This paper delves into the problem of optimal placement conditions for a group of agents collaboratively localizing a target using range-only or bearing-only measurements.The challenge in this study stems from the unc...This paper delves into the problem of optimal placement conditions for a group of agents collaboratively localizing a target using range-only or bearing-only measurements.The challenge in this study stems from the uncertainty associated with the positions of the agents,which may experience drift or disturbances during the target localization process.Initially,we derive the Cramer-Rao lower bound(CRLB)of the target position as the primary analytical metric.Subsequently,we establish the necessary and sufficient conditions for the optimal placement of agents.Based on these conditions,we analyze the maximal allowable agent position error for an expected mean squared error(MSE),providing valuable guidance for the selection of agent positioning sensors.The analytical findings are further validated through simulation experiments.展开更多
This paper researches some problems in complex formation for multi-agents,in which two matrices are proposed to record the formation.The pattern matrix is used to describe the pattern of the formation;meanwhile,the lo...This paper researches some problems in complex formation for multi-agents,in which two matrices are proposed to record the formation.The pattern matrix is used to describe the pattern of the formation;meanwhile,the location matrix is used to record the location of each agent.Thus,all desired positions of each agent will be obtained by geometrical relationship on the basis of two matrices above.In addition a self-adaptation flocking algorithm is proposed to control all agents to form a desired formation and avoid obstacles.The main idea is as follows:agents will form a desired formation through the method of formation control when far away from obstacles;otherwise,agents will freely fly to pass through the area of obstacles.In the simulation,three scenarios are designed to verify the effectiveness of our method.The results show that our method also can be applied in three dimensions.All agents will form a stable formation and keep the same velocity at last.展开更多
Aiming for the coordinated motion and cooperative control of multi-agents in a non-rectangular bounded space, a velocity consensus algorithm for the agents with double- integrator dynamics is presented. The traditiona...Aiming for the coordinated motion and cooperative control of multi-agents in a non-rectangular bounded space, a velocity consensus algorithm for the agents with double- integrator dynamics is presented. The traditional consensus algorithm for bounded space is only applicable to rectangular bouncing boundaries, not suitable for non-rectangular space. In order to extend the previous consensus algorithm to the non- rectangular space, the concept of mirrored velocity is introduced, which can convert the discontinuous real velocity to continuous mirrored velocity, and expand a bounded space into an infinite space. Using the consensus algorithm, it is found that the mirrored velocities of multi-agents asymptotically converge to the same values. Because each mirrored velocity points to a unique velocity in real space, it can be concluded that the real velocities of multi-agents also asymptotically converge. Finally, the effectiveness of the proposed consensus algorithm is examined by theoretical proof and numerical simulations. Moreover, an experiment is performed with the algorithm in a real multi-robot system successfully.展开更多
This paper discusses the progress of computer integrated processing （CIPS） of coal-preparation and then preserits an intelligence controlled production-process, device-maintenance and production-management system of...This paper discusses the progress of computer integrated processing （CIPS） of coal-preparation and then preserits an intelligence controlled production-process, device-maintenance and production-management system of coal- preparation based on multi-agents （IICMMS-CP）. The construction of the IICMMS-CP, the distributed network control system based on live intelligence control stations and the strategy of implementing distributed intelligence control system are studied in order to overcome the disadvantages brought about by the wide use of the PLC system by coaipreparation plants. The software frame, based on a Multi-Agent Intelligence Control and Maintenance Management integrated system, is studied and the implemention methods of IICMMS-CP are discussed. The characteristics of distributed architecture, cooperation and parallel computing meet the needs of integrated control of coal-preparation plants with large-scale spatial production distribution, densely-related processes and complex systems. Its application further improves the reliability and precision of process control, accuracy of fault identification and intelligence of production adjustment, establishes a technical basis for system integration and flexible production. The main function of the system has been tested in a coal-preparation plant to good effect in stabilizing product quality, improving efficiency and reducing consumption.展开更多
In this paper,the bipartite consensus problem is studied for a class of uncertain high-order nonlinear multi-agent systems.A signed digraph is presented to describe the collaborative and competitive interactions among...In this paper,the bipartite consensus problem is studied for a class of uncertain high-order nonlinear multi-agent systems.A signed digraph is presented to describe the collaborative and competitive interactions among agents.For each agent with lower triangular structure,a time-varying gain compensator is first designed by relative output information of neighboring agents.Subsequently,a distributed controller with dynamic event-triggered mechanism is proposed to drive the bipartite consensus error to zero.It is worth noting that an internal dynamic variable is introduced in triggering function,which plays an essential role in excluding the Zeno behavior and reducing energy consumption.Furthermore,the dynamic event-triggered control protocol is developed for upper triangular multi-agent systems to realize the bipartite consensus without Zeno behavior.Finally,simulation examples are provided to illustrate the effectiveness of the presented results.展开更多
In these latter days software agents are used for the development and implementation of intellectual decision support systems. In order to implement intelligence in a system some or several dozen of software agents ar...In these latter days software agents are used for the development and implementation of intellectual decision support systems. In order to implement intelligence in a system some or several dozen of software agents are used and the made system becomes multi-agent. For the development of these systems a set of methodologies, i.e., the sequence of consequent steps of analysis, designing and implementation, is offered. The carried out analysis of the methodologies showed that as a rule they are limited by the spectrum of their pending problem （within the pales of the requirements of specific applied task, within the pales of the possibilities of technical implementation） or within the pales of amount of detail. The variety of methodologies is influenced by the fact that for the development of these systems the requirements and attitudes are offered by the specialists of related spheres such as software, numeral intellect engineers. In the course of the development of hardware and software appeared possibilities to implement mobile multi-agents systems, however, there is no one united mobile multi-agent systems design methodology, whereas existing systems are underdeveloped and their number is small. In this article we introduce the course of the designing of an intellectual real time multi-agent investment management decision support information system adapting and combining some methodologies where the choice to use either communicating or mobile agents is the question of rather technical implementation than methodological. In the article we introduce two ways of system implementation by JADE platform： the first one-using communicating agents, and the second one-using mobile agents.展开更多
This paper deals with the distributed consensus problem of high-order multi-agent systems with nonlinear dynamics subject to external disturbances. The network topology is assumed to be a fixed undirected graph. Some ...This paper deals with the distributed consensus problem of high-order multi-agent systems with nonlinear dynamics subject to external disturbances. The network topology is assumed to be a fixed undirected graph. Some sufficient conditions are derived, under which the consensus can be achieved with a prescribed norm bound. It is shown that the parameter matrix in the consensus algorithm can be designed by solving two linear matrix inequalities (LMIs). In particular, if the nonzero eigenvalues of the laplacian matrix ac-cording to the network topology are identical, the parameter matrix in the consensus algorithm can be de-signed by solving one LMI. A numerical example is given to illustrate the proposed results.展开更多
This paper addresses the synchronization of follower agents’state vectors with that of a leader in high-order nonlinear multi-agent systems.The proposed low-complexity control scheme employs high-gain observers to es...This paper addresses the synchronization of follower agents’state vectors with that of a leader in high-order nonlinear multi-agent systems.The proposed low-complexity control scheme employs high-gain observers to estimate higher-order synchronization errors,enabling the controller to rely solely on relative output measurements.This approach significantly reduces the dependence on full-state information,which is often infeasible or costly in practical engineering applications.An output feedback control strategy is developed to overcome these limitations while ensuring robust and effective synchronization.Simulation results are provided to demonstrate the effectiveness of the proposed approach and validate the theoretical findings.展开更多
Addressing optimal confrontation methods in multi-agent attack-defense scenarios is a complex challenge.Multi-Agent Reinforcement Learning(MARL)provides an effective framework for tackling sequential decision-making p...Addressing optimal confrontation methods in multi-agent attack-defense scenarios is a complex challenge.Multi-Agent Reinforcement Learning(MARL)provides an effective framework for tackling sequential decision-making problems,significantly enhancing swarm intelligence in maneuvering.However,applying MARL to unmanned swarms presents two primary challenges.First,defensive agents must balance autonomy with collaboration under limited perception while coordinating against adversaries.Second,current algorithms aim to maximize global or individual rewards,making them sensitive to fluctuations in enemy strategies and environmental changes,especially when rewards are sparse.To tackle these issues,we propose an algorithm of MultiAgent Reinforcement Learning with Layered Autonomy and Collaboration(MARL-LAC)for collaborative confrontations.This algorithm integrates dual twin Critics to mitigate the high variance associated with policy gradients.Furthermore,MARL-LAC employs layered autonomy and collaboration to address multi-objective problems,specifically learning a global reward function for the swarm alongside local reward functions for individual defensive agents.Experimental results demonstrate that MARL-LAC enhances decision-making and collaborative behaviors among agents,outperforming the existing algorithms and emphasizing the importance of layered autonomy and collaboration in multi-agent systems.The observed adversarial behaviors demonstrate that agents using MARL-LAC effectively maintain cohesive formations that conceal their intentions by confusing the offensive agent while successfully encircling the target.展开更多
In recent years,researchers have leveraged single-agent reinforcement learning to boost educational outcomes and deliver personalized interventions;yet this paradigm provides no capacity for inter-agent interaction.Mu...In recent years,researchers have leveraged single-agent reinforcement learning to boost educational outcomes and deliver personalized interventions;yet this paradigm provides no capacity for inter-agent interaction.Multi-agent reinforcement learning(MARL)overcomes this limitation by allowing several agents to learn simultaneously within a shared environment,each choosing actions that maximize its own or the group's rewards.By explicitly modeling and exploiting agent-to-agent dynamics,MARL can align those interactions with pedagogical goals such as peer tutoring,collaborative problem-solving,or gamified competition,thus opening richer avenues for adaptive and socially informed learning experiences.This survey investigates the impact of MARL on educational outcomes by examining evidence of its effectiveness in enhancing learner performance,engagement,equity,and reducing teacher workload compared to single agent or traditional approaches.It explores the educational domains and pedagogical problems addressed by MARL,identifies the algorithmic families used,and analyzes their influence on learning.The review also assesses experimental settings and evaluation metrics to determine ecological validity,and outlines current challenges and future research directions in applying MARL to education.展开更多
This paper presents an adaptive multi-agent coordination(AMAC)strategy suitable for complex scenarios,which only requires information exchange between neighbouring robots.Unlike traditional multi-agent coordination me...This paper presents an adaptive multi-agent coordination(AMAC)strategy suitable for complex scenarios,which only requires information exchange between neighbouring robots.Unlike traditional multi-agent coordination methods that are solved by neural dynamics,the proposed strategy displays greater flexibility,adaptability and scalability.Furthermore,the proposed AMAC strategy is reconstructed as a time-varying complex-valued matrix equation.By introducing a dynamic error function,a fixed-time convergent zeroing neural network(FTCZNN)model is designed for the online solution of the AMAC strategy,with its convergence time upper bound derived theoretically.Finally,the effectiveness and applicability of the coordination control method are demonstrated by numerical simulations and physical experiments.Numerical results indicate that this method can reduce the formation error to the order of 10^(-6)within 1.8 s.展开更多
To maximize the profits of power grid operators(GOs),load aggregators(LAs)and electricity customers(ECs),this paper proposes a hierarchical demand response(HDR)framework that considers competing interaction based on m...To maximize the profits of power grid operators(GOs),load aggregators(LAs)and electricity customers(ECs),this paper proposes a hierarchical demand response(HDR)framework that considers competing interaction based on multiagent deep deterministic policy gradient(MaDDPG).The ECs are divided into conventional ECs and the electric vehicles(EVs)which are managed by ECs agent(ECA)and EV agent(EVA)to exploit the flexibility of the HDR framework.Thus,the HDR is a tri-layer model determined by five types of agents engaging in competing interaction to maximize their own profits.To address the limitations of mathematical expression and participation scale in the Stackelberg game within the HDR model,a dynamic interaction mechanism is adopted.Moreover,to tackle the HDR involving various entities,the MaDDPG develops multiple agents to simulation the dynamic competing interactions between each subject as well as solve the problem of continuous action control.Furthermore,MaDDPG adopts soft target update and priority experience replay method to ensure stable and effective training,and makes the exploration strategy comprehensive by using exploration noise.Simulation studies are conducted to verify the performance of the MaDDPG with dynamic interaction mechanism in dealing with multilayer multi-agent continuous action control,compared to the double deep Q network(DDQN),deep Q network(DQN)and dueling DQN.Additionally,comparisons among the proposed HDR with the price based DR(PBDR)and incentive based DR(IBDR)are analyzed to investigate the flexibility of the HDR.展开更多
This paper investigates the consensus tracking control problem for high order nonlinear multi-agent systems subject to non-affine faults,partial measurable states,uncertain control coefficients,and unknown external di...This paper investigates the consensus tracking control problem for high order nonlinear multi-agent systems subject to non-affine faults,partial measurable states,uncertain control coefficients,and unknown external disturbances.Under the directed topology conditions,an observer-based finite-time control strategy based on adaptive backstepping and is proposed,in which a neural network-based state observer is employed to approximate the unmeasurable system state variables.To address the complexity explosion problem associated with the backstepping method,a finite-time command filter is incorporated,with error compensation signals designed to mitigate the filter-induced errors.Additionally,the Butterworth low-pass filter is introduced to avoid the algebraic ring problem in the design of the controller.The finite-time stability of the closed-loop system is rigorously analyzed with the finite-time Lyapunov stability criterion,validating that all closed-loop signals of the system remain bounded within a finite time.Finally,the effectiveness of the proposed control strategy is verified through a simulation example.展开更多
This paper presents Dual Adaptive Neural Topology(Dual ANT),a distributed dual-network metaadaptive framework that enhances ant-colony-based multi-agent coordination with online introspection,adaptive parameter contro...This paper presents Dual Adaptive Neural Topology(Dual ANT),a distributed dual-network metaadaptive framework that enhances ant-colony-based multi-agent coordination with online introspection,adaptive parameter control,and privacy-preserving interactions.This approach improves standard Ant Colony Optimization(ACO)with two lightweight neural components:a forward network that estimates swarm efficiency in real time and an inverse network that converts these descriptors into parameter adaptations.To preserve the privacy of individual trajectories in shared pheromone maps,we introduce a locally differentially private pheromone update mechanism that adds calibrated noise to each agent’s pheromone deposit while preserving the efficacy of the global pheromone signal.The resulting systemenables agents to dynamically and autonomously adapt their coordination strategies under challenging and dynamic conditions,including varying obstacle layouts,uncertain target locations,and time-varying disturbances.Extensive simulations of large grid-based search tasks demonstrated that Dual ANT achieved faster convergence,higher robustness,and improved scalability compared to advanced baselines such asMulti-StrategyACO and Hierarchical ACO.The meta-adaptive feedback loop compensates for the performance degradation caused by privacy noise and prevents premature stagnation by triggering Levy flight exploration only when necessary.展开更多
Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal ...Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal alignment,temporal consistency,and robust handling of noisy or incomplete inputs across multiple modalities.We propose Multi Agent-Chain of Thought(CoT),a novel multi-agent chain-of-thought reasoning framework where specialized agents for text,vision,and speech modalities collaboratively construct shared reasoning traces through inter-agent message passing and consensus voting mechanisms.Our architecture incorporates self-reflection modules,conflict resolution protocols,and dynamic rationale alignment to enhance consistency,factual accuracy,and user engagement.The framework employs a hierarchical attention mechanism with cross-modal fusion and implements adaptive reasoning depth based on dialogue complexity.Comprehensive evaluations on Situated Interactive Multi-Modal Conversations(SIMMC)2.0,VisDial v1.0,and newly introduced challenging scenarios demonstrate statistically significant improvements in grounding accuracy(p<0.01),chain-of-thought interpretability,and robustness to adversarial inputs compared to state-of-the-art monolithic transformer baselines and existing multi-agent approaches.展开更多
文摘This paper delves into the problem of optimal placement conditions for a group of agents collaboratively localizing a target using range-only or bearing-only measurements.The challenge in this study stems from the uncertainty associated with the positions of the agents,which may experience drift or disturbances during the target localization process.Initially,we derive the Cramer-Rao lower bound(CRLB)of the target position as the primary analytical metric.Subsequently,we establish the necessary and sufficient conditions for the optimal placement of agents.Based on these conditions,we analyze the maximal allowable agent position error for an expected mean squared error(MSE),providing valuable guidance for the selection of agent positioning sensors.The analytical findings are further validated through simulation experiments.
文摘This paper researches some problems in complex formation for multi-agents,in which two matrices are proposed to record the formation.The pattern matrix is used to describe the pattern of the formation;meanwhile,the location matrix is used to record the location of each agent.Thus,all desired positions of each agent will be obtained by geometrical relationship on the basis of two matrices above.In addition a self-adaptation flocking algorithm is proposed to control all agents to form a desired formation and avoid obstacles.The main idea is as follows:agents will form a desired formation through the method of formation control when far away from obstacles;otherwise,agents will freely fly to pass through the area of obstacles.In the simulation,three scenarios are designed to verify the effectiveness of our method.The results show that our method also can be applied in three dimensions.All agents will form a stable formation and keep the same velocity at last.
基金The National Natural Science Foundation of China(No.61273110)the Specialized Fund for the Doctoral Program of Higher Education(No.20130092130002)
文摘Aiming for the coordinated motion and cooperative control of multi-agents in a non-rectangular bounded space, a velocity consensus algorithm for the agents with double- integrator dynamics is presented. The traditional consensus algorithm for bounded space is only applicable to rectangular bouncing boundaries, not suitable for non-rectangular space. In order to extend the previous consensus algorithm to the non- rectangular space, the concept of mirrored velocity is introduced, which can convert the discontinuous real velocity to continuous mirrored velocity, and expand a bounded space into an infinite space. Using the consensus algorithm, it is found that the mirrored velocities of multi-agents asymptotically converge to the same values. Because each mirrored velocity points to a unique velocity in real space, it can be concluded that the real velocities of multi-agents also asymptotically converge. Finally, the effectiveness of the proposed consensus algorithm is examined by theoretical proof and numerical simulations. Moreover, an experiment is performed with the algorithm in a real multi-robot system successfully.
文摘This paper discusses the progress of computer integrated processing （CIPS） of coal-preparation and then preserits an intelligence controlled production-process, device-maintenance and production-management system of coal- preparation based on multi-agents （IICMMS-CP）. The construction of the IICMMS-CP, the distributed network control system based on live intelligence control stations and the strategy of implementing distributed intelligence control system are studied in order to overcome the disadvantages brought about by the wide use of the PLC system by coaipreparation plants. The software frame, based on a Multi-Agent Intelligence Control and Maintenance Management integrated system, is studied and the implemention methods of IICMMS-CP are discussed. The characteristics of distributed architecture, cooperation and parallel computing meet the needs of integrated control of coal-preparation plants with large-scale spatial production distribution, densely-related processes and complex systems. Its application further improves the reliability and precision of process control, accuracy of fault identification and intelligence of production adjustment, establishes a technical basis for system integration and flexible production. The main function of the system has been tested in a coal-preparation plant to good effect in stabilizing product quality, improving efficiency and reducing consumption.
基金This work was supported by the National Natural Science Foundation of China(Nos.61973189,62073190)the Research Fund for the Taishan Scholar Project of Shandong Province of China(No.ts20190905)the Natural Science Foundation of Shandong Province of China(No.ZR2020ZD25).
文摘In this paper,the bipartite consensus problem is studied for a class of uncertain high-order nonlinear multi-agent systems.A signed digraph is presented to describe the collaborative and competitive interactions among agents.For each agent with lower triangular structure,a time-varying gain compensator is first designed by relative output information of neighboring agents.Subsequently,a distributed controller with dynamic event-triggered mechanism is proposed to drive the bipartite consensus error to zero.It is worth noting that an internal dynamic variable is introduced in triggering function,which plays an essential role in excluding the Zeno behavior and reducing energy consumption.Furthermore,the dynamic event-triggered control protocol is developed for upper triangular multi-agent systems to realize the bipartite consensus without Zeno behavior.Finally,simulation examples are provided to illustrate the effectiveness of the presented results.
文摘In these latter days software agents are used for the development and implementation of intellectual decision support systems. In order to implement intelligence in a system some or several dozen of software agents are used and the made system becomes multi-agent. For the development of these systems a set of methodologies, i.e., the sequence of consequent steps of analysis, designing and implementation, is offered. The carried out analysis of the methodologies showed that as a rule they are limited by the spectrum of their pending problem （within the pales of the requirements of specific applied task, within the pales of the possibilities of technical implementation） or within the pales of amount of detail. The variety of methodologies is influenced by the fact that for the development of these systems the requirements and attitudes are offered by the specialists of related spheres such as software, numeral intellect engineers. In the course of the development of hardware and software appeared possibilities to implement mobile multi-agents systems, however, there is no one united mobile multi-agent systems design methodology, whereas existing systems are underdeveloped and their number is small. In this article we introduce the course of the designing of an intellectual real time multi-agent investment management decision support information system adapting and combining some methodologies where the choice to use either communicating or mobile agents is the question of rather technical implementation than methodological. In the article we introduce two ways of system implementation by JADE platform： the first one-using communicating agents, and the second one-using mobile agents.
文摘This paper deals with the distributed consensus problem of high-order multi-agent systems with nonlinear dynamics subject to external disturbances. The network topology is assumed to be a fixed undirected graph. Some sufficient conditions are derived, under which the consensus can be achieved with a prescribed norm bound. It is shown that the parameter matrix in the consensus algorithm can be designed by solving two linear matrix inequalities (LMIs). In particular, if the nonzero eigenvalues of the laplacian matrix ac-cording to the network topology are identical, the parameter matrix in the consensus algorithm can be de-signed by solving one LMI. A numerical example is given to illustrate the proposed results.
文摘This paper addresses the synchronization of follower agents’state vectors with that of a leader in high-order nonlinear multi-agent systems.The proposed low-complexity control scheme employs high-gain observers to estimate higher-order synchronization errors,enabling the controller to rely solely on relative output measurements.This approach significantly reduces the dependence on full-state information,which is often infeasible or costly in practical engineering applications.An output feedback control strategy is developed to overcome these limitations while ensuring robust and effective synchronization.Simulation results are provided to demonstrate the effectiveness of the proposed approach and validate the theoretical findings.
基金co-supported by the National Natural Science Foundation of China(Nos.72371052 and 71871042).
文摘Addressing optimal confrontation methods in multi-agent attack-defense scenarios is a complex challenge.Multi-Agent Reinforcement Learning(MARL)provides an effective framework for tackling sequential decision-making problems,significantly enhancing swarm intelligence in maneuvering.However,applying MARL to unmanned swarms presents two primary challenges.First,defensive agents must balance autonomy with collaboration under limited perception while coordinating against adversaries.Second,current algorithms aim to maximize global or individual rewards,making them sensitive to fluctuations in enemy strategies and environmental changes,especially when rewards are sparse.To tackle these issues,we propose an algorithm of MultiAgent Reinforcement Learning with Layered Autonomy and Collaboration(MARL-LAC)for collaborative confrontations.This algorithm integrates dual twin Critics to mitigate the high variance associated with policy gradients.Furthermore,MARL-LAC employs layered autonomy and collaboration to address multi-objective problems,specifically learning a global reward function for the swarm alongside local reward functions for individual defensive agents.Experimental results demonstrate that MARL-LAC enhances decision-making and collaborative behaviors among agents,outperforming the existing algorithms and emphasizing the importance of layered autonomy and collaboration in multi-agent systems.The observed adversarial behaviors demonstrate that agents using MARL-LAC effectively maintain cohesive formations that conceal their intentions by confusing the offensive agent while successfully encircling the target.
文摘In recent years,researchers have leveraged single-agent reinforcement learning to boost educational outcomes and deliver personalized interventions;yet this paradigm provides no capacity for inter-agent interaction.Multi-agent reinforcement learning(MARL)overcomes this limitation by allowing several agents to learn simultaneously within a shared environment,each choosing actions that maximize its own or the group's rewards.By explicitly modeling and exploiting agent-to-agent dynamics,MARL can align those interactions with pedagogical goals such as peer tutoring,collaborative problem-solving,or gamified competition,thus opening richer avenues for adaptive and socially informed learning experiences.This survey investigates the impact of MARL on educational outcomes by examining evidence of its effectiveness in enhancing learner performance,engagement,equity,and reducing teacher workload compared to single agent or traditional approaches.It explores the educational domains and pedagogical problems addressed by MARL,identifies the algorithmic families used,and analyzes their influence on learning.The review also assesses experimental settings and evaluation metrics to determine ecological validity,and outlines current challenges and future research directions in applying MARL to education.
基金supported by the National Natural Science Foundation of China under Grants 61962023,61562029 and 62466019.
文摘This paper presents an adaptive multi-agent coordination(AMAC)strategy suitable for complex scenarios,which only requires information exchange between neighbouring robots.Unlike traditional multi-agent coordination methods that are solved by neural dynamics,the proposed strategy displays greater flexibility,adaptability and scalability.Furthermore,the proposed AMAC strategy is reconstructed as a time-varying complex-valued matrix equation.By introducing a dynamic error function,a fixed-time convergent zeroing neural network(FTCZNN)model is designed for the online solution of the AMAC strategy,with its convergence time upper bound derived theoretically.Finally,the effectiveness and applicability of the coordination control method are demonstrated by numerical simulations and physical experiments.Numerical results indicate that this method can reduce the formation error to the order of 10^(-6)within 1.8 s.
基金supported by the National Natural Science Foundation of China(No.52477097)the GuangDong Basic and Applied Basic Research Foundation(2023A1515240014)the State Key Laboratory of Advanced Electromagnetic Technology(Grant No.AET 2024KF005).
文摘To maximize the profits of power grid operators(GOs),load aggregators(LAs)and electricity customers(ECs),this paper proposes a hierarchical demand response(HDR)framework that considers competing interaction based on multiagent deep deterministic policy gradient(MaDDPG).The ECs are divided into conventional ECs and the electric vehicles(EVs)which are managed by ECs agent(ECA)and EV agent(EVA)to exploit the flexibility of the HDR framework.Thus,the HDR is a tri-layer model determined by five types of agents engaging in competing interaction to maximize their own profits.To address the limitations of mathematical expression and participation scale in the Stackelberg game within the HDR model,a dynamic interaction mechanism is adopted.Moreover,to tackle the HDR involving various entities,the MaDDPG develops multiple agents to simulation the dynamic competing interactions between each subject as well as solve the problem of continuous action control.Furthermore,MaDDPG adopts soft target update and priority experience replay method to ensure stable and effective training,and makes the exploration strategy comprehensive by using exploration noise.Simulation studies are conducted to verify the performance of the MaDDPG with dynamic interaction mechanism in dealing with multilayer multi-agent continuous action control,compared to the double deep Q network(DDQN),deep Q network(DQN)and dueling DQN.Additionally,comparisons among the proposed HDR with the price based DR(PBDR)and incentive based DR(IBDR)are analyzed to investigate the flexibility of the HDR.
基金supported in part by the Beijing Natural Science Foundation under Grant 4252050in part by the National Science Fund for Distinguished Young Scholars under Grant 62425304in part by the Basic Science Center Programs of NSFC under Grant 62088101.
文摘This paper investigates the consensus tracking control problem for high order nonlinear multi-agent systems subject to non-affine faults,partial measurable states,uncertain control coefficients,and unknown external disturbances.Under the directed topology conditions,an observer-based finite-time control strategy based on adaptive backstepping and is proposed,in which a neural network-based state observer is employed to approximate the unmeasurable system state variables.To address the complexity explosion problem associated with the backstepping method,a finite-time command filter is incorporated,with error compensation signals designed to mitigate the filter-induced errors.Additionally,the Butterworth low-pass filter is introduced to avoid the algebraic ring problem in the design of the controller.The finite-time stability of the closed-loop system is rigorously analyzed with the finite-time Lyapunov stability criterion,validating that all closed-loop signals of the system remain bounded within a finite time.Finally,the effectiveness of the proposed control strategy is verified through a simulation example.
基金funded by the Deanship of Scientific Research at Northern Border University,Arar,Saudi Arabia,under project number NBU-FFR-2026-2441-02.
文摘This paper presents Dual Adaptive Neural Topology(Dual ANT),a distributed dual-network metaadaptive framework that enhances ant-colony-based multi-agent coordination with online introspection,adaptive parameter control,and privacy-preserving interactions.This approach improves standard Ant Colony Optimization(ACO)with two lightweight neural components:a forward network that estimates swarm efficiency in real time and an inverse network that converts these descriptors into parameter adaptations.To preserve the privacy of individual trajectories in shared pheromone maps,we introduce a locally differentially private pheromone update mechanism that adds calibrated noise to each agent’s pheromone deposit while preserving the efficacy of the global pheromone signal.The resulting systemenables agents to dynamically and autonomously adapt their coordination strategies under challenging and dynamic conditions,including varying obstacle layouts,uncertain target locations,and time-varying disturbances.Extensive simulations of large grid-based search tasks demonstrated that Dual ANT achieved faster convergence,higher robustness,and improved scalability compared to advanced baselines such asMulti-StrategyACO and Hierarchical ACO.The meta-adaptive feedback loop compensates for the performance degradation caused by privacy noise and prevents premature stagnation by triggering Levy flight exploration only when necessary.
文摘Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal alignment,temporal consistency,and robust handling of noisy or incomplete inputs across multiple modalities.We propose Multi Agent-Chain of Thought(CoT),a novel multi-agent chain-of-thought reasoning framework where specialized agents for text,vision,and speech modalities collaboratively construct shared reasoning traces through inter-agent message passing and consensus voting mechanisms.Our architecture incorporates self-reflection modules,conflict resolution protocols,and dynamic rationale alignment to enhance consistency,factual accuracy,and user engagement.The framework employs a hierarchical attention mechanism with cross-modal fusion and implements adaptive reasoning depth based on dialogue complexity.Comprehensive evaluations on Situated Interactive Multi-Modal Conversations(SIMMC)2.0,VisDial v1.0,and newly introduced challenging scenarios demonstrate statistically significant improvements in grounding accuracy(p<0.01),chain-of-thought interpretability,and robustness to adversarial inputs compared to state-of-the-art monolithic transformer baselines and existing multi-agent approaches.
