This paper is concerned with consensus of a secondorder linear time-invariant multi-agent system in the situation that there exists a communication delay among the agents in the network.A proportional-integral consens...This paper is concerned with consensus of a secondorder linear time-invariant multi-agent system in the situation that there exists a communication delay among the agents in the network.A proportional-integral consensus protocol is designed by using delayed and memorized state information.Under the proportional-integral consensus protocol,the consensus problem of the multi-agent system is transformed into the problem of asymptotic stability of the corresponding linear time-invariant time-delay system.Note that the location of the eigenvalues of the corresponding characteristic function of the linear time-invariant time-delay system not only determines the stability of the system,but also plays a critical role in the dynamic performance of the system.In this paper,based on recent results on the distribution of roots of quasi-polynomials,several necessary conditions for Hurwitz stability for a class of quasi-polynomials are first derived.Then allowable regions of consensus protocol parameters are estimated.Some necessary and sufficient conditions for determining effective protocol parameters are provided.The designed protocol can achieve consensus and improve the dynamic performance of the second-order multi-agent system.Moreover,the effects of delays on consensus of systems of harmonic oscillators/double integrators under proportional-integral consensus protocols are investigated.Furthermore,some results on proportional-integral consensus are derived for a class of high-order linear time-invariant multi-agent systems.展开更多
This paper studies the problem of time-varying formation control with finite-time prescribed performance for nonstrict feedback second-order multi-agent systems with unmeasured states and unknown nonlinearities.To eli...This paper studies the problem of time-varying formation control with finite-time prescribed performance for nonstrict feedback second-order multi-agent systems with unmeasured states and unknown nonlinearities.To eliminate nonlinearities,neural networks are applied to approximate the inherent dynamics of the system.In addition,due to the limitations of the actual working conditions,each follower agent can only obtain the locally measurable partial state information of the leader agent.To address this problem,a neural network state observer based on the leader state information is designed.Then,a finite-time prescribed performance adaptive output feedback control strategy is proposed by restricting the sliding mode surface to a prescribed region,which ensures that the closed-loop system has practical finite-time stability and that formation errors of the multi-agent systems converge to the prescribed performance bound in finite time.Finally,a numerical simulation is provided to demonstrate the practicality and effectiveness of the developed algorithm.展开更多
Multi-Agent Reinforcement Learning(MARL)has proven to be successful in cooperative assignments.MARL is used to investigate how autonomous agents with the same interests can connect and act in one team.MARL cooperation...Multi-Agent Reinforcement Learning(MARL)has proven to be successful in cooperative assignments.MARL is used to investigate how autonomous agents with the same interests can connect and act in one team.MARL cooperation scenarios are explored in recreational cooperative augmented reality environments,as well as realworld scenarios in robotics.In this paper,we explore the realm of MARL and its potential applications in cooperative assignments.Our focus is on developing a multi-agent system that can collaborate to attack or defend against enemies and achieve victory withminimal damage.To accomplish this,we utilize the StarCraftMulti-Agent Challenge(SMAC)environment and train four MARL algorithms:Q-learning with Mixtures of Experts(QMIX),Value-DecompositionNetwork(VDN),Multi-agent Proximal PolicyOptimizer(MAPPO),andMulti-Agent Actor Attention Critic(MAA2C).These algorithms allow multiple agents to cooperate in a specific scenario to achieve the targeted mission.Our results show that the QMIX algorithm outperforms the other three algorithms in the attacking scenario,while the VDN algorithm achieves the best results in the defending scenario.Specifically,the VDNalgorithmreaches the highest value of battle wonmean and the lowest value of dead alliesmean.Our research demonstrates the potential forMARL algorithms to be used in real-world applications,such as controllingmultiple robots to provide helpful services or coordinating teams of agents to accomplish tasks that would be impossible for a human to do.The SMAC environment provides a unique opportunity to test and evaluate MARL algorithms in a challenging and dynamic environment,and our results show that these algorithms can be used to achieve victory with minimal damage.展开更多
Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metavers...Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.展开更多
Dear Editor, As a promising multi-agent systems(MASs) operation, autonomous interception has attracted more and more attentions in these years, where defenders prevent intruders from reaching destinations.So far, most...Dear Editor, As a promising multi-agent systems(MASs) operation, autonomous interception has attracted more and more attentions in these years, where defenders prevent intruders from reaching destinations.So far, most of the relevant methods are applied in ideal environments without agent damages. As a remedy, this letter proposes a more realistic interception method for MASs suffered by damages.展开更多
This paper investigates the problem of global/semi-global finite-time consensus for integrator-type multi-agent sys-tems.New hyperbolic tangent function-based protocols are pro-posed to achieve global and semi-global ...This paper investigates the problem of global/semi-global finite-time consensus for integrator-type multi-agent sys-tems.New hyperbolic tangent function-based protocols are pro-posed to achieve global and semi-global finite-time consensus for both single-integrator and double-integrator multi-agent systems with leaderless undirected and leader-following directed commu-nication topologies.These new protocols not only provide an explicit upper-bound estimate for the settling time,but also have a user-prescribed bounded control level.In addition,compared to some existing results based on the saturation function,the pro-posed approach considerably simplifies the protocol design and the stability analysis.Illustrative examples and an application demonstrate the effectiveness of the proposed protocols.展开更多
As an important mechanism in multi-agent interaction,communication can make agents form complex team relationships rather than constitute a simple set of multiple independent agents.However,the existing communication ...As an important mechanism in multi-agent interaction,communication can make agents form complex team relationships rather than constitute a simple set of multiple independent agents.However,the existing communication schemes can bring much timing redundancy and irrelevant messages,which seriously affects their practical application.To solve this problem,this paper proposes a targeted multiagent communication algorithm based on state control(SCTC).The SCTC uses a gating mechanism based on state control to reduce the timing redundancy of communication between agents and determines the interaction relationship between agents and the importance weight of a communication message through a series connection of hard-and self-attention mechanisms,realizing targeted communication message processing.In addition,by minimizing the difference between the fusion message generated from a real communication message of each agent and a fusion message generated from the buffered message,the correctness of the final action choice of the agent is ensured.Our evaluation using a challenging set of Star Craft II benchmarks indicates that the SCTC can significantly improve the learning performance and reduce the communication overhead between agents,thus ensuring better cooperation between agents.展开更多
This paper studies a novel distributed optimization problem that aims to minimize the sum of the non-convex objective functionals of the multi-agent network under privacy protection, which means that the local objecti...This paper studies a novel distributed optimization problem that aims to minimize the sum of the non-convex objective functionals of the multi-agent network under privacy protection, which means that the local objective of each agent is unknown to others. The above problem involves complexity simultaneously in the time and space aspects. Yet existing works about distributed optimization mainly consider privacy protection in the space aspect where the decision variable is a vector with finite dimensions. In contrast, when the time aspect is considered in this paper, the decision variable is a continuous function concerning time. Hence, the minimization of the overall functional belongs to the calculus of variations. Traditional works usually aim to seek the optimal decision function. Due to privacy protection and non-convexity, the Euler-Lagrange equation of the proposed problem is a complicated partial differential equation.Hence, we seek the optimal decision derivative function rather than the decision function. This manner can be regarded as seeking the control input for an optimal control problem, for which we propose a centralized reinforcement learning(RL) framework. In the space aspect, we further present a distributed reinforcement learning framework to deal with the impact of privacy protection. Finally, rigorous theoretical analysis and simulation validate the effectiveness of our framework.展开更多
Model checking is an automated formal verification method to verify whether epistemic multi-agent systems adhere to property specifications.Although there is an extensive literature on qualitative properties such as s...Model checking is an automated formal verification method to verify whether epistemic multi-agent systems adhere to property specifications.Although there is an extensive literature on qualitative properties such as safety and liveness,there is still a lack of quantitative and uncertain property verifications for these systems.In uncertain environments,agents must make judicious decisions based on subjective epistemic.To verify epistemic and measurable properties in multi-agent systems,this paper extends fuzzy computation tree logic by introducing epistemic modalities and proposing a new Fuzzy Computation Tree Logic of Knowledge(FCTLK).We represent fuzzy multi-agent systems as distributed knowledge bases with fuzzy epistemic interpreted systems.In addition,we provide a transformation algorithm from fuzzy epistemic interpreted systems to fuzzy Kripke structures,as well as transformation rules from FCTLK formulas to Fuzzy Computation Tree Logic(FCTL)formulas.Accordingly,we transform the FCTLK model checking problem into the FCTL model checking.This enables the verification of FCTLK formulas by using the fuzzy model checking algorithm of FCTL without additional computational overheads.Finally,we present correctness proofs and complexity analyses of the proposed algorithms.Additionally,we further illustrate the practical application of our approach through an example of a train control system.展开更多
As the number of automated guided vehicles(AGVs)within automated container terminals(ACT)continues to rise,conflicts have becomemore frequent.Addressing point and edge conflicts ofAGVs,amulti-AGVconflict-free path pla...As the number of automated guided vehicles(AGVs)within automated container terminals(ACT)continues to rise,conflicts have becomemore frequent.Addressing point and edge conflicts ofAGVs,amulti-AGVconflict-free path planning model has been formulated to minimize the total path length of AGVs between shore bridges and yards.For larger terminalmaps and complex environments,the grid method is employed to model AGVs’road networks.An improved bounded conflict-based search(IBCBS)algorithmtailored to ACT is proposed,leveraging the binary tree principle to resolve conflicts and employing focal search to expand the search range.Comparative experiments involving 60 AGVs indicate a reduction in computing time by 37.397%to 64.06%while maintaining the over cost within 1.019%.Numerical experiments validate the proposed algorithm’s efficacy in enhancing efficiency and ensuring solution quality.展开更多
Nitrogen-14(^(14)N)overtone(OT)spectroscopy under fast magic angle spinning(MAS)conditions(>60 kHz)has emerged as a powerful technique for observing correlations and distances between ^(14)N and ^(1)H,owing to the ...Nitrogen-14(^(14)N)overtone(OT)spectroscopy under fast magic angle spinning(MAS)conditions(>60 kHz)has emerged as a powerful technique for observing correlations and distances between ^(14)N and ^(1)H,owing to the absence of the first-order quadrupolar broadenings.In addition,^(14)N^(OT) allows selective manipulation of ^(14)N nuclei for each site.Despite extensive theoretical and experimental studies,the spin dynamics of ^(14)N^(OT) remains under debate.In this study,we conducted experimental investigations to assess the spin dynamics of ^(14)N^(OT) using the rotational-echo saturation-pulse double-resonance(RESPDOR)sequence,which monitors population transfer induced by a^(14)N^(OT) pulse.The ^(14)N^(OT) spin dynamics is well represented by a model of a two-energy-level system.Unlike spin-1/2,the maximum excitation efficiency of ^(14)N^(OT) coherences of powdered solids,denoted by p,depends on the radiofrequency field(rf-field)strength due to orientation dependence of effective nutation fields even when pulse lengths are optimized.It is also found that the p factor,contributing to the ^(14)N^(OT) spin dynamics,is nearly independent of the B0 field.Consequently,the filtering efficiency of RESPDOR experiments exhibits negligible dependence on B0 when the ^(14)N^(OT) pulse length is optimized.The study also identifies the optimal experimental conditions for ^(14)N^(OT)/^(1)H RESPDOR correlation experiments.展开更多
This paper studies the connectivity-maintaining consensus of multi-agent systems.Considering the impact of the sensing ranges of agents for connectivity and communication energy consumption,a novel communication manag...This paper studies the connectivity-maintaining consensus of multi-agent systems.Considering the impact of the sensing ranges of agents for connectivity and communication energy consumption,a novel communication management strategy is proposed for multi-agent systems so that the connectivity of the system can be maintained and the communication energy can be saved.In this paper,communication management means a strategy about how the sensing ranges of agents are adjusted in the process of reaching consensus.The proposed communication management in this paper is not coupled with controller but only imposes a constraint for controller,so there is more freedom to develop an appropriate control strategy for achieving consensus.For the multi-agent systems with this novel communication management,a predictive control based strategy is developed for achieving consensus.Simulation results indicate the effectiveness and advantages of our scheme.展开更多
The optimization of multi-zone residential heating,ventilation,and air conditioning(HVAC)control is not an easy task due to its complex dynamic thermal model and the uncertainty of occupant-driven cooling loads.Deep r...The optimization of multi-zone residential heating,ventilation,and air conditioning(HVAC)control is not an easy task due to its complex dynamic thermal model and the uncertainty of occupant-driven cooling loads.Deep reinforcement learning(DRL)methods have recently been proposed to address the HVAC control problem.However,the application of single-agent DRL formulti-zone residential HVAC controlmay lead to non-convergence or slow convergence.In this paper,we propose MAQMC(Multi-Agent deep Q-network for multi-zone residential HVAC Control)to address this challenge with the goal of minimizing energy consumption while maintaining occupants’thermal comfort.MAQMC is divided into MAQMC2(MAQMC with two agents:one agent controls the temperature of each zone,and the other agent controls the humidity of each zone)and MAQMC3(MAQMC with three agents:three agents control the temperature and humidity of three zones,respectively).The experimental results showthatMAQMC3 can reduce energy consumption by 6.27%andMAQMC2 by 3.73%compared with the fixed point;compared with the rule-based,MAQMC3 andMAQMC2 respectively can reduce 61.89%and 59.07%comfort violation.In addition,experiments with different regional weather data demonstrate that the well-trained MAQMC RL agents have the robustness and adaptability to unknown environments.展开更多
This paper considers the mean square output containment control problem for heterogeneous multi-agent systems(MASs)with randomly switching topologies and nonuniform distributed delays.By modeling the switching topolog...This paper considers the mean square output containment control problem for heterogeneous multi-agent systems(MASs)with randomly switching topologies and nonuniform distributed delays.By modeling the switching topologies as a continuous-time Markov process and taking the distributed delays into consideration,a novel distributed containment observer is proposed to estimate the convex hull spanned by the leaders'states.A novel distributed output feedback containment controller is then designed without using the prior knowledge of distributed delays.By constructing a novel switching Lyapunov functional,the output containment control problem is then solved in the sense of mean square under an easily-verifiable sufficient condition.Finally,two numerical examples are given to show the effectiveness of the proposed controller.展开更多
The smart grid utilizes the demand side management technology to motivate energy users towards cutting demand during peak power consumption periods, which greatly improves the operation efficiency of the power grid. H...The smart grid utilizes the demand side management technology to motivate energy users towards cutting demand during peak power consumption periods, which greatly improves the operation efficiency of the power grid. However, as the number of energy users participating in the smart grid continues to increase, the demand side management strategy of individual agent is greatly affected by the dynamic strategies of other agents. In addition, the existing demand side management methods, which need to obtain users’ power consumption information,seriously threaten the users’ privacy. To address the dynamic issue in the multi-microgrid demand side management model, a novel multi-agent reinforcement learning method based on centralized training and decentralized execution paradigm is presented to mitigate the damage of training performance caused by the instability of training experience. In order to protect users’ privacy, we design a neural network with fixed parameters as the encryptor to transform the users’ energy consumption information from low-dimensional to high-dimensional and theoretically prove that the proposed encryptor-based privacy preserving method will not affect the convergence property of the reinforcement learning algorithm. We verify the effectiveness of the proposed demand side management scheme with the real-world energy consumption data of Xi’an, Shaanxi, China. Simulation results show that the proposed method can effectively improve users’ satisfaction while reducing the bill payment compared with traditional reinforcement learning(RL) methods(i.e., deep Q learning(DQN), deep deterministic policy gradient(DDPG),QMIX and multi-agent deep deterministic policy gradient(MADDPG)). The results also demonstrate that the proposed privacy protection scheme can effectively protect users’ privacy while ensuring the performance of the algorithm.展开更多
To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model wit...To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model without boundary constraints are built,and the criteria for successful target capture are given.Then,the cooperative hunting problem of a USV fleet is modeled as a decentralized partially observable Markov decision process(Dec-POMDP),and a distributed partially observable multitarget hunting Proximal Policy Optimization(DPOMH-PPO)algorithm applicable to USVs is proposed.In addition,an observation model,a reward function and the action space applicable to multi-target hunting tasks are designed.To deal with the dynamic change of observational feature dimension input by partially observable systems,a feature embedding block is proposed.By combining the two feature compression methods of column-wise max pooling(CMP)and column-wise average-pooling(CAP),observational feature encoding is established.Finally,the centralized training and decentralized execution framework is adopted to complete the training of hunting strategy.Each USV in the fleet shares the same policy and perform actions independently.Simulation experiments have verified the effectiveness of the DPOMH-PPO algorithm in the test scenarios with different numbers of USVs.Moreover,the advantages of the proposed model are comprehensively analyzed from the aspects of algorithm performance,migration effect in task scenarios and self-organization capability after being damaged,the potential deployment and application of DPOMH-PPO in the real environment is verified.展开更多
The increasing adoption of renewable energy has posed challenges for voltage regulation in power distribution networks.Gridaware energy management,which includes the control of smart inverters and energy management sy...The increasing adoption of renewable energy has posed challenges for voltage regulation in power distribution networks.Gridaware energy management,which includes the control of smart inverters and energy management systems,is a trending way to mitigate this problem.However,existing multi-agent reinforcement learning methods for grid-aware energy management have not sufficiently considered the importance of agent cooperation and the unique characteristics of the grid,which leads to limited performance.In this study,we propose a new approach named multi-agent hierarchical graph attention reinforcement learning framework(MAHGA)to stabilize the voltage.Specifically,under the paradigm of centralized training and decentralized execution,we model the power distribution network as a novel hierarchical graph containing the agent-level topology and the bus-level topology.Then a hierarchical graph attention model is devised to capture the complex correlation between agents.Moreover,we incorporate graph contrastive learning as an auxiliary task in the reinforcement learning process to improve representation learning from graphs.Experiments on several real-world scenarios reveal that our approach achieves the best performance and can reduce the number of voltage violations remarkably.展开更多
基金supported in part by the National Natural Science Foundation of China (NSFC)(61703086, 61773106)the IAPI Fundamental Research Funds (2018ZCX27)
文摘This paper is concerned with consensus of a secondorder linear time-invariant multi-agent system in the situation that there exists a communication delay among the agents in the network.A proportional-integral consensus protocol is designed by using delayed and memorized state information.Under the proportional-integral consensus protocol,the consensus problem of the multi-agent system is transformed into the problem of asymptotic stability of the corresponding linear time-invariant time-delay system.Note that the location of the eigenvalues of the corresponding characteristic function of the linear time-invariant time-delay system not only determines the stability of the system,but also plays a critical role in the dynamic performance of the system.In this paper,based on recent results on the distribution of roots of quasi-polynomials,several necessary conditions for Hurwitz stability for a class of quasi-polynomials are first derived.Then allowable regions of consensus protocol parameters are estimated.Some necessary and sufficient conditions for determining effective protocol parameters are provided.The designed protocol can achieve consensus and improve the dynamic performance of the second-order multi-agent system.Moreover,the effects of delays on consensus of systems of harmonic oscillators/double integrators under proportional-integral consensus protocols are investigated.Furthermore,some results on proportional-integral consensus are derived for a class of high-order linear time-invariant multi-agent systems.
基金the National Natural Science Foundation of China(62203356)Fundamental Research Funds for the Central Universities of China(31020210502002)。
文摘This paper studies the problem of time-varying formation control with finite-time prescribed performance for nonstrict feedback second-order multi-agent systems with unmeasured states and unknown nonlinearities.To eliminate nonlinearities,neural networks are applied to approximate the inherent dynamics of the system.In addition,due to the limitations of the actual working conditions,each follower agent can only obtain the locally measurable partial state information of the leader agent.To address this problem,a neural network state observer based on the leader state information is designed.Then,a finite-time prescribed performance adaptive output feedback control strategy is proposed by restricting the sliding mode surface to a prescribed region,which ensures that the closed-loop system has practical finite-time stability and that formation errors of the multi-agent systems converge to the prescribed performance bound in finite time.Finally,a numerical simulation is provided to demonstrate the practicality and effectiveness of the developed algorithm.
基金supported in part by United States Air Force Research Institute for Tactical Autonomy(RITA)University Affiliated Research Center(UARC)in part by the United States Air Force Office of Scientific Research(AFOSR)Contract FA9550-22-1-0268 awarded to KHA,https://www.afrl.af.mil/AFOSR/The contract is entitled:“Investigating Improving Safety of Autonomous Exploring Intelligent Agents with Human-in-the-Loop Reinforcement Learning,”and in part by Jackson State University.
文摘Multi-Agent Reinforcement Learning(MARL)has proven to be successful in cooperative assignments.MARL is used to investigate how autonomous agents with the same interests can connect and act in one team.MARL cooperation scenarios are explored in recreational cooperative augmented reality environments,as well as realworld scenarios in robotics.In this paper,we explore the realm of MARL and its potential applications in cooperative assignments.Our focus is on developing a multi-agent system that can collaborate to attack or defend against enemies and achieve victory withminimal damage.To accomplish this,we utilize the StarCraftMulti-Agent Challenge(SMAC)environment and train four MARL algorithms:Q-learning with Mixtures of Experts(QMIX),Value-DecompositionNetwork(VDN),Multi-agent Proximal PolicyOptimizer(MAPPO),andMulti-Agent Actor Attention Critic(MAA2C).These algorithms allow multiple agents to cooperate in a specific scenario to achieve the targeted mission.Our results show that the QMIX algorithm outperforms the other three algorithms in the attacking scenario,while the VDN algorithm achieves the best results in the defending scenario.Specifically,the VDNalgorithmreaches the highest value of battle wonmean and the lowest value of dead alliesmean.Our research demonstrates the potential forMARL algorithms to be used in real-world applications,such as controllingmultiple robots to provide helpful services or coordinating teams of agents to accomplish tasks that would be impossible for a human to do.The SMAC environment provides a unique opportunity to test and evaluate MARL algorithms in a challenging and dynamic environment,and our results show that these algorithms can be used to achieve victory with minimal damage.
基金supported in part by NSFC (62102099, U22A2054, 62101594)in part by the Pearl River Talent Recruitment Program (2021QN02S643)+9 种基金Guangzhou Basic Research Program (2023A04J1699)in part by the National Research Foundation, SingaporeInfocomm Media Development Authority under its Future Communications Research Development ProgrammeDSO National Laboratories under the AI Singapore Programme under AISG Award No AISG2-RP-2020-019Energy Research Test-Bed and Industry Partnership Funding Initiative, Energy Grid (EG) 2.0 programmeDesCartes and the Campus for Research Excellence and Technological Enterprise (CREATE) programmeMOE Tier 1 under Grant RG87/22in part by the Singapore University of Technology and Design (SUTD) (SRG-ISTD-2021- 165)in part by the SUTD-ZJU IDEA Grant SUTD-ZJU (VP) 202102in part by the Ministry of Education, Singapore, through its SUTD Kickstarter Initiative (SKI 20210204)。
文摘Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.
基金supported by the Science and Technology Project of State Grid Corporation of China, China (5100202199557A-0-5-ZN)。
文摘Dear Editor, As a promising multi-agent systems(MASs) operation, autonomous interception has attracted more and more attentions in these years, where defenders prevent intruders from reaching destinations.So far, most of the relevant methods are applied in ideal environments without agent damages. As a remedy, this letter proposes a more realistic interception method for MASs suffered by damages.
基金supported by the National Natural Science Foundation of China(62073019)。
文摘This paper investigates the problem of global/semi-global finite-time consensus for integrator-type multi-agent sys-tems.New hyperbolic tangent function-based protocols are pro-posed to achieve global and semi-global finite-time consensus for both single-integrator and double-integrator multi-agent systems with leaderless undirected and leader-following directed commu-nication topologies.These new protocols not only provide an explicit upper-bound estimate for the settling time,but also have a user-prescribed bounded control level.In addition,compared to some existing results based on the saturation function,the pro-posed approach considerably simplifies the protocol design and the stability analysis.Illustrative examples and an application demonstrate the effectiveness of the proposed protocols.
文摘As an important mechanism in multi-agent interaction,communication can make agents form complex team relationships rather than constitute a simple set of multiple independent agents.However,the existing communication schemes can bring much timing redundancy and irrelevant messages,which seriously affects their practical application.To solve this problem,this paper proposes a targeted multiagent communication algorithm based on state control(SCTC).The SCTC uses a gating mechanism based on state control to reduce the timing redundancy of communication between agents and determines the interaction relationship between agents and the importance weight of a communication message through a series connection of hard-and self-attention mechanisms,realizing targeted communication message processing.In addition,by minimizing the difference between the fusion message generated from a real communication message of each agent and a fusion message generated from the buffered message,the correctness of the final action choice of the agent is ensured.Our evaluation using a challenging set of Star Craft II benchmarks indicates that the SCTC can significantly improve the learning performance and reduce the communication overhead between agents,thus ensuring better cooperation between agents.
基金supported in part by the National Natural Science Foundation of China(NSFC)(61773260)the Ministry of Science and Technology (2018YFB130590)。
文摘This paper studies a novel distributed optimization problem that aims to minimize the sum of the non-convex objective functionals of the multi-agent network under privacy protection, which means that the local objective of each agent is unknown to others. The above problem involves complexity simultaneously in the time and space aspects. Yet existing works about distributed optimization mainly consider privacy protection in the space aspect where the decision variable is a vector with finite dimensions. In contrast, when the time aspect is considered in this paper, the decision variable is a continuous function concerning time. Hence, the minimization of the overall functional belongs to the calculus of variations. Traditional works usually aim to seek the optimal decision function. Due to privacy protection and non-convexity, the Euler-Lagrange equation of the proposed problem is a complicated partial differential equation.Hence, we seek the optimal decision derivative function rather than the decision function. This manner can be regarded as seeking the control input for an optimal control problem, for which we propose a centralized reinforcement learning(RL) framework. In the space aspect, we further present a distributed reinforcement learning framework to deal with the impact of privacy protection. Finally, rigorous theoretical analysis and simulation validate the effectiveness of our framework.
基金The work is partially supported by Natural Science Foundation of Ningxia(Grant No.AAC03300)National Natural Science Foundation of China(Grant No.61962001)Graduate Innovation Project of North Minzu University(Grant No.YCX23152).
文摘Model checking is an automated formal verification method to verify whether epistemic multi-agent systems adhere to property specifications.Although there is an extensive literature on qualitative properties such as safety and liveness,there is still a lack of quantitative and uncertain property verifications for these systems.In uncertain environments,agents must make judicious decisions based on subjective epistemic.To verify epistemic and measurable properties in multi-agent systems,this paper extends fuzzy computation tree logic by introducing epistemic modalities and proposing a new Fuzzy Computation Tree Logic of Knowledge(FCTLK).We represent fuzzy multi-agent systems as distributed knowledge bases with fuzzy epistemic interpreted systems.In addition,we provide a transformation algorithm from fuzzy epistemic interpreted systems to fuzzy Kripke structures,as well as transformation rules from FCTLK formulas to Fuzzy Computation Tree Logic(FCTL)formulas.Accordingly,we transform the FCTLK model checking problem into the FCTL model checking.This enables the verification of FCTLK formulas by using the fuzzy model checking algorithm of FCTL without additional computational overheads.Finally,we present correctness proofs and complexity analyses of the proposed algorithms.Additionally,we further illustrate the practical application of our approach through an example of a train control system.
基金supported by National Natural Science Foundation of China(No.62073212)Shanghai Science and Technology Commission(No.23ZR1426600).
文摘As the number of automated guided vehicles(AGVs)within automated container terminals(ACT)continues to rise,conflicts have becomemore frequent.Addressing point and edge conflicts ofAGVs,amulti-AGVconflict-free path planning model has been formulated to minimize the total path length of AGVs between shore bridges and yards.For larger terminalmaps and complex environments,the grid method is employed to model AGVs’road networks.An improved bounded conflict-based search(IBCBS)algorithmtailored to ACT is proposed,leveraging the binary tree principle to resolve conflicts and employing focal search to expand the search range.Comparative experiments involving 60 AGVs indicate a reduction in computing time by 37.397%to 64.06%while maintaining the over cost within 1.019%.Numerical experiments validate the proposed algorithm’s efficacy in enhancing efficiency and ensuring solution quality.
文摘Nitrogen-14(^(14)N)overtone(OT)spectroscopy under fast magic angle spinning(MAS)conditions(>60 kHz)has emerged as a powerful technique for observing correlations and distances between ^(14)N and ^(1)H,owing to the absence of the first-order quadrupolar broadenings.In addition,^(14)N^(OT) allows selective manipulation of ^(14)N nuclei for each site.Despite extensive theoretical and experimental studies,the spin dynamics of ^(14)N^(OT) remains under debate.In this study,we conducted experimental investigations to assess the spin dynamics of ^(14)N^(OT) using the rotational-echo saturation-pulse double-resonance(RESPDOR)sequence,which monitors population transfer induced by a^(14)N^(OT) pulse.The ^(14)N^(OT) spin dynamics is well represented by a model of a two-energy-level system.Unlike spin-1/2,the maximum excitation efficiency of ^(14)N^(OT) coherences of powdered solids,denoted by p,depends on the radiofrequency field(rf-field)strength due to orientation dependence of effective nutation fields even when pulse lengths are optimized.It is also found that the p factor,contributing to the ^(14)N^(OT) spin dynamics,is nearly independent of the B0 field.Consequently,the filtering efficiency of RESPDOR experiments exhibits negligible dependence on B0 when the ^(14)N^(OT) pulse length is optimized.The study also identifies the optimal experimental conditions for ^(14)N^(OT)/^(1)H RESPDOR correlation experiments.
基金supported by the National Key Research and Development Program of China(2018AAA0101701)the National Natural Science Foundation of China(62173224,61833012)。
文摘This paper studies the connectivity-maintaining consensus of multi-agent systems.Considering the impact of the sensing ranges of agents for connectivity and communication energy consumption,a novel communication management strategy is proposed for multi-agent systems so that the connectivity of the system can be maintained and the communication energy can be saved.In this paper,communication management means a strategy about how the sensing ranges of agents are adjusted in the process of reaching consensus.The proposed communication management in this paper is not coupled with controller but only imposes a constraint for controller,so there is more freedom to develop an appropriate control strategy for achieving consensus.For the multi-agent systems with this novel communication management,a predictive control based strategy is developed for achieving consensus.Simulation results indicate the effectiveness and advantages of our scheme.
基金supported by Primary Research and Development Plan of China(No.2020YFC2006602)National Natural Science Foundation of China(Nos.62072324,61876217,61876121,61772357)+2 种基金University Natural Science Foundation of Jiangsu Province(No.21KJA520005)Primary Research and Development Plan of Jiangsu Province(No.BE2020026)Natural Science Foundation of Jiangsu Province(No.BK20190942).
文摘The optimization of multi-zone residential heating,ventilation,and air conditioning(HVAC)control is not an easy task due to its complex dynamic thermal model and the uncertainty of occupant-driven cooling loads.Deep reinforcement learning(DRL)methods have recently been proposed to address the HVAC control problem.However,the application of single-agent DRL formulti-zone residential HVAC controlmay lead to non-convergence or slow convergence.In this paper,we propose MAQMC(Multi-Agent deep Q-network for multi-zone residential HVAC Control)to address this challenge with the goal of minimizing energy consumption while maintaining occupants’thermal comfort.MAQMC is divided into MAQMC2(MAQMC with two agents:one agent controls the temperature of each zone,and the other agent controls the humidity of each zone)and MAQMC3(MAQMC with three agents:three agents control the temperature and humidity of three zones,respectively).The experimental results showthatMAQMC3 can reduce energy consumption by 6.27%andMAQMC2 by 3.73%compared with the fixed point;compared with the rule-based,MAQMC3 andMAQMC2 respectively can reduce 61.89%and 59.07%comfort violation.In addition,experiments with different regional weather data demonstrate that the well-trained MAQMC RL agents have the robustness and adaptability to unknown environments.
文摘This paper considers the mean square output containment control problem for heterogeneous multi-agent systems(MASs)with randomly switching topologies and nonuniform distributed delays.By modeling the switching topologies as a continuous-time Markov process and taking the distributed delays into consideration,a novel distributed containment observer is proposed to estimate the convex hull spanned by the leaders'states.A novel distributed output feedback containment controller is then designed without using the prior knowledge of distributed delays.By constructing a novel switching Lyapunov functional,the output containment control problem is then solved in the sense of mean square under an easily-verifiable sufficient condition.Finally,two numerical examples are given to show the effectiveness of the proposed controller.
基金supported in part by the National Science Foundation of China (61973247, 61673315, 62173268)the Key Research and Development Program of Shaanxi (2022GY-033)+2 种基金the Nationa Postdoctoral Innovative Talents Support Program of China (BX20200272)the Key Program of the National Natural Science Foundation of China (61833015)the Fundamental Research Funds for the Central Universities (xzy022021050)。
文摘The smart grid utilizes the demand side management technology to motivate energy users towards cutting demand during peak power consumption periods, which greatly improves the operation efficiency of the power grid. However, as the number of energy users participating in the smart grid continues to increase, the demand side management strategy of individual agent is greatly affected by the dynamic strategies of other agents. In addition, the existing demand side management methods, which need to obtain users’ power consumption information,seriously threaten the users’ privacy. To address the dynamic issue in the multi-microgrid demand side management model, a novel multi-agent reinforcement learning method based on centralized training and decentralized execution paradigm is presented to mitigate the damage of training performance caused by the instability of training experience. In order to protect users’ privacy, we design a neural network with fixed parameters as the encryptor to transform the users’ energy consumption information from low-dimensional to high-dimensional and theoretically prove that the proposed encryptor-based privacy preserving method will not affect the convergence property of the reinforcement learning algorithm. We verify the effectiveness of the proposed demand side management scheme with the real-world energy consumption data of Xi’an, Shaanxi, China. Simulation results show that the proposed method can effectively improve users’ satisfaction while reducing the bill payment compared with traditional reinforcement learning(RL) methods(i.e., deep Q learning(DQN), deep deterministic policy gradient(DDPG),QMIX and multi-agent deep deterministic policy gradient(MADDPG)). The results also demonstrate that the proposed privacy protection scheme can effectively protect users’ privacy while ensuring the performance of the algorithm.
基金financial support from National Natural Science Foundation of China(Grant No.61601491)Natural Science Foundation of Hubei Province,China(Grant No.2018CFC865)Military Research Project of China(-Grant No.YJ2020B117)。
文摘To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model without boundary constraints are built,and the criteria for successful target capture are given.Then,the cooperative hunting problem of a USV fleet is modeled as a decentralized partially observable Markov decision process(Dec-POMDP),and a distributed partially observable multitarget hunting Proximal Policy Optimization(DPOMH-PPO)algorithm applicable to USVs is proposed.In addition,an observation model,a reward function and the action space applicable to multi-target hunting tasks are designed.To deal with the dynamic change of observational feature dimension input by partially observable systems,a feature embedding block is proposed.By combining the two feature compression methods of column-wise max pooling(CMP)and column-wise average-pooling(CAP),observational feature encoding is established.Finally,the centralized training and decentralized execution framework is adopted to complete the training of hunting strategy.Each USV in the fleet shares the same policy and perform actions independently.Simulation experiments have verified the effectiveness of the DPOMH-PPO algorithm in the test scenarios with different numbers of USVs.Moreover,the advantages of the proposed model are comprehensively analyzed from the aspects of algorithm performance,migration effect in task scenarios and self-organization capability after being damaged,the potential deployment and application of DPOMH-PPO in the real environment is verified.
基金supported by National Key R&D Program of China under Grant No.2022ZD0119802National Natural Science Foundation of China under Grant No.61836011.
文摘The increasing adoption of renewable energy has posed challenges for voltage regulation in power distribution networks.Gridaware energy management,which includes the control of smart inverters and energy management systems,is a trending way to mitigate this problem.However,existing multi-agent reinforcement learning methods for grid-aware energy management have not sufficiently considered the importance of agent cooperation and the unique characteristics of the grid,which leads to limited performance.In this study,we propose a new approach named multi-agent hierarchical graph attention reinforcement learning framework(MAHGA)to stabilize the voltage.Specifically,under the paradigm of centralized training and decentralized execution,we model the power distribution network as a novel hierarchical graph containing the agent-level topology and the bus-level topology.Then a hierarchical graph attention model is devised to capture the complex correlation between agents.Moreover,we incorporate graph contrastive learning as an auxiliary task in the reinforcement learning process to improve representation learning from graphs.Experiments on several real-world scenarios reveal that our approach achieves the best performance and can reduce the number of voltage violations remarkably.