Vehicle Edge Computing(VEC)and Cloud Computing(CC)significantly enhance the processing efficiency of delay-sensitive and computation-intensive applications by offloading compute-intensive tasks from resource-constrain...Vehicle Edge Computing(VEC)and Cloud Computing(CC)significantly enhance the processing efficiency of delay-sensitive and computation-intensive applications by offloading compute-intensive tasks from resource-constrained onboard devices to nearby Roadside Unit(RSU),thereby achieving lower delay and energy consumption.However,due to the limited storage capacity and energy budget of RSUs,it is challenging to meet the demands of the highly dynamic Internet of Vehicles(IoV)environment.Therefore,determining reasonable service caching and computation offloading strategies is crucial.To address this,this paper proposes a joint service caching scheme for cloud-edge collaborative IoV computation offloading.By modeling the dynamic optimization problem using Markov Decision Processes(MDP),the scheme jointly optimizes task delay,energy consumption,load balancing,and privacy entropy to achieve better quality of service.Additionally,a dynamic adaptive multi-objective deep reinforcement learning algorithm is proposed.Each Double Deep Q-Network(DDQN)agent obtains rewards for different objectives based on distinct reward functions and dynamically updates the objective weights by learning the value changes between objectives using Radial Basis Function Networks(RBFN),thereby efficiently approximating the Pareto-optimal decisions for multiple objectives.Extensive experiments demonstrate that the proposed algorithm can better coordinate the three-tier computing resources of cloud,edge,and vehicles.Compared to existing algorithms,the proposed method reduces task delay and energy consumption by 10.64%and 5.1%,respectively.展开更多
Traffic at urban intersections frequently encounters unexpected obstructions,resulting in congestion due to uncooperative and priority-based driving behavior.This paper presents an optimal right-turn coordination syst...Traffic at urban intersections frequently encounters unexpected obstructions,resulting in congestion due to uncooperative and priority-based driving behavior.This paper presents an optimal right-turn coordination system for Connected and Automated Vehicles(CAVs)at single-lane intersections,particularly in the context of left-hand side driving on roads.The goal is to facilitate smooth right turns for certain vehicles without creating bottlenecks.We consider that all approaching vehicles share relevant information through vehicular communications.The Intersection Coordination Unit(ICU)processes this information and communicates the optimal crossing or turning times to the vehicles.The primary objective of this coordination is to minimize overall traffic delays,which also helps improve the fuel consumption of vehicles.By considering information from upcoming vehicles at the intersection,the coordination system solves an optimization problem to determine the best timing for executing right turns,ultimately minimizing the total delay for all vehicles.The proposed coordination system is evaluated at a typical urban intersection,and its performance is compared to traditional traffic systems.Numerical simulation results indicate that the proposed coordination system significantly enhances the average traffic speed and fuel consumption compared to the traditional traffic system in various scenarios.展开更多
Rapidly-exploring Random Tree(RRT)and its variants have become foundational in path-planning research,yet in complex three-dimensional off-road environments their uniform blind sampling and limited safety guarantees l...Rapidly-exploring Random Tree(RRT)and its variants have become foundational in path-planning research,yet in complex three-dimensional off-road environments their uniform blind sampling and limited safety guarantees lead to slow convergence and force an unfavorable trade-off between path quality and traversal safety.To address these challenges,we introduce HS-APF-RRT*,a novel algorithm that fuses layered sampling,an enhanced Artificial Potential Field(APF),and a dynamic neighborhood-expansion mechanism.First,the workspace is hierarchically partitioned into macro,meso,and micro sampling layers,progressively biasing random samples toward safer,lower-energy regions.Second,we augment the traditional APF by incorporating a slope-dependent repulsive term,enabling stronger avoidance of steep obstacles.Third,a dynamic expansion strategy adaptively switches between 8 and 16 connected neighborhoods based on local obstacle density,striking an effective balance between search efficiency and collision-avoidance precision.In simulated off-road scenarios,HS-APF-RRT*is benchmarked against RRT*,GoalBiased RRT*,and APF-RRT*,and demonstrates significantly faster convergence,lower path-energy consumption,and enhanced safety margins.展开更多
Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instabili...Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instability,occur frequently in both experimental and operational data.This infrequency causes events to be overlooked by existing prediction models,which lack the precision to accurately predict inclination attitudes in amphibious vehicles.To address this gap in predicting attitudes near extreme inclination points,this study introduces a novel loss function,termed generalized extreme value loss.Subsequently,a deep learning model for improved waterborne attitude prediction,termed iInformer,was developed using a Transformer-based approach.During the embedding phase,a text prototype is created based on the vehicle’s operation log data is constructed to help the model better understand the vehicle’s operating environment.Data segmentation techniques are used to highlight local data variation features.Furthermore,to mitigate issues related to poor convergence and slow training speeds caused by the extreme value loss function,a teacher forcing mechanism is integrated into the model,enhancing its convergence capabilities.Experimental results validate the effectiveness of the proposed method,demonstrating its ability to handle data imbalance challenges.Specifically,the model achieves over a 60%improvement in root mean square error under extreme value conditions,with significant improvements observed across additional metrics.展开更多
Flapping-Wing Micro Air Vehicles(FMAVs)are compact and agile,capable of accessing narrow spaces that conventional vehicles struggle to reach,such as ruins,caves,or the interiors of complex structures,making them ideal...Flapping-Wing Micro Air Vehicles(FMAVs)are compact and agile,capable of accessing narrow spaces that conventional vehicles struggle to reach,such as ruins,caves,or the interiors of complex structures,making them ideal tools for reconnaissance and rescue missions.1 However,the operation of FMAVs relies on coordinating multiple forces with different scaling effects,posing challenges to miniaturization design.展开更多
Dear Editor,This letter considers the problem of achieving optimal formation control in multiple vertical take-off and landing(VTOL)unmanned aerial vehicles(UAVs).Specifically,the objective is to derive the vehicles t...Dear Editor,This letter considers the problem of achieving optimal formation control in multiple vertical take-off and landing(VTOL)unmanned aerial vehicles(UAVs).Specifically,the objective is to derive the vehicles to the desired formation shape while minimizing the total cost function.Leveraging the backstepping design,a distributed control strategy is proposed that incorporates a dynamic system for generating a reference trajectory and a trajectory tracking controller for each vehicle.展开更多
The usage of electric vehicles holds a crucial role in lowering the diminishing of the ozone layer because electric vehicles are not dependent on fossil fuels.With more research,evaluation,and its characteristics on e...The usage of electric vehicles holds a crucial role in lowering the diminishing of the ozone layer because electric vehicles are not dependent on fossil fuels.With more research,evaluation,and its characteristics on electric vehicles,the infrastructure of charging points,production of electric vehicles,and network modelling,this paper provides a comprehensive overview of electric vehicles,and hybrid vehicles,including an analysis of their market growth,as well as different types of optimization used in the current scenario.In developing countries like India,the biggest barrier is their unfulfilled facility over the charging.Without renewable energy sources,vehicle-to-grid technology facilitates the enhancement of additional power requirements.The mobility factor has been considered an important and special characteristic of electric vehicles.展开更多
Studying the coupling coordination development of new energy vehicles(NEVs)and the ecological environment in China is helpful in promoting the development of NEVs in the country and is of great significance in promoti...Studying the coupling coordination development of new energy vehicles(NEVs)and the ecological environment in China is helpful in promoting the development of NEVs in the country and is of great significance in promoting high-quality development of new energy in China.This paper constructs an evaluation index system for the development of NEVs and the ecological environment.It uses game theory combining weighting model,particle swarm optimized projection tracking evaluation model,coupling coordination degree model,and machine learning algorithms to calculate and analyze the level of coupling coordination development of NEVs and the ecological environment in China from 2010 to 2021,and identifies the driving factors.The research results show that:(i)From 2010 to 2021,the development index of NEVs in China has steadily increased from 0.085 to 0.634,while the ecological environment level index significantly rose from 0.170 to 0.884,reflecting the continuous development of China in both NEVs and the ecological environment.(ii)From 2010 to 2012,the two systems—new energy vehicle(NEV)development and the ecological environment—were in a period of imbalance and decline.From 2013 to 2016,they underwent a transition period,and from 2017 to 2021,they entered a period of coordinated development showing a trend of benign and continuous improvement.By 2021,they reached a good level of coordination.(iii)Indicators such as the number of patents granted for NEVs,water consumption per unit of GDP,and energy consumption per unit of GDP are the main driving factors affecting the coupling coordination development of NEVs and the ecological environment in China.展开更多
Considering the uncertainty of grid connection of electric vehicle charging stations and the uncertainty of new energy and residential electricity load,a spatio-temporal decoupling strategy of dynamic reactive power o...Considering the uncertainty of grid connection of electric vehicle charging stations and the uncertainty of new energy and residential electricity load,a spatio-temporal decoupling strategy of dynamic reactive power optimization based on clustering-local relaxation-correction is proposed.Firstly,the k-medoids clustering algorithm is used to divide the reduced power scene into periods.Then,the discrete variables and continuous variables are optimized in the same period of time.Finally,the number of input groups of parallel capacitor banks(CB)in multiple periods is fixed,and then the secondary static reactive power optimization correction is carried out by using the continuous reactive power output device based on the static reactive power compensation device(SVC),the new energy grid-connected inverter,and the electric vehicle charging station.According to the characteristics of the model,a hybrid optimization algorithm with a cross-feedback mechanism is used to solve different types of variables,and an improved artificial hummingbird algorithm based on tent chaotic mapping and adaptive mutation is proposed to improve the solution efficiency.The simulation results show that the proposed decoupling strategy can obtain satisfactory optimization resultswhile strictly guaranteeing the dynamic constraints of discrete variables,and the hybrid algorithm can effectively solve the mixed integer nonlinear optimization problem.展开更多
Utilizing artificial intelligence(AI)to protect smart coastal cities has become a novel vision for scientific and industrial institutions.One of these AI technologies is using efficient and secure multi-environment Un...Utilizing artificial intelligence(AI)to protect smart coastal cities has become a novel vision for scientific and industrial institutions.One of these AI technologies is using efficient and secure multi-environment Unmanned Vehicles(UVs)for anti-submarine attacks.This study’s contribution is the early detection of a submarine assault employing hybrid environment UVs that are controlled using swarm optimization and secure the information in between UVs using a decentralized cybersecurity strategy.The Dragonfly Algorithm is used for the orientation and clustering of the UVs in the optimization approach,and the Re-fragmentation strategy is used in the Network layer of the TCP/IP protocol as a cybersecurity solution.The research’s noteworthy findings demonstrate UVs’logistical capability to promptly detect the target and address the problem while securely keeping the drone’s geographical information.The results suggest that detecting the submarine early increases the likelihood of averting a collision.The dragonfly strategy of sensing the position of the submersible and aggregating around it demonstrates the reliability of swarm intelligence in increasing access efficiency.Securing communication between Unmanned Aerial Vehicles(UAVs)improves the level of secrecy necessary for the task.The swarm navigation is based on a peer-to-peer system,which allows each UAV to access information from its peers.This,in turn,helps the UAVs to determine the best route to take and to avoid collisions with other UAVs.The dragonfly strategy also increases the speed of the mission by minimizing the time spent finding the target.展开更多
In Internet of Vehicles,VehicleInfrastructure-Cloud cooperation supports diverse intelligent driving and intelligent transportation applications.Federated Learning(FL)is the emerging computation paradigm to provide ef...In Internet of Vehicles,VehicleInfrastructure-Cloud cooperation supports diverse intelligent driving and intelligent transportation applications.Federated Learning(FL)is the emerging computation paradigm to provide efficient and privacypreserving collaborative learning.However,in Io V environment,federated learning faces the challenges introduced by high mobility of vehicles and nonIndependently Identically Distribution(non-IID)of data.High mobility causes FL clients quit and the communication offline.The non-IID data leads to slow and unstable convergence of global model and single global model's weak adaptability to clients with different localization characteristics.Accordingly,this paper proposes a personalized aggregation strategy for hierarchical Federated Learning in Io V environment,including Fed SA(Special Asynchronous Federated Learning with Self-adaptive Aggregation)for low-level FL between a Road Side Unit(RSU)and the vehicles within its coverage,and Fed Att(Federated Learning with Attention Mechanism)for high-level FL between a cloud server and multiple RSUs.Agents self-adaptively obtain model aggregation weight based on Advantage Actor-Critic(A2C)algorithm.Experiments show the proposed strategy encourages vehicles to participate in global aggregation,and outperforms existing methods in training performance.展开更多
In March 2025,prominent Chinese automaker NIO(Shanghai,China),the global leader in electric vehicle(EV)battery swapping,and Contemporary Amperex Technology Co.,Ltd.(CATL)(Nindge,China),the world’s biggest manufacture...In March 2025,prominent Chinese automaker NIO(Shanghai,China),the global leader in electric vehicle(EV)battery swapping,and Contemporary Amperex Technology Co.,Ltd.(CATL)(Nindge,China),the world’s biggest manufacturer of EV batteries,announced a strategic partnership to build the world’s largest battery swapping network,while also promoting unified standards and technologies[1].Just weeks later,CATL announced another partnership,this one with Chinese state-owned oil giant Sinopec(Beijing,China)to build 10000 new battery swapping stations in China,at least 500 in 2025[2].展开更多
Complex road conditions without signalized intersections when the traffic flow is nearly saturated result in high traffic congestion and accidents,reducing the traffic efficiency of intelligent vehicles.The complex ro...Complex road conditions without signalized intersections when the traffic flow is nearly saturated result in high traffic congestion and accidents,reducing the traffic efficiency of intelligent vehicles.The complex road traffic environment of smart vehicles and other vehicles frequently experiences conflicting start and stop motion.The fine-grained scheduling of autonomous vehicles(AVs)at non-signalized intersections,which is a promising technique for exploring optimal driving paths for both assisted driving nowadays and driverless cars in the near future,has attracted significant attention owing to its high potential for improving road safety and traffic efficiency.Fine-grained scheduling primarily focuses on signalized intersection scenarios,as applying it directly to non-signalized intersections is challenging because each AV can move freely without traffic signal control.This may cause frequent driving collisions and low road traffic efficiency.Therefore,this study proposes a novel algorithm to address this issue.Our work focuses on the fine-grained scheduling of automated vehicles at non-signal intersections via dual reinforced training(FS-DRL).For FS-DRL,we first use a grid to describe the non-signalized intersection and propose a convolutional neural network(CNN)-based fast decision model that can rapidly yield a coarse-grained scheduling decision for each AV in a distributed manner.We then load these coarse-grained scheduling decisions onto a deep Q-learning network(DQN)for further evaluation.We use an adaptive learning rate to maximize the reward function and employ parameterεto tradeoff the fast speed of coarse-grained scheduling in the CNN and optimal fine-grained scheduling in the DQN.In addition,we prove that using this adaptive learning rate leads to a converged loss rate with an extremely small number of training loops.The simulation results show that compared with Dijkstra,RNN,and ant colony-based scheduling,FS-DRL yields a high accuracy of 96.5%on the sample,with improved performance of approximately 61.54%-85.37%in terms of the average conflict and traffic efficiency.展开更多
As an essential element of intelligent trans-port systems,Internet of vehicles(IoV)has brought an immersive user experience recently.Meanwhile,the emergence of mobile edge computing(MEC)has enhanced the computational ...As an essential element of intelligent trans-port systems,Internet of vehicles(IoV)has brought an immersive user experience recently.Meanwhile,the emergence of mobile edge computing(MEC)has enhanced the computational capability of the vehicle which reduces task processing latency and power con-sumption effectively and meets the quality of service requirements of vehicle users.However,there are still some problems in the MEC-assisted IoV system such as poor connectivity and high cost.Unmanned aerial vehicles(UAVs)equipped with MEC servers have become a promising approach for providing com-munication and computing services to mobile vehi-cles.Hence,in this article,an optimal framework for the UAV-assisted MEC system for IoV to minimize the average system cost is presented.Through joint consideration of computational offloading decisions and computational resource allocation,the optimiza-tion problem of our proposed architecture is presented to reduce system energy consumption and delay.For purpose of tackling this issue,the original non-convex issue is converted into a convex issue and the alternat-ing direction method of multipliers-based distributed optimal scheme is developed.The simulation results illustrate that the presented scheme can enhance the system performance dramatically with regard to other schemes,and the convergence of the proposed scheme is also significant.展开更多
Unmanned Aerial Vehicles(UAVs)are increasingly recognized for their pivotal role in military and civilian applications,serving as essential technology for transmitting,evaluating,and gathering information.Unfortunatel...Unmanned Aerial Vehicles(UAVs)are increasingly recognized for their pivotal role in military and civilian applications,serving as essential technology for transmitting,evaluating,and gathering information.Unfortunately,this crucial process often occurs through unsecured wireless connections,exposing it to numerous cyber-physical attacks.Furthermore,UAVs’limited onboard computing resources make it challenging to perform complex cryptographic operations.The main aim of constructing a cryptographic scheme is to provide substantial security while reducing the computation and communication costs.This article introduces an efficient and secure cross-domain Authenticated Key Agreement(AKA)scheme that uses Hyperelliptic Curve Cryptography(HECC).The HECC,a modified version of ECC with a smaller key size of 80 bits,is well-suited for use in UAVs.In addition,the proposed scheme is employed in a cross-domain environment that integrates a Public Key Infrastructure(PKI)at the receiving end and a Certificateless Cryptosystem(CLC)at the sending end.Integrating CLC with PKI improves network security by restricting the exposure of encryption keys only to the message’s sender and subsequent receiver.A security study employing ROM and ROR models,together with a comparative performance analysis,shows that the proposed scheme outperforms comparable existing schemes in terms of both efficiency and security.展开更多
An effective energy management strategy(EMS)is essential to optimize the energy efficiency of electric vehicles(EVs).With the advent of advanced machine learning techniques,the focus on developing sophisticated EMS fo...An effective energy management strategy(EMS)is essential to optimize the energy efficiency of electric vehicles(EVs).With the advent of advanced machine learning techniques,the focus on developing sophisticated EMS for EVs is increasing.Here,we introduce LearningEMS:a unified framework and open-source benchmark designed to facilitate rapid development and assessment of EMS.LearningEMS is distinguished by its ability to support a variety of EV configurations,including hybrid EVs,fuel cell EVs,and plug-in EVs,offering a general platform for the development of EMS.The framework enables detailed comparisons of several EMS algorithms,encompassing imitation learning,deep reinforcement learning(RL),offline RL,model predictive control,and dynamic programming.We rigorously evaluated these algorithms across multiple perspectives:energy efficiency,consistency,adaptability,and practicability.Furthermore,we discuss state,reward,and action settings for RL in EV energy management,introduce a policy extraction and reconstruction method for learning-based EMS deployment,and conduct hardware-in-the-loop experiments.In summary,we offer a unified and comprehensive framework that comes with three distinct EV platforms,over 10000 km of EMS policy data set,ten state-of-the-art algorithms,and over 160 benchmark tasks,along with three learning libraries.Its flexible design allows easy expansion for additional tasks and applications.The open-source algorithms,models,data sets,and deployment processes foster additional research and innovation in EV and broader engineering domains.展开更多
New energy vehicles are distinguished by their environmentally friendly characteristics;however,their sales remain low compared with those of fossil fuel vehicles.This study identifies the key factors influencing cons...New energy vehicles are distinguished by their environmentally friendly characteristics;however,their sales remain low compared with those of fossil fuel vehicles.This study identifies the key factors influencing consumer purchases of new energy vehicles with the aim of increasing sales and promoting the development of the new energy vehicle industry.Machine learning(ML)techniques were employed to analyze more than 26000 consumer reviews of new energy vehicles and identify the factors influencing their purchasing decisions.Subsequently,a hybrid simulation model was constructed using the complex adaptive system framework.The model combines the strengths of ML,multi-agent modeling,and system dynamics modeling,thereby enhancing its capacity to identify key factors.The model comprises two categories of manufacturers:producers of new energy vehicles and producers of fossil fuel vehicles.Dynamic simulations were conducted using the AnyLogic simulation platform.The findings indicated a negative correlation between consumer income and demand for new energy vehicles.Conversely,expansions in the interior space of new energy vehicles and favorable consumer perceptions of their environmental benefits have contributed to increased demand for these vehicles.Therefore,rather than exclusively focusing on price advantages,it would be more beneficial to prioritize expanding new energy vehicles’interior space and disseminating information about their environmental benefits to consumers.It seems reasonable to posit that these strategies would increase consumer willingness to purchase new energy vehicles in the long term.展开更多
The high cost and low efficiency of full-scale vehicle experiments and numerical simulations limit the efficient development of armored vehicle occupant protection systems.The floor-occupant-seat local simulation mode...The high cost and low efficiency of full-scale vehicle experiments and numerical simulations limit the efficient development of armored vehicle occupant protection systems.The floor-occupant-seat local simulation model provides an alternative solution for quickly evaluating the performance of occupant protection systems.However,the error and rationality of the loading of the thin-walled floor in the local model cannot be ignored.This study proposed an equivalent loading method for the local model,which includes two parts:the dimensionality reduction method for acceleration matrix and the joint optimization framework for equivalent node coordinates.In the dimensionality reduction method,the dimension of the acceleration matrix was reduced based on the improved kernel principal component analysis(KPCA),and a dynamic variable bandwidth was introduced to address the limitation of failing to effectively measure the similarity between acceleration data in conventional KPCA.In addition,a least squares problem with forced displacement constraints was constructed to solve the correction matrix,thereby achieving the scale restoration process of the principal component acceleration matrix.The joint optimization framework for coordinates consists of the error assessment of response time histories(EARTH)and Bayesian optimization.In this framework,the local loading error of the equivalent acceleration matrix is taken as the Bayesian optimization objective,which is quantified and scored by EARTH.The expected improvement acquisition function was used to select the new set of the equivalent acceleration node coordinates for the self-updating optimization of the observation dataset and Gaussian process surrogate model.We reduced the dimension of the acceleration matrix from 2256 to 7,while retaining 91%of the information features.The comprehensive error score of occupant's lower limb response in the local model increased from 58.5%to 80.4%.The proposed equivalent loading method provides a solution for the rapid and reliable development of occupant protection systems.展开更多
Reinforcement learning(RL)has been widely studied as an efficient class of machine learning methods for adaptive optimal control under uncertainties.In recent years,the applications of RL in optimised decision-making ...Reinforcement learning(RL)has been widely studied as an efficient class of machine learning methods for adaptive optimal control under uncertainties.In recent years,the applications of RL in optimised decision-making and motion control of intelligent vehicles have received increasing attention.Due to the complex and dynamic operating environments of intelligent vehicles,it is necessary to improve the learning efficiency and generalisation ability of RL-based decision and control algorithms under different conditions.This survey systematically examines the theoretical foundations,algorithmic advancements and practical challenges of applying RL to intelligent vehicle systems operating in complex and dynamic environments.The major algorithm frameworks of RL are first introduced,and the recent advances in RL-based decision-making and control of intelligent vehicles are overviewed.In addition to self-learning decision and control approaches using state measurements,the developments of DRL methods for end-to-end driving control of intelligent vehicles are summarised.The open problems and directions for further research works are also discussed.展开更多
Small-drone technology has opened a range of new applications for aerial transportation. These drones leverage the Internet of Things (IoT) to offer cross-location services for navigation. However, they are susceptibl...Small-drone technology has opened a range of new applications for aerial transportation. These drones leverage the Internet of Things (IoT) to offer cross-location services for navigation. However, they are susceptible to security and privacy threats due to hardware and architectural issues. Although small drones hold promise for expansion in both civil and defense sectors, they have safety, security, and privacy threats. Addressing these challenges is crucial to maintaining the security and uninterrupted operations of these drones. In this regard, this study investigates security, and preservation concerning both the drones and Internet of Drones (IoD), emphasizing the significance of creating drone networks that are secure and can robustly withstand interceptions and intrusions. The proposed framework incorporates a weighted voting ensemble model comprising three convolutional neural network (CNN) models to enhance intrusion detection within the network. The employed CNNs are customized 1D models optimized to obtain better performance. The output from these CNNs is voted using a weighted criterion using a 0.4, 0.3, and 0.3 ratio for three CNNs, respectively. Experiments involve using multiple benchmark datasets, achieving an impressive accuracy of up to 99.89% on drone data. The proposed model shows promising results concerning precision, recall, and F1 as indicated by their obtained values of 99.92%, 99.98%, and 99.97%, respectively. Furthermore, cross-validation and performance comparison with existing works is also carried out. Findings indicate that the proposed approach offers a prospective solution for detecting security threats for aerial systems and satellite systems with high accuracy.展开更多
基金supported by Key Science and Technology Program of Henan Province,China(Grant Nos.242102210147,242102210027)Fujian Province Young and Middle aged Teacher Education Research Project(Science and Technology Category)(No.JZ240101)(Corresponding author:Dong Yuan).
文摘Vehicle Edge Computing(VEC)and Cloud Computing(CC)significantly enhance the processing efficiency of delay-sensitive and computation-intensive applications by offloading compute-intensive tasks from resource-constrained onboard devices to nearby Roadside Unit(RSU),thereby achieving lower delay and energy consumption.However,due to the limited storage capacity and energy budget of RSUs,it is challenging to meet the demands of the highly dynamic Internet of Vehicles(IoV)environment.Therefore,determining reasonable service caching and computation offloading strategies is crucial.To address this,this paper proposes a joint service caching scheme for cloud-edge collaborative IoV computation offloading.By modeling the dynamic optimization problem using Markov Decision Processes(MDP),the scheme jointly optimizes task delay,energy consumption,load balancing,and privacy entropy to achieve better quality of service.Additionally,a dynamic adaptive multi-objective deep reinforcement learning algorithm is proposed.Each Double Deep Q-Network(DDQN)agent obtains rewards for different objectives based on distinct reward functions and dynamically updates the objective weights by learning the value changes between objectives using Radial Basis Function Networks(RBFN),thereby efficiently approximating the Pareto-optimal decisions for multiple objectives.Extensive experiments demonstrate that the proposed algorithm can better coordinate the three-tier computing resources of cloud,edge,and vehicles.Compared to existing algorithms,the proposed method reduces task delay and energy consumption by 10.64%and 5.1%,respectively.
基金supported by the Japan Society for the Promotion of Science(JSPS)Grants-in-Aid for Scientific Research(C)23K03898.
文摘Traffic at urban intersections frequently encounters unexpected obstructions,resulting in congestion due to uncooperative and priority-based driving behavior.This paper presents an optimal right-turn coordination system for Connected and Automated Vehicles(CAVs)at single-lane intersections,particularly in the context of left-hand side driving on roads.The goal is to facilitate smooth right turns for certain vehicles without creating bottlenecks.We consider that all approaching vehicles share relevant information through vehicular communications.The Intersection Coordination Unit(ICU)processes this information and communicates the optimal crossing or turning times to the vehicles.The primary objective of this coordination is to minimize overall traffic delays,which also helps improve the fuel consumption of vehicles.By considering information from upcoming vehicles at the intersection,the coordination system solves an optimization problem to determine the best timing for executing right turns,ultimately minimizing the total delay for all vehicles.The proposed coordination system is evaluated at a typical urban intersection,and its performance is compared to traditional traffic systems.Numerical simulation results indicate that the proposed coordination system significantly enhances the average traffic speed and fuel consumption compared to the traditional traffic system in various scenarios.
基金supported in part by 14th Five Year National Key R&D Program Project(Project Number:2023YFB3211001)the National Natural Science Foundation of China(62273339,U24A201397).
文摘Rapidly-exploring Random Tree(RRT)and its variants have become foundational in path-planning research,yet in complex three-dimensional off-road environments their uniform blind sampling and limited safety guarantees lead to slow convergence and force an unfavorable trade-off between path quality and traversal safety.To address these challenges,we introduce HS-APF-RRT*,a novel algorithm that fuses layered sampling,an enhanced Artificial Potential Field(APF),and a dynamic neighborhood-expansion mechanism.First,the workspace is hierarchically partitioned into macro,meso,and micro sampling layers,progressively biasing random samples toward safer,lower-energy regions.Second,we augment the traditional APF by incorporating a slope-dependent repulsive term,enabling stronger avoidance of steep obstacles.Third,a dynamic expansion strategy adaptively switches between 8 and 16 connected neighborhoods based on local obstacle density,striking an effective balance between search efficiency and collision-avoidance precision.In simulated off-road scenarios,HS-APF-RRT*is benchmarked against RRT*,GoalBiased RRT*,and APF-RRT*,and demonstrates significantly faster convergence,lower path-energy consumption,and enhanced safety margins.
基金Supported by the National Defense Basic Scientific Research Program of China.
文摘Amphibious vehicles are more prone to attitude instability compared to ships,making it crucial to develop effective methods for monitoring instability risks.However,large inclination events,which can lead to instability,occur frequently in both experimental and operational data.This infrequency causes events to be overlooked by existing prediction models,which lack the precision to accurately predict inclination attitudes in amphibious vehicles.To address this gap in predicting attitudes near extreme inclination points,this study introduces a novel loss function,termed generalized extreme value loss.Subsequently,a deep learning model for improved waterborne attitude prediction,termed iInformer,was developed using a Transformer-based approach.During the embedding phase,a text prototype is created based on the vehicle’s operation log data is constructed to help the model better understand the vehicle’s operating environment.Data segmentation techniques are used to highlight local data variation features.Furthermore,to mitigate issues related to poor convergence and slow training speeds caused by the extreme value loss function,a teacher forcing mechanism is integrated into the model,enhancing its convergence capabilities.Experimental results validate the effectiveness of the proposed method,demonstrating its ability to handle data imbalance challenges.Specifically,the model achieves over a 60%improvement in root mean square error under extreme value conditions,with significant improvements observed across additional metrics.
基金supported by the Scientific Research Innovation Capability Support Project for Young Faculty,China(No.ZYGXQNJSKYCXNLZCXM-D1)the National Natural Science Foundation of China(No.52272384).
文摘Flapping-Wing Micro Air Vehicles(FMAVs)are compact and agile,capable of accessing narrow spaces that conventional vehicles struggle to reach,such as ruins,caves,or the interiors of complex structures,making them ideal tools for reconnaissance and rescue missions.1 However,the operation of FMAVs relies on coordinating multiple forces with different scaling effects,posing challenges to miniaturization design.
基金supported by the National Natural Science Foundation of China(62003214)Guangdong Basic and Applied Basic Research Foundation(2024A1515012681)+1 种基金the Natural Science Foundation of Shanghai(22ZR1443600)Shanghai Pujiang Programme(23PJD064).
文摘Dear Editor,This letter considers the problem of achieving optimal formation control in multiple vertical take-off and landing(VTOL)unmanned aerial vehicles(UAVs).Specifically,the objective is to derive the vehicles to the desired formation shape while minimizing the total cost function.Leveraging the backstepping design,a distributed control strategy is proposed that incorporates a dynamic system for generating a reference trajectory and a trajectory tracking controller for each vehicle.
文摘The usage of electric vehicles holds a crucial role in lowering the diminishing of the ozone layer because electric vehicles are not dependent on fossil fuels.With more research,evaluation,and its characteristics on electric vehicles,the infrastructure of charging points,production of electric vehicles,and network modelling,this paper provides a comprehensive overview of electric vehicles,and hybrid vehicles,including an analysis of their market growth,as well as different types of optimization used in the current scenario.In developing countries like India,the biggest barrier is their unfulfilled facility over the charging.Without renewable energy sources,vehicle-to-grid technology facilitates the enhancement of additional power requirements.The mobility factor has been considered an important and special characteristic of electric vehicles.
基金Supported by the Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX24_0102)the China Scholarship Council Program(202406190114)。
文摘Studying the coupling coordination development of new energy vehicles(NEVs)and the ecological environment in China is helpful in promoting the development of NEVs in the country and is of great significance in promoting high-quality development of new energy in China.This paper constructs an evaluation index system for the development of NEVs and the ecological environment.It uses game theory combining weighting model,particle swarm optimized projection tracking evaluation model,coupling coordination degree model,and machine learning algorithms to calculate and analyze the level of coupling coordination development of NEVs and the ecological environment in China from 2010 to 2021,and identifies the driving factors.The research results show that:(i)From 2010 to 2021,the development index of NEVs in China has steadily increased from 0.085 to 0.634,while the ecological environment level index significantly rose from 0.170 to 0.884,reflecting the continuous development of China in both NEVs and the ecological environment.(ii)From 2010 to 2012,the two systems—new energy vehicle(NEV)development and the ecological environment—were in a period of imbalance and decline.From 2013 to 2016,they underwent a transition period,and from 2017 to 2021,they entered a period of coordinated development showing a trend of benign and continuous improvement.By 2021,they reached a good level of coordination.(iii)Indicators such as the number of patents granted for NEVs,water consumption per unit of GDP,and energy consumption per unit of GDP are the main driving factors affecting the coupling coordination development of NEVs and the ecological environment in China.
基金funded by the“Research and Application Project of Collaborative Optimization Control Technology for Distribution Station Area for High Proportion Distributed PV Consumption(4000-202318079A-1-1-ZN)”of the Headquarters of the State Grid Corporation.
文摘Considering the uncertainty of grid connection of electric vehicle charging stations and the uncertainty of new energy and residential electricity load,a spatio-temporal decoupling strategy of dynamic reactive power optimization based on clustering-local relaxation-correction is proposed.Firstly,the k-medoids clustering algorithm is used to divide the reduced power scene into periods.Then,the discrete variables and continuous variables are optimized in the same period of time.Finally,the number of input groups of parallel capacitor banks(CB)in multiple periods is fixed,and then the secondary static reactive power optimization correction is carried out by using the continuous reactive power output device based on the static reactive power compensation device(SVC),the new energy grid-connected inverter,and the electric vehicle charging station.According to the characteristics of the model,a hybrid optimization algorithm with a cross-feedback mechanism is used to solve different types of variables,and an improved artificial hummingbird algorithm based on tent chaotic mapping and adaptive mutation is proposed to improve the solution efficiency.The simulation results show that the proposed decoupling strategy can obtain satisfactory optimization resultswhile strictly guaranteeing the dynamic constraints of discrete variables,and the hybrid algorithm can effectively solve the mixed integer nonlinear optimization problem.
基金This work was funded by the research center of the Future University in Egypt,in 2023.
文摘Utilizing artificial intelligence(AI)to protect smart coastal cities has become a novel vision for scientific and industrial institutions.One of these AI technologies is using efficient and secure multi-environment Unmanned Vehicles(UVs)for anti-submarine attacks.This study’s contribution is the early detection of a submarine assault employing hybrid environment UVs that are controlled using swarm optimization and secure the information in between UVs using a decentralized cybersecurity strategy.The Dragonfly Algorithm is used for the orientation and clustering of the UVs in the optimization approach,and the Re-fragmentation strategy is used in the Network layer of the TCP/IP protocol as a cybersecurity solution.The research’s noteworthy findings demonstrate UVs’logistical capability to promptly detect the target and address the problem while securely keeping the drone’s geographical information.The results suggest that detecting the submarine early increases the likelihood of averting a collision.The dragonfly strategy of sensing the position of the submersible and aggregating around it demonstrates the reliability of swarm intelligence in increasing access efficiency.Securing communication between Unmanned Aerial Vehicles(UAVs)improves the level of secrecy necessary for the task.The swarm navigation is based on a peer-to-peer system,which allows each UAV to access information from its peers.This,in turn,helps the UAVs to determine the best route to take and to avoid collisions with other UAVs.The dragonfly strategy also increases the speed of the mission by minimizing the time spent finding the target.
基金supported by the National Natural Science Foundation of China under Grant 61931005Beijing Natural Science Foundation under Grant L202018the Key Laboratory of Internet of Vehicle Technical Innovation and Testing(CAICT),Ministry of Industry and Information Technology under Grant No.KL-2023-001。
文摘In Internet of Vehicles,VehicleInfrastructure-Cloud cooperation supports diverse intelligent driving and intelligent transportation applications.Federated Learning(FL)is the emerging computation paradigm to provide efficient and privacypreserving collaborative learning.However,in Io V environment,federated learning faces the challenges introduced by high mobility of vehicles and nonIndependently Identically Distribution(non-IID)of data.High mobility causes FL clients quit and the communication offline.The non-IID data leads to slow and unstable convergence of global model and single global model's weak adaptability to clients with different localization characteristics.Accordingly,this paper proposes a personalized aggregation strategy for hierarchical Federated Learning in Io V environment,including Fed SA(Special Asynchronous Federated Learning with Self-adaptive Aggregation)for low-level FL between a Road Side Unit(RSU)and the vehicles within its coverage,and Fed Att(Federated Learning with Attention Mechanism)for high-level FL between a cloud server and multiple RSUs.Agents self-adaptively obtain model aggregation weight based on Advantage Actor-Critic(A2C)algorithm.Experiments show the proposed strategy encourages vehicles to participate in global aggregation,and outperforms existing methods in training performance.
文摘In March 2025,prominent Chinese automaker NIO(Shanghai,China),the global leader in electric vehicle(EV)battery swapping,and Contemporary Amperex Technology Co.,Ltd.(CATL)(Nindge,China),the world’s biggest manufacturer of EV batteries,announced a strategic partnership to build the world’s largest battery swapping network,while also promoting unified standards and technologies[1].Just weeks later,CATL announced another partnership,this one with Chinese state-owned oil giant Sinopec(Beijing,China)to build 10000 new battery swapping stations in China,at least 500 in 2025[2].
基金Supported by National Natural Science Foundation of China(Grant No.61803206)Jiangsu Provincial Natural Science Foundation(Grant No.222300420468)Jiangsu Provincial key R&D Program(Grant No.BE2017008-2).
文摘Complex road conditions without signalized intersections when the traffic flow is nearly saturated result in high traffic congestion and accidents,reducing the traffic efficiency of intelligent vehicles.The complex road traffic environment of smart vehicles and other vehicles frequently experiences conflicting start and stop motion.The fine-grained scheduling of autonomous vehicles(AVs)at non-signalized intersections,which is a promising technique for exploring optimal driving paths for both assisted driving nowadays and driverless cars in the near future,has attracted significant attention owing to its high potential for improving road safety and traffic efficiency.Fine-grained scheduling primarily focuses on signalized intersection scenarios,as applying it directly to non-signalized intersections is challenging because each AV can move freely without traffic signal control.This may cause frequent driving collisions and low road traffic efficiency.Therefore,this study proposes a novel algorithm to address this issue.Our work focuses on the fine-grained scheduling of automated vehicles at non-signal intersections via dual reinforced training(FS-DRL).For FS-DRL,we first use a grid to describe the non-signalized intersection and propose a convolutional neural network(CNN)-based fast decision model that can rapidly yield a coarse-grained scheduling decision for each AV in a distributed manner.We then load these coarse-grained scheduling decisions onto a deep Q-learning network(DQN)for further evaluation.We use an adaptive learning rate to maximize the reward function and employ parameterεto tradeoff the fast speed of coarse-grained scheduling in the CNN and optimal fine-grained scheduling in the DQN.In addition,we prove that using this adaptive learning rate leads to a converged loss rate with an extremely small number of training loops.The simulation results show that compared with Dijkstra,RNN,and ant colony-based scheduling,FS-DRL yields a high accuracy of 96.5%on the sample,with improved performance of approximately 61.54%-85.37%in terms of the average conflict and traffic efficiency.
基金in part by the National Natural Science Foundation of China(NSFC)under Grant 62371012in part by the Beijing Natural Science Foundation under Grant 4252001.
文摘As an essential element of intelligent trans-port systems,Internet of vehicles(IoV)has brought an immersive user experience recently.Meanwhile,the emergence of mobile edge computing(MEC)has enhanced the computational capability of the vehicle which reduces task processing latency and power con-sumption effectively and meets the quality of service requirements of vehicle users.However,there are still some problems in the MEC-assisted IoV system such as poor connectivity and high cost.Unmanned aerial vehicles(UAVs)equipped with MEC servers have become a promising approach for providing com-munication and computing services to mobile vehi-cles.Hence,in this article,an optimal framework for the UAV-assisted MEC system for IoV to minimize the average system cost is presented.Through joint consideration of computational offloading decisions and computational resource allocation,the optimiza-tion problem of our proposed architecture is presented to reduce system energy consumption and delay.For purpose of tackling this issue,the original non-convex issue is converted into a convex issue and the alternat-ing direction method of multipliers-based distributed optimal scheme is developed.The simulation results illustrate that the presented scheme can enhance the system performance dramatically with regard to other schemes,and the convergence of the proposed scheme is also significant.
文摘Unmanned Aerial Vehicles(UAVs)are increasingly recognized for their pivotal role in military and civilian applications,serving as essential technology for transmitting,evaluating,and gathering information.Unfortunately,this crucial process often occurs through unsecured wireless connections,exposing it to numerous cyber-physical attacks.Furthermore,UAVs’limited onboard computing resources make it challenging to perform complex cryptographic operations.The main aim of constructing a cryptographic scheme is to provide substantial security while reducing the computation and communication costs.This article introduces an efficient and secure cross-domain Authenticated Key Agreement(AKA)scheme that uses Hyperelliptic Curve Cryptography(HECC).The HECC,a modified version of ECC with a smaller key size of 80 bits,is well-suited for use in UAVs.In addition,the proposed scheme is employed in a cross-domain environment that integrates a Public Key Infrastructure(PKI)at the receiving end and a Certificateless Cryptosystem(CLC)at the sending end.Integrating CLC with PKI improves network security by restricting the exposure of encryption keys only to the message’s sender and subsequent receiver.A security study employing ROM and ROR models,together with a comparative performance analysis,shows that the proposed scheme outperforms comparable existing schemes in terms of both efficiency and security.
基金supported in part by the National Natural Science Foundation of China(52172377).
文摘An effective energy management strategy(EMS)is essential to optimize the energy efficiency of electric vehicles(EVs).With the advent of advanced machine learning techniques,the focus on developing sophisticated EMS for EVs is increasing.Here,we introduce LearningEMS:a unified framework and open-source benchmark designed to facilitate rapid development and assessment of EMS.LearningEMS is distinguished by its ability to support a variety of EV configurations,including hybrid EVs,fuel cell EVs,and plug-in EVs,offering a general platform for the development of EMS.The framework enables detailed comparisons of several EMS algorithms,encompassing imitation learning,deep reinforcement learning(RL),offline RL,model predictive control,and dynamic programming.We rigorously evaluated these algorithms across multiple perspectives:energy efficiency,consistency,adaptability,and practicability.Furthermore,we discuss state,reward,and action settings for RL in EV energy management,introduce a policy extraction and reconstruction method for learning-based EMS deployment,and conduct hardware-in-the-loop experiments.In summary,we offer a unified and comprehensive framework that comes with three distinct EV platforms,over 10000 km of EMS policy data set,ten state-of-the-art algorithms,and over 160 benchmark tasks,along with three learning libraries.Its flexible design allows easy expansion for additional tasks and applications.The open-source algorithms,models,data sets,and deployment processes foster additional research and innovation in EV and broader engineering domains.
基金fund support was received from Sichuan Philosophy and Social Science Foundation Program[Grant No.SCJJ24ND066].
文摘New energy vehicles are distinguished by their environmentally friendly characteristics;however,their sales remain low compared with those of fossil fuel vehicles.This study identifies the key factors influencing consumer purchases of new energy vehicles with the aim of increasing sales and promoting the development of the new energy vehicle industry.Machine learning(ML)techniques were employed to analyze more than 26000 consumer reviews of new energy vehicles and identify the factors influencing their purchasing decisions.Subsequently,a hybrid simulation model was constructed using the complex adaptive system framework.The model combines the strengths of ML,multi-agent modeling,and system dynamics modeling,thereby enhancing its capacity to identify key factors.The model comprises two categories of manufacturers:producers of new energy vehicles and producers of fossil fuel vehicles.Dynamic simulations were conducted using the AnyLogic simulation platform.The findings indicated a negative correlation between consumer income and demand for new energy vehicles.Conversely,expansions in the interior space of new energy vehicles and favorable consumer perceptions of their environmental benefits have contributed to increased demand for these vehicles.Therefore,rather than exclusively focusing on price advantages,it would be more beneficial to prioritize expanding new energy vehicles’interior space and disseminating information about their environmental benefits to consumers.It seems reasonable to posit that these strategies would increase consumer willingness to purchase new energy vehicles in the long term.
基金supported by the National Natural Science Foundation of China(Grant Nos.52272437 and 52272370)the Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX24_0635)。
文摘The high cost and low efficiency of full-scale vehicle experiments and numerical simulations limit the efficient development of armored vehicle occupant protection systems.The floor-occupant-seat local simulation model provides an alternative solution for quickly evaluating the performance of occupant protection systems.However,the error and rationality of the loading of the thin-walled floor in the local model cannot be ignored.This study proposed an equivalent loading method for the local model,which includes two parts:the dimensionality reduction method for acceleration matrix and the joint optimization framework for equivalent node coordinates.In the dimensionality reduction method,the dimension of the acceleration matrix was reduced based on the improved kernel principal component analysis(KPCA),and a dynamic variable bandwidth was introduced to address the limitation of failing to effectively measure the similarity between acceleration data in conventional KPCA.In addition,a least squares problem with forced displacement constraints was constructed to solve the correction matrix,thereby achieving the scale restoration process of the principal component acceleration matrix.The joint optimization framework for coordinates consists of the error assessment of response time histories(EARTH)and Bayesian optimization.In this framework,the local loading error of the equivalent acceleration matrix is taken as the Bayesian optimization objective,which is quantified and scored by EARTH.The expected improvement acquisition function was used to select the new set of the equivalent acceleration node coordinates for the self-updating optimization of the observation dataset and Gaussian process surrogate model.We reduced the dimension of the acceleration matrix from 2256 to 7,while retaining 91%of the information features.The comprehensive error score of occupant's lower limb response in the local model increased from 58.5%to 80.4%.The proposed equivalent loading method provides a solution for the rapid and reliable development of occupant protection systems.
基金supported by the National Natural Science Foundation of China under Grant T2521006,Grant 62403483,Grant 62533021 and Grant U24A20279.
文摘Reinforcement learning(RL)has been widely studied as an efficient class of machine learning methods for adaptive optimal control under uncertainties.In recent years,the applications of RL in optimised decision-making and motion control of intelligent vehicles have received increasing attention.Due to the complex and dynamic operating environments of intelligent vehicles,it is necessary to improve the learning efficiency and generalisation ability of RL-based decision and control algorithms under different conditions.This survey systematically examines the theoretical foundations,algorithmic advancements and practical challenges of applying RL to intelligent vehicle systems operating in complex and dynamic environments.The major algorithm frameworks of RL are first introduced,and the recent advances in RL-based decision-making and control of intelligent vehicles are overviewed.In addition to self-learning decision and control approaches using state measurements,the developments of DRL methods for end-to-end driving control of intelligent vehicles are summarised.The open problems and directions for further research works are also discussed.
文摘Small-drone technology has opened a range of new applications for aerial transportation. These drones leverage the Internet of Things (IoT) to offer cross-location services for navigation. However, they are susceptible to security and privacy threats due to hardware and architectural issues. Although small drones hold promise for expansion in both civil and defense sectors, they have safety, security, and privacy threats. Addressing these challenges is crucial to maintaining the security and uninterrupted operations of these drones. In this regard, this study investigates security, and preservation concerning both the drones and Internet of Drones (IoD), emphasizing the significance of creating drone networks that are secure and can robustly withstand interceptions and intrusions. The proposed framework incorporates a weighted voting ensemble model comprising three convolutional neural network (CNN) models to enhance intrusion detection within the network. The employed CNNs are customized 1D models optimized to obtain better performance. The output from these CNNs is voted using a weighted criterion using a 0.4, 0.3, and 0.3 ratio for three CNNs, respectively. Experiments involve using multiple benchmark datasets, achieving an impressive accuracy of up to 99.89% on drone data. The proposed model shows promising results concerning precision, recall, and F1 as indicated by their obtained values of 99.92%, 99.98%, and 99.97%, respectively. Furthermore, cross-validation and performance comparison with existing works is also carried out. Findings indicate that the proposed approach offers a prospective solution for detecting security threats for aerial systems and satellite systems with high accuracy.
