System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose sign...System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose significant challenges for efficient decision-making,necessitating a modular multiagent control system.Deep Reinforcement Learning(DRL)and Decision Tree(DT)have been utilized for these complex decision-making tasks,but each has its limitations:DRL is highly adaptive but lacks interpretability,while DT is inherently interpretable but has limited adaptability.To overcome these challenges,we propose the Adaptive Interpretable Decision Tree(AIDT),an evolutionary-based algorithm that is both adaptable to diverse environmental settings and highly interpretable in its decision-making processes.We first construct a Markov decision process(MDP)-based simulation environment using the Cooperative Submarine Search task as a representative scenario for training and testing the proposed method.Specifically,we use the heat map as a state variable to address the issue of multi-agent input state proliferation.Next,we introduce the curiosity-guiding intrinsic reward to encourage comprehensive exploration and enhance algorithm performance.Additionally,we incorporate decision tree size as an influence factor in the adaptation process to balance task completion with computational efficiency.To further improve the generalization capability of the decision tree,we apply a normalization method to ensure consistent processing of input states.Finally,we validate the proposed algorithm in different environmental settings,and the results demonstrate both its adaptability and interpretability.展开更多
When performing tasks,unmanned clusters often face a variety of strategy choices.One of the key issues in unmanned cluster tasks is the method through which to design autonomous collaboration and cooperative evolution...When performing tasks,unmanned clusters often face a variety of strategy choices.One of the key issues in unmanned cluster tasks is the method through which to design autonomous collaboration and cooperative evolution mechanisms that allow for unmanned clusters to maximize their overall task effective-ness under the condition of strategic diversity.This paper ana-lyzes these task requirements from three perspectives:the diver-sity of the decision space,information network construction,and the autonomous collaboration mechanism.Then,this paper pro-poses a method for solving the problem of strategy selection diversity under two network structures.Next,this paper presents a Moran-rule-based evolution dynamics model for unmanned cluster strategies and a vision-driven-mechanism-based evolu-tion dynamics model for unmanned cluster strategy in the con-text of strategy selection diversity according to various unmanned cluster application scenarios.Finally,this paper pro-vides a simulation analysis of the effects of relevant parameters such as the payoff factor and cluster size on cooperative evolu-tion in autonomous cluster collaboration for the two types of models.On this basis,this paper presents advice for effectively addressing diverse choices in unmanned cluster tasks,thereby providing decision support for practical applications of unmanned cluster tasks.展开更多
A situation maintenance-based cooperative guidance strategy is proposed to intercept a high-speed and high-maneuverability target via inferior missiles.Reachability and relative motion analyses are conducted to develo...A situation maintenance-based cooperative guidance strategy is proposed to intercept a high-speed and high-maneuverability target via inferior missiles.Reachability and relative motion analyses are conducted to develop and pursue virtual targets,respectively.A two-stage guidance strategy under nonlinear kinematics is developed on the basis of virtual targets.The first stage optimizes the coverage and collision situation by pursuing virtual targets under specific angular constraints.The second stage subsequently intercepts the superior target based on the handover condition optimized by the first stage.Numerical simulation results are provided to compare the effectiveness and superiority of the proposed strategy with those of the reachability-based cooperative strategy(RCS),coverage-based cooperative guidance(CBCG)and augmented proportional navigation(APN)under various maneuvering modes.展开更多
This paper presents a mode-switching collaborative defense strategy for spacecraft pursuit-evasiondefense scenarios.In these scenarios,the pursuer tries to avoid the defender while capturing the evader,while the evade...This paper presents a mode-switching collaborative defense strategy for spacecraft pursuit-evasiondefense scenarios.In these scenarios,the pursuer tries to avoid the defender while capturing the evader,while the evader and defender form an alliance to prevent the pursuer from achieving its goal.First,the behavioral modes of the pursuer,including attack and avoidance modes,were established using differential game theory.These modes are then recognized by an interactive multiple model-matching algorithm(IMM),that uses several smooth variable structure filters to match the modes of the pursuer and update their probabilities in real time.Based on the linear-quadratic optimization theory,combined with the results of strategy identification,a two-way cooperative optimal strategy for the defender and evader is proposed,where the evader aids the defender to intercept the pursuer by performing luring maneuvers.Simulation results show that the interactive multi-model algorithm based on several smooth variable structure filters perform well in the strategy identification of the pursuer,and the cooperative defense strategy based on strategy identification has good interception performance when facing pursuers,who are able to flexibly adjust their game objectives.展开更多
This paper presents a fixed-time cooperative gui-dance method with impact angle constraints for multiple flight vehicles (MFV) to address the challenges of intercepting large maneuvering targets with difficulty and lo...This paper presents a fixed-time cooperative gui-dance method with impact angle constraints for multiple flight vehicles (MFV) to address the challenges of intercepting large maneuvering targets with difficulty and low precision. A coopera-tive guidance model is proposed, transforming the cooperative interception problem into a consensus problem based on the remaining flight time of the flight vehicles. First, the impact angle constraint is converted into the line of sight (LOS) angle con-straint, and a new fixed-time convergent non-singular terminal sliding surface is introduced, which resolves the singularity issue of the traditional sliding surfaces. With this approach, LOS angle rate and normal overloads can converge in fixed time, ensuring that the upper bound of the system convergence time is not affected by the initial value of the system. Furthermore, the maneuvering movement of the target is considered as a system disturbance, and an extended state observer is employed to estimate and compensate for it in the guidance law. Lastly, by applying consensus theory and distributed communication topology, the remaining flight time of each flight vehicle is syn-chronized to ensure that they intercept the target simulta-neously with different impact angles. Simulation experiments are conducted to validate the effectiveness of the proposed cooper-ative interception and guidance method.展开更多
In the realm of missile defense systems,the self-sufficient maneuver capacity of missile swarms is pivotal for their survival.Through the analysis of the missile dynamics model,a time-efficient cooperative attack stra...In the realm of missile defense systems,the self-sufficient maneuver capacity of missile swarms is pivotal for their survival.Through the analysis of the missile dynamics model,a time-efficient cooperative attack strategy for missile swarm is proposed.Based on the distribution of the attackers and defenders,the collision avoidance against the defenders is considered during the attack process.By analyzing the geometric relationship between the relative velocity vector and relative position vector of the attackers and defenders,the collision avoidance constrains of attacking swarm are redefined.The key point is on adjusting the relative velocity vectors to fall outside the collision cone.This work facilitates high-precision attack toward the target while keeping safe missing distance between other attackers during collision avoidance process.By leveraging an innovative repulsion artificial function,a time-efficient cooperative attack strategy for missile swarm is obtained.Through rigorous simulation,the effectiveness of this cooperative attack strategy is substantiated.Furthermore,by employing Monte Carlo simulation,the success rate of the cooperative attack strategy is assessesed and the optimal configuration for the missile swarm is deduced.展开更多
To solve the problem of providing the best initial situation for terminal guidance when multiple missiles intercept multiple targets,a group cooperative midcourse guidance law(GCMGL)considering time-to-go is proposed....To solve the problem of providing the best initial situation for terminal guidance when multiple missiles intercept multiple targets,a group cooperative midcourse guidance law(GCMGL)considering time-to-go is proposed.Firstly,a threedimensional(3D)guidance model is established and a cooperative trajectory shaping guidance law is given.Secondly,for estimating the unknown target maneuvering acceleration,an adaptive disturbance observer(ADO)is designed,combining finitetime theory with a radial basis function(RBF)neural network,and the convergence of the estimation error is proven using Lyapunov stability theory.Then,to ensure time-to-go cooperation among missiles within the same group and across different groups,the group consensus protocols of virtual collision point mean and the inter-group cooperative consensus protocol are designed respectively.Based on the group consensus protocols,the virtual collision point cooperative guidance law is given,and the finite-time convergence is proved by Lyapunov stability theory.Simultaneously,combined with trajectory shaping guidance law,virtual collision point cooperative guidance law and the intergroup cooperative consensus protocol,the design of GCMGL considering time-to-go is given.Finally,numerical simulation results show the effectiveness and the superiority of the proposed GCMGL.展开更多
How multi-unmanned aerial vehicles(UAVs)carrying a payload pass an obstacle-dense environment is practically important.Up to now,there have been few results on safe motion planning for the multi-UAVs cooperative trans...How multi-unmanned aerial vehicles(UAVs)carrying a payload pass an obstacle-dense environment is practically important.Up to now,there have been few results on safe motion planning for the multi-UAVs cooperative transportation system(CTS)to pass through such an environment.The prob-lem is challenging because it is difficult to analyze and explicitly take into account the swing motion of the payload in planning.In this paper,a modeling method of virtual tube is proposed by fus-ing the advantages of the existing modeling algorithm for regu-lar virtual tube and the expansion environment method.The pro-posed method can not only generate a safe and smooth tube for UAVs,but also ensure the payload stays away from the dense obstacles.Simulation results show the effectiveness of the method and the safety of the planned tube.展开更多
With the development of China＇s market economy, the agricultural products＇ market has changed from the seller＇s market into the buyer＇s market. Therefore, the limitations of the household contract responsibility s...With the development of China＇s market economy, the agricultural products＇ market has changed from the seller＇s market into the buyer＇s market. Therefore, the limitations of the household contract responsibility system gradually appeared. The farmers professional cooperatives not only covered the limitations but also effectively connected the small-scale farmers with the competitive market by increasing the farmers＇ organizational degree. However, during the development process of farmers＇ professional cooperatives, many problems were exposed. By using SWOT analysis belonging to the field of enterprise strategic management, this paper discussed the opportunities and threats of the external environment, as well as the strengths and weaknesses of the internal environment of Chinese farmers＇ professional cooperatives. Thereby, it proposed some development strategies for Chinese farmers professional cooperatives in the current stage .展开更多
Aiming at the problem of multi-UAV pursuit-evasion confrontation, a UAV cooperative maneuver method based on an improved multi-agent deep reinforcement learning(MADRL) is proposed. In this method, an improved Comm Net...Aiming at the problem of multi-UAV pursuit-evasion confrontation, a UAV cooperative maneuver method based on an improved multi-agent deep reinforcement learning(MADRL) is proposed. In this method, an improved Comm Net network based on a communication mechanism is introduced into a deep reinforcement learning algorithm to solve the multi-agent problem. A layer of gated recurrent unit(GRU) is added to the actor-network structure to remember historical environmental states. Subsequently,another GRU is designed as a communication channel in the Comm Net core network layer to refine communication information between UAVs. Finally, the simulation results of the algorithm in two sets of scenarios are given, and the results show that the method has good effectiveness and applicability.展开更多
Improvement of integrated battlefield situational awareness in complex environments involving dynamic factors such as restricted communications and electromagnetic interference(EMI)has become a contentious research pr...Improvement of integrated battlefield situational awareness in complex environments involving dynamic factors such as restricted communications and electromagnetic interference(EMI)has become a contentious research problem.In certain mission environments,due to the impact of many interference sources on real-time communication or mission requirements such as the need to implement communication regulations,the mission stages are represented as a dynamic combination of several communication-available and communication-unavailable stages.Furthermore,the data interaction between unmanned aerial vehicles(UAVs)can only be performed in specific communication-available stages.Traditional cooperative search algorithms cannot handle such situations well.To solve this problem,this study constructed a distributed model predictive control(DMPC)architecture for a collaborative control of UAVs and used the Voronoi diagram generation method to re-plan the search areas of all UAVs in real time to avoid repetition of search areas and UAV collisions while improving the search efficiency and safety factor.An attention mechanism ant-colony optimization(AACO)algorithm is proposed for UAV search-control decision planning.The search strategy is adaptively updated by introducing an attention mechanism for regular instruction information,a priori information,and emergent information of the mission to satisfy different search expectations to the maximum extent.Simulation results show that the proposed algorithm achieves better search performance than traditional algorithms in restricted communication constraint scenarios.展开更多
To solve the problem that multiple missiles should simultaneously attack unmeasurable maneuvering targets,a guidance law with temporal consistency constraint based on the super-twisting observer is proposed.Firstly,th...To solve the problem that multiple missiles should simultaneously attack unmeasurable maneuvering targets,a guidance law with temporal consistency constraint based on the super-twisting observer is proposed.Firstly,the relative motion equations between multiple missiles and targets are established,and the topological model among multiple agents is considered.Secondly,based on the temporal consistency constraint,a cooperative guidance law for simultaneous arrival with finite-time convergence is derived.Finally,the unknown target maneuver-ing is regarded as bounded interference.Based on the second-order sliding mode theory,a super-twisting sliding mode observer is devised to observe and track the bounded interfer-ence,and the stability of the observer is proved.Compared with the existing research,this approach only needs to obtain the sliding mode variable which simplifies the design process.The simulation results show that the designed cooperative guidance law for maneuvering targets achieves the expected effect.It ensures successful cooperative attacks,even when confronted with strong maneuvering targets.展开更多
To address the charging infrastructure challenges associated with slow electric vehicle(EV)industry growth,this study investigates the collaboration between private charging-pile-sharing platforms struggling with prof...To address the charging infrastructure challenges associated with slow electric vehicle(EV)industry growth,this study investigates the collaboration between private charging-pile-sharing platforms struggling with profitability and automotive companies.This collaboration is crucial,as it demands a balanced price and service quality management due to consumer expectations.This paper introduces a Stackelberg game model to explore the relationship between a charging platform and an automotive company.Through numerical analysis,we assess how this cooperation might improve the platform’s efficiency and benefit society,potentially overcoming existing industry hurdles.Our findings indicate that such partnerships could benefit all parties involved,despite possible negative environmental impacts.However,after collaborat-ing,platforms may increase consumer prices and payments to suppliers,potentially lowering service quality for brand-associated consumers due to a compromise between shorter waiting times and service quality.This research offers valu-able insights for stakeholders on the effects of cooperation,enabling better strategic decisions in the EV charging sector.展开更多
As the unmanned weap system-of systems(UWSoS)becomes complex,the inevitable uncertain interference gradu-ally increases,which leads to a strong emphasis on the resilience of UWSoS.Hence,this paper presents a resilienc...As the unmanned weap system-of systems(UWSoS)becomes complex,the inevitable uncertain interference gradu-ally increases,which leads to a strong emphasis on the resilience of UWSoS.Hence,this paper presents a resilience-driven cooperative reconfiguration strategy to enhance the resilience of UWSoS.First,a unified resilience-driven coopera-tive reconfiguration strategy framework is designed to guide the UWSoS resilience enhancement.Subsequently,a cooperative reconfiguration strategy algorithm is proposed to identify the optimal cooperative reconfiguration sequence,combining the cooperative pair resilience contribution index(CPRCI)and coop-erative pair importance index(CPII).At last,the effectiveness and superiority of the proposed algorithm are demonstrated through various attack scenario simulations that include differ-ent attack modes and intensities.The analysis results can pro-vide a reference for decision-makers to manage UWSoS.展开更多
文摘System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose significant challenges for efficient decision-making,necessitating a modular multiagent control system.Deep Reinforcement Learning(DRL)and Decision Tree(DT)have been utilized for these complex decision-making tasks,but each has its limitations:DRL is highly adaptive but lacks interpretability,while DT is inherently interpretable but has limited adaptability.To overcome these challenges,we propose the Adaptive Interpretable Decision Tree(AIDT),an evolutionary-based algorithm that is both adaptable to diverse environmental settings and highly interpretable in its decision-making processes.We first construct a Markov decision process(MDP)-based simulation environment using the Cooperative Submarine Search task as a representative scenario for training and testing the proposed method.Specifically,we use the heat map as a state variable to address the issue of multi-agent input state proliferation.Next,we introduce the curiosity-guiding intrinsic reward to encourage comprehensive exploration and enhance algorithm performance.Additionally,we incorporate decision tree size as an influence factor in the adaptation process to balance task completion with computational efficiency.To further improve the generalization capability of the decision tree,we apply a normalization method to ensure consistent processing of input states.Finally,we validate the proposed algorithm in different environmental settings,and the results demonstrate both its adaptability and interpretability.
基金supported by the National Natural Science Foundation of China(72471240).
文摘When performing tasks,unmanned clusters often face a variety of strategy choices.One of the key issues in unmanned cluster tasks is the method through which to design autonomous collaboration and cooperative evolution mechanisms that allow for unmanned clusters to maximize their overall task effective-ness under the condition of strategic diversity.This paper ana-lyzes these task requirements from three perspectives:the diver-sity of the decision space,information network construction,and the autonomous collaboration mechanism.Then,this paper pro-poses a method for solving the problem of strategy selection diversity under two network structures.Next,this paper presents a Moran-rule-based evolution dynamics model for unmanned cluster strategies and a vision-driven-mechanism-based evolu-tion dynamics model for unmanned cluster strategy in the con-text of strategy selection diversity according to various unmanned cluster application scenarios.Finally,this paper pro-vides a simulation analysis of the effects of relevant parameters such as the payoff factor and cluster size on cooperative evolu-tion in autonomous cluster collaboration for the two types of models.On this basis,this paper presents advice for effectively addressing diverse choices in unmanned cluster tasks,thereby providing decision support for practical applications of unmanned cluster tasks.
基金supported by the National Natural Science Foundation of China(Grant No.62203362)the Natural Science Basic Research Program of Shaanxi(Grant No.2023-JC-QN-0569)。
文摘A situation maintenance-based cooperative guidance strategy is proposed to intercept a high-speed and high-maneuverability target via inferior missiles.Reachability and relative motion analyses are conducted to develop and pursue virtual targets,respectively.A two-stage guidance strategy under nonlinear kinematics is developed on the basis of virtual targets.The first stage optimizes the coverage and collision situation by pursuing virtual targets under specific angular constraints.The second stage subsequently intercepts the superior target based on the handover condition optimized by the first stage.Numerical simulation results are provided to compare the effectiveness and superiority of the proposed strategy with those of the reachability-based cooperative strategy(RCS),coverage-based cooperative guidance(CBCG)and augmented proportional navigation(APN)under various maneuvering modes.
基金the Science and Technology Department,Heilongjiang Province under Grant Agreement No JJ2022LH0315。
文摘This paper presents a mode-switching collaborative defense strategy for spacecraft pursuit-evasiondefense scenarios.In these scenarios,the pursuer tries to avoid the defender while capturing the evader,while the evader and defender form an alliance to prevent the pursuer from achieving its goal.First,the behavioral modes of the pursuer,including attack and avoidance modes,were established using differential game theory.These modes are then recognized by an interactive multiple model-matching algorithm(IMM),that uses several smooth variable structure filters to match the modes of the pursuer and update their probabilities in real time.Based on the linear-quadratic optimization theory,combined with the results of strategy identification,a two-way cooperative optimal strategy for the defender and evader is proposed,where the evader aids the defender to intercept the pursuer by performing luring maneuvers.Simulation results show that the interactive multi-model algorithm based on several smooth variable structure filters perform well in the strategy identification of the pursuer,and the cooperative defense strategy based on strategy identification has good interception performance when facing pursuers,who are able to flexibly adjust their game objectives.
基金supported by the National Natural Science Foundation of China(61903099)the Natural Science Foundation of Heilongjiang Province(LH2020F025)+2 种基金the Project of Science and Technology Research Program of Chongqing Education Commission of China(KJZD-K20200470)the Postdoctoral Science Foundation of China(2021M690812)the Postdoctoral Science Fund of Heilongjiang Province(LBH-Z21048).
文摘This paper presents a fixed-time cooperative gui-dance method with impact angle constraints for multiple flight vehicles (MFV) to address the challenges of intercepting large maneuvering targets with difficulty and low precision. A coopera-tive guidance model is proposed, transforming the cooperative interception problem into a consensus problem based on the remaining flight time of the flight vehicles. First, the impact angle constraint is converted into the line of sight (LOS) angle con-straint, and a new fixed-time convergent non-singular terminal sliding surface is introduced, which resolves the singularity issue of the traditional sliding surfaces. With this approach, LOS angle rate and normal overloads can converge in fixed time, ensuring that the upper bound of the system convergence time is not affected by the initial value of the system. Furthermore, the maneuvering movement of the target is considered as a system disturbance, and an extended state observer is employed to estimate and compensate for it in the guidance law. Lastly, by applying consensus theory and distributed communication topology, the remaining flight time of each flight vehicle is syn-chronized to ensure that they intercept the target simulta-neously with different impact angles. Simulation experiments are conducted to validate the effectiveness of the proposed cooper-ative interception and guidance method.
基金supported by the Intelligent Aerospace System Leading Innovation Team Program of Zhejiang(2022R01003).
文摘In the realm of missile defense systems,the self-sufficient maneuver capacity of missile swarms is pivotal for their survival.Through the analysis of the missile dynamics model,a time-efficient cooperative attack strategy for missile swarm is proposed.Based on the distribution of the attackers and defenders,the collision avoidance against the defenders is considered during the attack process.By analyzing the geometric relationship between the relative velocity vector and relative position vector of the attackers and defenders,the collision avoidance constrains of attacking swarm are redefined.The key point is on adjusting the relative velocity vectors to fall outside the collision cone.This work facilitates high-precision attack toward the target while keeping safe missing distance between other attackers during collision avoidance process.By leveraging an innovative repulsion artificial function,a time-efficient cooperative attack strategy for missile swarm is obtained.Through rigorous simulation,the effectiveness of this cooperative attack strategy is substantiated.Furthermore,by employing Monte Carlo simulation,the success rate of the cooperative attack strategy is assessesed and the optimal configuration for the missile swarm is deduced.
基金supported by the National Natural Science Foundation of China(62003264).
文摘To solve the problem of providing the best initial situation for terminal guidance when multiple missiles intercept multiple targets,a group cooperative midcourse guidance law(GCMGL)considering time-to-go is proposed.Firstly,a threedimensional(3D)guidance model is established and a cooperative trajectory shaping guidance law is given.Secondly,for estimating the unknown target maneuvering acceleration,an adaptive disturbance observer(ADO)is designed,combining finitetime theory with a radial basis function(RBF)neural network,and the convergence of the estimation error is proven using Lyapunov stability theory.Then,to ensure time-to-go cooperation among missiles within the same group and across different groups,the group consensus protocols of virtual collision point mean and the inter-group cooperative consensus protocol are designed respectively.Based on the group consensus protocols,the virtual collision point cooperative guidance law is given,and the finite-time convergence is proved by Lyapunov stability theory.Simultaneously,combined with trajectory shaping guidance law,virtual collision point cooperative guidance law and the intergroup cooperative consensus protocol,the design of GCMGL considering time-to-go is given.Finally,numerical simulation results show the effectiveness and the superiority of the proposed GCMGL.
基金supported by the National Natural Science Foundation of China(6237338661973327).
文摘How multi-unmanned aerial vehicles(UAVs)carrying a payload pass an obstacle-dense environment is practically important.Up to now,there have been few results on safe motion planning for the multi-UAVs cooperative transportation system(CTS)to pass through such an environment.The prob-lem is challenging because it is difficult to analyze and explicitly take into account the swing motion of the payload in planning.In this paper,a modeling method of virtual tube is proposed by fus-ing the advantages of the existing modeling algorithm for regu-lar virtual tube and the expansion environment method.The pro-posed method can not only generate a safe and smooth tube for UAVs,but also ensure the payload stays away from the dense obstacles.Simulation results show the effectiveness of the method and the safety of the planned tube.
文摘With the development of China＇s market economy, the agricultural products＇ market has changed from the seller＇s market into the buyer＇s market. Therefore, the limitations of the household contract responsibility system gradually appeared. The farmers professional cooperatives not only covered the limitations but also effectively connected the small-scale farmers with the competitive market by increasing the farmers＇ organizational degree. However, during the development process of farmers＇ professional cooperatives, many problems were exposed. By using SWOT analysis belonging to the field of enterprise strategic management, this paper discussed the opportunities and threats of the external environment, as well as the strengths and weaknesses of the internal environment of Chinese farmers＇ professional cooperatives. Thereby, it proposed some development strategies for Chinese farmers professional cooperatives in the current stage .
基金supported in part by the National Key Laboratory of Air-based Information Perception and Fusion and the Aeronautical Science Foundation of China (Grant No. 20220001068001)National Natural Science Foundation of China (Grant No.61673327)+1 种基金Natural Science Basic Research Plan in Shaanxi Province,China (Grant No. 2023-JC-QN-0733)China IndustryUniversity-Research Innovation Foundation (Grant No. 2022IT188)。
文摘Aiming at the problem of multi-UAV pursuit-evasion confrontation, a UAV cooperative maneuver method based on an improved multi-agent deep reinforcement learning(MADRL) is proposed. In this method, an improved Comm Net network based on a communication mechanism is introduced into a deep reinforcement learning algorithm to solve the multi-agent problem. A layer of gated recurrent unit(GRU) is added to the actor-network structure to remember historical environmental states. Subsequently,another GRU is designed as a communication channel in the Comm Net core network layer to refine communication information between UAVs. Finally, the simulation results of the algorithm in two sets of scenarios are given, and the results show that the method has good effectiveness and applicability.
基金the support of the National Natural Science Foundation of China(Grant No.62076204)the Seed Foundation of Innovation and Creation for Graduate Students in Northwestern Polytechnical University(Grant No.CX2020019)in part by the China Postdoctoral Science Foundation(Grants No.2021M700337)。
文摘Improvement of integrated battlefield situational awareness in complex environments involving dynamic factors such as restricted communications and electromagnetic interference(EMI)has become a contentious research problem.In certain mission environments,due to the impact of many interference sources on real-time communication or mission requirements such as the need to implement communication regulations,the mission stages are represented as a dynamic combination of several communication-available and communication-unavailable stages.Furthermore,the data interaction between unmanned aerial vehicles(UAVs)can only be performed in specific communication-available stages.Traditional cooperative search algorithms cannot handle such situations well.To solve this problem,this study constructed a distributed model predictive control(DMPC)architecture for a collaborative control of UAVs and used the Voronoi diagram generation method to re-plan the search areas of all UAVs in real time to avoid repetition of search areas and UAV collisions while improving the search efficiency and safety factor.An attention mechanism ant-colony optimization(AACO)algorithm is proposed for UAV search-control decision planning.The search strategy is adaptively updated by introducing an attention mechanism for regular instruction information,a priori information,and emergent information of the mission to satisfy different search expectations to the maximum extent.Simulation results show that the proposed algorithm achieves better search performance than traditional algorithms in restricted communication constraint scenarios.
基金supported by the Funds for the Central Universities。
文摘To solve the problem that multiple missiles should simultaneously attack unmeasurable maneuvering targets,a guidance law with temporal consistency constraint based on the super-twisting observer is proposed.Firstly,the relative motion equations between multiple missiles and targets are established,and the topological model among multiple agents is considered.Secondly,based on the temporal consistency constraint,a cooperative guidance law for simultaneous arrival with finite-time convergence is derived.Finally,the unknown target maneuver-ing is regarded as bounded interference.Based on the second-order sliding mode theory,a super-twisting sliding mode observer is devised to observe and track the bounded interfer-ence,and the stability of the observer is proved.Compared with the existing research,this approach only needs to obtain the sliding mode variable which simplifies the design process.The simulation results show that the designed cooperative guidance law for maneuvering targets achieves the expected effect.It ensures successful cooperative attacks,even when confronted with strong maneuvering targets.
基金supported by the National Natural Science Foundation of China(72474034,72104034)Humanities and Social Science Fund of the Ministry of Education of China(21YJC630037,22XJC910001)China Postdoctoral Science Foundation(2022T150072)。
文摘To address the charging infrastructure challenges associated with slow electric vehicle(EV)industry growth,this study investigates the collaboration between private charging-pile-sharing platforms struggling with profitability and automotive companies.This collaboration is crucial,as it demands a balanced price and service quality management due to consumer expectations.This paper introduces a Stackelberg game model to explore the relationship between a charging platform and an automotive company.Through numerical analysis,we assess how this cooperation might improve the platform’s efficiency and benefit society,potentially overcoming existing industry hurdles.Our findings indicate that such partnerships could benefit all parties involved,despite possible negative environmental impacts.However,after collaborat-ing,platforms may increase consumer prices and payments to suppliers,potentially lowering service quality for brand-associated consumers due to a compromise between shorter waiting times and service quality.This research offers valu-able insights for stakeholders on the effects of cooperation,enabling better strategic decisions in the EV charging sector.
基金This work was supported by Ph.D.Intelligent Innovation Foundation Project(201-CXCY-A01-08-19-01)Science and Technology on Information System Engineering Laboratory(05202007).
文摘As the unmanned weap system-of systems(UWSoS)becomes complex,the inevitable uncertain interference gradu-ally increases,which leads to a strong emphasis on the resilience of UWSoS.Hence,this paper presents a resilience-driven cooperative reconfiguration strategy to enhance the resilience of UWSoS.First,a unified resilience-driven coopera-tive reconfiguration strategy framework is designed to guide the UWSoS resilience enhancement.Subsequently,a cooperative reconfiguration strategy algorithm is proposed to identify the optimal cooperative reconfiguration sequence,combining the cooperative pair resilience contribution index(CPRCI)and coop-erative pair importance index(CPII).At last,the effectiveness and superiority of the proposed algorithm are demonstrated through various attack scenario simulations that include differ-ent attack modes and intensities.The analysis results can pro-vide a reference for decision-makers to manage UWSoS.
