance bounds of failure and latency in message validation are obtained. This article also analyzes the throughput of block generation, as well as the asymptotic latency, security, and communication complexity of PoQF. An incentive distribution mechanism to reward honest nodes and punish malicious nodes is further presented and its effectiveness against the collusion of nodes is proved using the game theory. Simulation results show that PoQF reduces failure in validation by 11% and 15% as compared to PoS and PoET, respectively, and is 68 ms faster than PoET.

Task offloading decision making plays a key role in enabling mobile-edge computing (MEC) technologies in Internet of Things (IoT). However, it meets the significant challenges arising from the stochastic dynamics of task queueing in the application layer and coupled wireless interference in the physical layer in a distributed multiagent network without any centralized communication and computing coordination. In this article, we investigate the distributed task offloading optimization problem with consideration of the upper layer queueing dynamics and the lower-layer coupled wireless interference. We first propose a new optimization model that aims at maximizing the expected offloading rate of multiple agents by optimizing their offloading thresholds. Then, we transform the problem into a game-theoretic formulation, which further leads to the design of a distributed best-response (DBR) iterative optimization framework. The existence of Nash equilibrium strategies in the game-theoretic model has been analyzed. For the individual optimization of each agent's threshold policy, we further propose a programming scheme by transforming a constrained threshold optimization into an unconstrained Lagrangian optimization (ULO). The individual ULO is integrated into the DBR framework to enable agents to cooperate and converge to a global optimum in a distributed manner. Finally, simulation results are provided to validate the proposed method and demonstrate its significant advantage over other existing distributed methods. The numerical results also show that the proposed method can achieve comparable performance to a centralized optimization method.

Rule-based autonomous driving systems may suffer from increased complexity with large-scale intercoupled rules, so many researchers are exploring learning-based approaches. Reinforcement learning (RL) has been applied in designing autonomous driving systems because of its outstanding performance on a wide variety of sequential control problems. However, poor initial performance is a major challenge to the practical implementation of an RL-based autonomous driving system. RL training requires extensive training data before the model achieves reasonable performance, making an RL-based model inapplicable in a real-world setting, particularly when data are expensive. We propose an asynchronous supervised learning (ASL) method for the RL-based end-to-end autonomous driving model to address the problem of poor initial performance before training this RL-based model in real-world settings. Specifically, prior knowledge is introduced in the ASL pre-training stage by asynchronously executing multiple supervised learning processes in parallel, on multiple driving demonstration data sets. After pre-training, the model is deployed on a real vehicle to be further trained by RL to adapt to the real environment and continuously break the performance limit. The presented pre-training method is evaluated on the race car simulator, TORCS (The Open Racing Car Simulator), to verify that it can be sufficiently reliable in improving the initial performance and convergence speed of an end-to-end autonomous driving model in the RL training stage. In addition, a real-vehicle verification system is built to verify the feasibility of the proposed pre-training method in a real-vehicle deployment. Simulations results show that using some demonstrations during a supervised pre-training stage allows significant improvements in initial performance and convergence speed in the RL training stage.

As a key enabler in the green transport system, the popularity of Electric Vehicles (EV) has attracted attention from academia and industrial communities. However, the driving range of EVs is inevitably affected by the insufficient battery volume, as such EV drivers may experience trip discomfort due to a long battery charging time (under traditional plug-in charging service). One feasible alternative to accelerate the service time to feed electricity is the battery switch technology, by cycling switchable (fully-recharged) batteries at Battery Switch Stations (BSSs) to replace the depleted batteries from incoming EVs. Along with recent advance of vehicle cooperation through emerging Information Communication Technology (ICT), in this paper we propose a Mobile Edge Computing (MEC) driven architecture to gear the intelligent battery switch service management for EVs. Here, the decision making on where to switch battery is operated by EVs in a distributed manner. Besides, the Vehicle-to-Vehicle (V2V) communication in line with public transportation bus system is applied to operate flexible information exchange between EVs and BSSs. Dedicated MEC functions are positioned for bus system to efficiently disseminate BSSs status and aggregate EVs’ reservations, concerning the massive signalling exchange cost. The Global Controller (GC) is positioned as cloud server to gather BSSs (service providers) status and EVs’ reservations (clients), and predict the service availability of BSS (e.g., whether/when a battery can be switched). We conduct performance evaluation to show the advantage of MEC system in terms of reduction of communication cost, and BSS service management scheme regarding reduction of service waiting time (e.g., how long to wait for battery switch) and increase of service satisfaction rate (e.g., how many batteries to switch for EVs).

This paper comprehensively discusses the cooperative communication and computation of vehicular system. Based on the cooperative transmission, an stochastic model of vehicle-to-vehicle (V2V) communication reliability is established using probability theory. Furthermore, the computation reliability is defined as a new metric for computation offloading, and a vehicle computational performance evaluation model is also established. In order to effectively compute the required data, we combine V2V communication and vehicle computing to further characterize the coupling reliability of cooperative communications and computation systems. In addition, we propose a virtual queue model that combines queue length and vehicle privacy entropy to optimize partitioning. Finally, considering the amount of processing data and cut-off time of vehicle applications, we establish the optimal partition model of vehicle computing with the goal of maximizing the coupling reliability, and propose the coupling-oriented reliability calculation for vehicle collaboration using dynamic programming methods. Simulations show that the proposed scheme outperforms traditional approaches in terms of coupling reliability and completion rate. In addition, the allocation between local computing and data offloading is controlled by the server’s privacy perception of collaboration events.

With increasing popularity of related applications of mobile crowdsensing, especially in the field of Internet of Vehicles (IoV), task allocation has attracted wide attention. How to select appropriate participants is a key problem in vehicle-based crowdsensing networks. Some traditional methods choose participants based on minimizing distance, which requires participants to submit their current locations. In this case, participants' location privacy is violated, which influences disclosure of participants' sensitive information. Many privacy preserving task allocation mechanisms have been proposed to encourage users to participate in mobile crowdsensing. However, most of them assume that different participants' task completion quality is the same, which is not reasonable in reality. In this paper, we propose an optimal location privacy preserving and service quality guaranteed task allocation in vehicle-based crowdsensing networks. Specifically, we utilize differential privacy to preserve participants' location privacy, where every participant can submit the obfuscated location to the platform instead of the real one. Based on the obfuscated locations, we design an optimal problem to minimize the moving distance and maximize the task completion quality simultaneously. In order to solve this problem, we decompose it into two linear optimization problems. We conduct extensive experiments to demonstrate the effectiveness of our proposed mechanism.

Collaborative beamforming (CB) in wireless sensor networks (WSNs) based on a virtual node antenna array (VNAA) can increase the transmission distance and enhance the energy efficiency of sensor nodes. However, a VNAA cannot be pre-designed like the conventional antenna arrays due to the randomly deployed sensor nodes, thereby causing a high sidelobe level (SLL) which increases the interferences. In this article, we formulate a hybrid discrete and continuous optimization problem (HDCOP) for reducing the maximum SLL. HDCOP requires to solve both the discrete and the continuous problems simultaneously, and we propose both centralized and consensus-based distributed CB strategies for solving HDCOP. For the centralized strategy, we convert HDCOP into two sub-optimization problems, and propose a discrete cuckoo search (CS) algorithm for the node location selection optimization and a continuous CS algorithm to optimize the excitation current weights of the selected nodes. For the distributed strategy, we propose a parallel distributed CS algorithm to solve the discrete and continuous parts of HDCOP simultaneously. Moreover, we propose two operating mechanisms based on these two algorithms. Simulation results verify the effectiveness of the proposed strategies for reducing the maximum SLL of CB in WSNs. Moreover, the proposed CB strategies have better performance in terms of the energy efficiency compared with other approaches such as the cross-entropy optimization-based method.

Secure message dissemination is an important requirement of intelligent transportation systems (ITS). Existing solutions, such as broadcasting, are effective in flooding a message to a wider area, however, they are inherently unreliable and bandwidth inefficient. Furthermore, it is difficult to both assess the authenticity of a message and maintain the privacy of sender in a single solution. Moreover, as a practical solution, there is a need of economic modeling to incentivise vehicles for safe driving and cooperation. This paper proposes a blockchain based message dissemination approach which utilises incentive distribution and reputation management to overcome these challenges. Specifically, with the proposed voting based consensus algorithm, it can assess the authenticity of a message and select the most suitable relay node for its dissemination in a completely decentralised fashion. Meanwhile, the blockchain based integrated incentive and reputation scheme encourages the cooperation among vehicles and strengthens its ability to deliver authentic messages. The security capacity of the proposed solution is demonstrated by a game theoretic analysis. Simulation results show that the proposed approach can save average consensus time by 11% and improve success rate of authentic message dissemination by 17% with less number of hops as compared to the existing solutions.

Multiaccess edge computing (MEC) is a new paradigm to meet the requirements for low latency and high reliability of applications in vehicular networking. More computation-intensive and delay-sensitive applications can be realized through computation offloading of vehicles in vehicular MEC networks. However, the resources of a MEC server are not unlimited. Vehicles need to determine their task offloading strategies in real time under a dynamic-network environment to achieve optimal performance. In this article, we propose a multiuser noncooperative computation offloading game to adjust the offloading probability of each vehicle in vehicular MEC networks and design the payoff function considering the distance between the vehicle and MEC access point, application and communication model, and multivehicle competition for MEC resources. Moreover, we construct a distributed best response algorithm based on the computation offloading game model to maximize the utility of each vehicle and demonstrate that the strategy in this algorithm can converge to a unique and stable equilibrium under certain conditions. Furthermore, we conduct a series of experiments and comparisons with other offloading methods to analyze the effectiveness and performance of the proposed algorithms. The fast convergence and the improved performance of this algorithm are verified by numerical results.

Dynamic channel assignment (DCA) plays a key role in extending vehicular ad-hoc network capacity and mitigating congestion. However, channel assignment under vehicular direct communication scenarios faces mutual influence of large-scale nodes, the lack of centralized coordination, unknown global state information, and other challenges. To solve this problem, a multiagent reinforcement learning (RL) based cooperative DCA (RL-CDCA) mechanism is proposed. Specifically, each vehicular node can successfully learn the proper strategies of channel selection and backoff adaptation from the real-time channel state information (CSI) using two cooperative RL models. In addition, neural networks are constructed as nonlinear Q-function approximators, which facilitates the mapping of the continuously sensed input to the mixed policy output. Nodes are driven to locally share and incorporate their individual rewards such that they can optimize their policies in a distributed collaborative manner. Simulation results show that the proposed multiagent RL-CDCA can better reduce the one-hop packet delay by no less than 73.73%, improve the packet delivery ratio by no less than 12.66% on average in a highly dense situation, and improve the fairness of the global network resource allocation.

Acquiring traffic condition information is of great significance in transportation guidance, urban planning, and route recommendation. To date, traffic density data are generally acquired by road sound analysis, video data analysis, or in-vehicle network communication, which are usually financially or temporally expensive. Another way to get traffic conditions is to collect track data by crowdsourcing. However, this way lead to a greater risk of leaking users’ privacy. To avoid the risk, this article proposes a traffic density estimation model based on crowdsourcing privacy protection. First, in the acquisition process of the track data by crowdsourcing, dual servers are employed for transmission, and homomorphic encryption is carried out to encrypt the data to protect the data from being leaked during transmission. Second, sampling is implemented for randomization and anonymization to reduce the spatial continuity and temporal continuity of position data. In this way, the intermediate server cannot acquire users’ original data, and the main server cannot obtain users’ personal information. Finally, before data transmission, Laplace noising is performed on the users’ local position data to further protect the original location information. The proposed algorithm in this study realizes that only users have their original track data, and the servers involved in the work cannot infer the original track data, which ensures the real security of user privacy. The proposed algorithm was verified with the track data from the Didi Gaia Data Opening Plan. The experimental results showed that the proposed algorithm could still maintain the validity of data analysis results and the security of user data privacy after homomorphic encryption, noise addition, and sample collection, and displayed good robustness and scalability.

Cognitive radio-enabled vehicular nodes as unlicensed users can competitively and opportunistically access the radio spectrum provided by a licensed provider and simultaneously use a dedicated channel for vehicular communications. In such cognitive vehicular networks, channel access optimization plays a key role in making the most of the spectrum resources. In this paper, we present the competition among self-interest-driven vehicular nodes as an evolutionary game and study fundamental properties of the Nash equilibrium and the evolutionary stability. To deal with the inefficiency of the Nash equilibrium, we design a delayed pricing mechanism and propose a discretized replicator dynamics with this pricing mechanism. The strategy adaptation and the channel pricing can be performed in an asynchronous manner, such that vehicular users can obtain the knowledge of the channel prices prior to actually making access decisions. We prove that the Nash equilibrium of the proposed evolutionary dynamics is evolutionary stable and coincides with the social optimum. Besides, performance comparison is also carried out in different environments to demonstrate the effectiveness and advantages of our method over the distributed multi-agent reinforcement learning scheme in current literature in terms of the system convergence, stability and adaptability.

The emergence of vehicular networking enables distributed cooperative computation among nearby vehicles and infrastructures to achieve various applications that may need to handle mass data by a short deadline. In this paper, we investigate the fundamental problems of a cooperative vehicle-infrastructure system (CVIS): how does vehicular communication and networking affect the benefit gained from cooperative computation in the CVIS and what should a reliability-optimal cooperation be? We develop an analytical framework of reliability-oriented cooperative computation optimization, considering the dynamics of vehicular communication and computation. To be specific, we propose stochastic modeling of V2V and V2I communications, incorporating effects of the vehicle mobility, channel contentions, and fading, and theoretically derive the probability of successful data transmission. We also formulate and solve an execution time minimization model to obtain the success probability of application completion with the constrained computation capacity and application requirements. By combining these models, we develop constrained optimizations to maximize the coupled reliability of communication and computation by optimizing the data partitions among different cooperators. Numerical results confirm that vehicular applications with a short deadline and large processing data size can better benefit from the cooperative computation rather than non-cooperative solutions.

Computation offloading is critical for mobile applications that are sensitive to computational power, while dynamic and random nature of vehicular networks makes it challenging to guarantee the reliability of vehicular computation offloading. In this letter, we propose a reliability-oriented stochastic optimization model based on the dynamic programming for computation offloading in the presence of the deadline constraint on application execution. Specifically, a theoretical lower bound of the expected reliability of computation offloading is derived, and then an optimal data transmission scheduling mechanism is proposed to maximize the lower bound with consideration of randomness in vehicle-to-infrastructure communications. Experimental results demonstrate that our mechanism can outperform the conventional scheme and benefits vehicular computation offloading in terms of reliability performance in stochastic situations.

With energy scarcity and environmental pollution becoming increasingly serious, the accurate estimation of fuel consumption of vehicles has been important in vehicle management and transportation planning toward a sustainable green transition. Fuel consumption is calculated by fuel-level data collected from high-precision fuel-level sensors. However, in the vehicle monitor platform, there are many types of error in the data collection and transmission processes, such as the noise, interference, and collision errors that are common in the high speed and dynamic vehicle environment. In this paper, an effective method for cleaning and repairing the fuel-level data is proposed, which adopts the threshold to acquire abnormal fuel data, the time quantum to identify abnormal data, and linear interpolation based algorithm to correct data errors. Specifically, a modified Gaussian mixture model (GMM) based on the synchronous iteration method is proposed to acquire the thresholds, which uses the particle swarm optimization algorithm and the steepest descent algorithm to optimize the parameters of GMM. The experiment results based on the fuel-level data of vehicles collected over one month prove that the modified GMM is superior to GMM-expectation maximization on fuel-level data, and the proposed method is effective for cleaning and repairing outliers of fuel-level data.

Vehicular ad hoc networks (VANETs) have a potential to promote vehicular telematics and infotainment applications, where a key and challenging issue is the design of robust and efficient vehicular content transmissions to combat the lossy inter-vehicle links. In this paper, we focus on the robust optimization of content transmissions over cooperative VANETs. We first derive a stochastic model for estimation of time-varying inter-vehicle distance, which is dependent of the vehicle real-time kinematics and the distribution of the initial space headway. With this model, we analytically formulate the transient inter-vehicle connectivity assuming Nakagami fading channels for the physical (PHY) layer. We also model the contention nature of the medium access control (MAC) layer, on which we are based to evaluate the throughput achieved by each vehicle equipped with dedicated short-range communication (DSRC). Combining these models, we derive a closed-formed expression for the upper bound of the probability of failure in intact-content transmissions. Based upon this theoretical bound, we develop a robust optimization model for assigning content data traffic among different cooperative transmission paths, where the objective is to minimize the maximum likelihood of unsuccessful content transmissions over the cooperative VANET. We mathematically transform the optimization model to another equivalent form, such that it can be practically deployed. Finally, we validate our theoretical development with extensive simulations. Numerical results are also provided to confirm the power of cooperation in boosting the VANET performance as well as demonstrate the advantage of the proposed robust optimization in terms of content data reception reliability.

As a new type of low power wide area (LPWA) technology, the narrowband Internet of Things (NB-IoT) technology supports wide coverage and low bitrate services, thus it has a great potential to be the future commercial technology of LPWA network. Therefore, it has attracted attention of both academia and industry. In this paper, we present the NB-IoT development, and main characteristics and design objectives of NB-IoT according to 3GPP R13. In addition, we provide the review of related literatures about NB-IoT modeling and algorithm analysis. And we explain current problems of NB-IoT system-level modeling based on visualized simulation platform. Moreover, this paper is devoted to the construction of the NB-IoT model based on OPNET and the verification of its characteristics, such as wide coverage and high channel utilization. This paper mainly considers NB-IoT model design and realization in terms of NB-IoT physical layer characteristics. We summarize the correlated characteristics of NB-IoT uplink and downlink. Then we design and construct the NB-IoT model based on Long Term Evolution (LTE) network. Lastly, we use the constructed NB-IoT model for simulations and conduct an experiment on it using the LTE network with channel bandwidths of 3 MHz, 5 MHz, 10 MHz, 15 MHz, and 20 MHz. The simulation results have verified the performance of NB-IoT, wherein uplink time delay is lower than 10 s, channel utilization is higher than that of LTE network, and coverage area is larger than LTE network.

Vehicular ad hoc networks (VANETs) can help reduce traffic accidents through broadcasting emergency messages among vehicles in advance. However, it is a great challenge to timely deliver the emergency messages to the right vehicles which are interested in them. Some protocols require to collect nearby real-time information before broadcasting a message, which may result in an increased delivery latency. In this paper, we proposed an improved position-based protocol to disseminate emergency messages among a large scale vehicle networks. Specifically, defined by the proposed protocol, messages are only broadcasted along their regions of interest, and a rebroadcast of a message depends on the information including in the message it has received. The simulation results demonstrate that the proposed protocol can reduce unnecessary rebroadcasts considerably, and the collisions of broadcast can be effectively mitigated.

We present a bio-inspired unicast routing protocol for vehicular ad hoc networks which uses the cellular attractor selection mechanism to select next hops. The proposed unicast routing protocol based on attractor selecting (URAS) is an opportunistic routing protocol, which is able to change itself adaptively to the complex and dynamic environment by routing feedback packets. We further employ a multiattribute decision-making strategy, the technique for order preference by similarity to an ideal solution, to reduce the number of redundant candidates for next-hop selection, so as to enhance the performance of attractor selection mechanism. Once the routing path is found, URAS maintains the current path or finds another better path adaptively based on the performance of current path, that is, it can self-evolution until the best routing path is found. Our simulation study compares the proposed solution with the stateof-the-art schemes, and shows the robustness and effectiveness of the proposed routing protocol and the significant performance improvement, in terms of packet delivery, end-to-end delay, and congestion, over the conventional method.

The increasing complexity of automotive electronics has put considerable pressure on automotive communication networking to accommodate in-vehicle information flows. The use of power lines has been a promising alternative to in- vehicle communications because of elimination of extra data cables. In this paper, we focus on the latest HomePlug Green PHY (HPGP) which has been promoted by major automotive manufacturers for green communications with electric vehicles, and study its worst-case access delay performance in supporting Delay-critical in-vehicle applications using both theoretical analysis and the simulation. Specifically, we apply Network Calculas as a deterministic modeling approach to evaluate the worst delay and further verify its performance using the OMNeT++ simulation. Evaluation results are also supplemented to compare with legacy methods and provide useful guidelines for developing HPGP based vehicular power line communication systems.

Many vehicular ad hoc applications rely on vehicular broadcasting-based multi-hop routing to disseminate messages. In this work, we study the question of vehicular broadcasting-based routing. In particular, by modelling the vehicular message dissemination with a limited-time epidemic dynamics, we propose an online self-adaptive beaconing method to dynamically learn the optimal beaconing policy for vehicular broadcasting with consideration of varying opportunistic contacts between vehicles. The vehicular broadcasting incorporated within the proposed method can ensure message delivery with low dissemination delay and routing cost. Both theoretical analysis and simulation results are provided to exhibit the robustness and effectiveness of the proposed solution and the significantly performance with respect to the conventional solution.

In this paper, we study the problem of distributed information estimation that is closely relevant to some network-based applications, such as distributed surveillance, cooperative localization, and optimization. We consider a problem where an application area containing multiple information sources of interest is divided into a series of subregions in which only one information source exists. The information is presented as a signal variable, which has finite states associated with certain probabilities. The probability distribution of information states of all the subregions constitutes a global information picture for the whole area. Agents with limited measurement and communication ranges are assumed to monitor the area, and cooperatively create a local estimate of the global information. To efficiently approximate the actual global information using individual agents' own estimates, we propose an adaptive distributed information fusion strategy and use it to enhance the local Bayesian rule-based updating procedure. Specifically, this adaptive fusion strategy is induced by iteratively minimizing a Jensen-Shannon divergence-based objective function. A constrained optimization model is also presented to derive minimum Jensen-Shannon divergence weights at each agent for fusing local neighbors' individual estimates. Theoretical analysis and numerical results are supplemented to show the convergence performance and effectiveness of the proposed solution.

In this paper, we consider the problem of vehicular positioning enhancement with emerging connected vehicles (CV) technologies. In order to actually describe the scenario, the Interacting Multiple Model (IMM) filter is used for depicting varies of observation models. A CV-enhanced IMM filtering approach is proposed to locate a vehicle by data fusion from both coarse GPS data and the Doppler frequency shifts (DFS) measured from dedicated short-range communications (DSRC) radio signals. Simulation results state the effectiveness of the proposed approach.

With the increasing demands for vehicle-to-vehicle and vehicle-to-infrastructure communications in intelligent transportation systems, new generation of vehicular telematics inevitably depends on the cooperation of heterogeneous wireless networks. In heterogeneous vehicular telematics, the network selection is an important step to the realization of multimode communications that use multiple access technologies and multiple radios in a collaborative manner. This paper presents an innovative network selection solution for the fundamental technological requirement of multimode communications in heterogeneous vehicular telematics. To guarantee the QoS satisfaction of multiple mobile users and the efficient utilization and fair allocation of heterogeneous network resources in a global sense, a dynamic and self-adaptive method for network selection is proposed. It is biologically inspired by the cellular gene network, which enables terminals to dynamically select an appropriate access network according to the variety of QoS requirements and to the dynamic conditions of various available networks. The experimental results prove the effectiveness of the bioinspired scheme and confirm that the proposed network selection method provides better global performance when compared with the utility function method with greedy optimization.

Abstract High mobility of nodes in vehicular ad hoc networks (VANETs) may lead to frequent breakdowns of established routes in conventional routing algorithms commonly used in mobile ad hoc networks. To satisfy the high reliability and low delivery‐latency requirements for safety applications in VANETs, broadcasting becomes an essential operation for route establishment and repair. However, high node mobility causes constantly changing traffic and topology, which creates great challenges for broadcasting. Therefore, there is much interest in better understanding the properties of broadcasting in VANETs. In this paper we perform stochastic analysis of broadcasting delays in VANETs under three typical scenarios: freeway, sparse traffic and dense traffic, and utilize them to analyze the broadcasting delays in these scenarios. In the freeway scenario, the analytical equation of the expected delay in one connected group is given based on statistical analysis of real traffic data collected on freeways. In the sparse traffic scenario, the broadcasting delay in an n‐vehicle network is calculated by a finite Markov chain. In the dense traffic scenario, the collision problem is analyzed by different radio propagation models. The correctness of these theoretical analyses is confirmed by simulations. These results are useful to provide theoretical insights into the broadcasting delays in VANETs. Copyright © 2010 John Wiley & Sons, Ltd.

Abstract Modeling network traffic has been a critical task in the development of Internet. Attacks and defense are prevalent in the current Internet. Traditional network models such as Poisson‐related models do not consider the competition behaviors between the attack and defense parties. In this paper, we present a microscopic competition model to analyze the dynamics among the nodes, benign or malicious, connected to a router, which compete for the bandwidth. The dynamics analysis demonstrates that the model can well describe the competition behavior among normal users and attackers. Based on this model, an anomaly attack detection method is presented. The method is based on the adaptive resonance theory, which is used to learn the model by normal traffic data. The evaluation shows that it can effectively detect the network attacks. Copyright © 2009 John Wiley & Sons, Ltd.

Routing of data packets in vehicular ad hoc networks (VANETs) is challenging due to dynamic changes in the network topologies. As nodes in VANETs can obtain accurate position information from onboard Global Positioning System receivers, position-based routing is considered to be a very promising routing strategy for VANETs. This paper presents a novel position-based directional vehicular routing (PDVR) method. To make sure the packets can be sent to the destination in an efficient and stable route, PDVR selects the next-hop from vehicles traveling in the same direction as the forwarding vehicle based on their angular directions relative to the destination. We analyze the straight and the curve highway scenarios, and present the realizing algorithm based on position and velocity vectors. The method is evaluated using NS2 and compared with typical ad hoc routing protocol ad hoc on-demand distance vector (AODV), the position-based routing protocol distance routing effect algorithm for mobility (DREAM), and VANETs routing based on the Cartesian space method. Simulation results show that PDVR can find and maintain more stable routes compared with the other routing protocols.