基于MAS(Multi-AgentSystem)的多机器人系统:协作多机器人学发展的一个重要方向

机器人的应用方式正在由部件式单元应用向系统式应用方向发展 .这是实际应用的需要 ,也是技术发展的必然趋势 ;相关技术如计算机网络技术的发展也为它的实现提供了相应支持 .多机器人协作理论问题必然也已经成为机器人学研究的一个热点 ,其中 ,分布式人工智能 ( DAI)中的多智能体 (代理 )系统 ( MAS:Multi-agentSystem)理论已引起多机器人协作理论研究者的关注 .本文即在揭示协作多机器人系统与 MAS的内在联系的基础上 ,指出基于 MAS的协作多机器人系统是协作多机器人学发展的一个重要方向 .

Finite-time Prescribed Performance Time-Varying Formation Control for Second-Order Multi-Agent Systems With Non-Strict Feedback Based on a Neural Network Observer

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.

CoopAI-Route: DRL Empowered Multi-Agent Cooperative System for Efficient QoS-Aware Routing for Network Slicing in Multi-Domain SDN

The emergence of beyond 5G networks has the potential for seamless and intelligent connectivity on a global scale.Network slicing is crucial in delivering services for different,demanding vertical applications in this context.Next-generation applications have time-sensitive requirements and depend on the most efficient routing path to ensure packets reach their intended destinations.However,the existing IP(Internet Protocol)over a multi-domain network faces challenges in enforcing network slicing due to minimal collaboration and information sharing among network operators.Conventional inter-domain routing methods,like Border Gateway Protocol(BGP),cannot make routing decisions based on performance,which frequently results in traffic flowing across congested paths that are never optimal.To address these issues,we propose CoopAI-Route,a multi-agent cooperative deep reinforcement learning(DRL)system utilizing hierarchical software-defined networks(SDN).This framework enforces network slicing in multi-domain networks and cooperative communication with various administrators to find performance-based routes in intra-and inter-domain.CoopAI-Route employs the Distributed Global Topology(DGT)algorithm to define inter-domain Quality of Service(QoS)paths.CoopAI-Route uses a DRL agent with a message-passing multi-agent Twin-Delayed Deep Deterministic Policy Gradient method to ensure optimal end-to-end routes adapted to the specific requirements of network slicing applications.Our evaluation demonstrates CoopAI-Route’s commendable performance in scalability,link failure handling,and adaptability to evolving topologies compared to state-of-the-art methods.

Designing Proportional-Integral Consensus Protocols for Second-Order Multi-Agent Systems Using Delayed and Memorized State Information

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.

Unleashing the Power of Multi-Agent Reinforcement Learning for Algorithmic Trading in the Digital Financial Frontier and Enterprise Information Systems

In the rapidly evolving landscape of today’s digital economy,Financial Technology(Fintech)emerges as a trans-formative force,propelled by the dynamic synergy between Artificial Intelligence(AI)and Algorithmic Trading.Our in-depth investigation delves into the intricacies of merging Multi-Agent Reinforcement Learning(MARL)and Explainable AI(XAI)within Fintech,aiming to refine Algorithmic Trading strategies.Through meticulous examination,we uncover the nuanced interactions of AI-driven agents as they collaborate and compete within the financial realm,employing sophisticated deep learning techniques to enhance the clarity and adaptability of trading decisions.These AI-infused Fintech platforms harness collective intelligence to unearth trends,mitigate risks,and provide tailored financial guidance,fostering benefits for individuals and enterprises navigating the digital landscape.Our research holds the potential to revolutionize finance,opening doors to fresh avenues for investment and asset management in the digital age.Additionally,our statistical evaluation yields encouraging results,with metrics such as Accuracy=0.85,Precision=0.88,and F1 Score=0.86,reaffirming the efficacy of our approach within Fintech and emphasizing its reliability and innovative prowess.

MADDPG-D2: An Intelligent Dynamic Task Allocation Algorithm Based on Multi-Agent Architecture Driven by Prior Knowledge

Aiming at the problems of low solution accuracy and high decision pressure when facing large-scale dynamic task allocation(DTA)and high-dimensional decision space with single agent,this paper combines the deep reinforce-ment learning(DRL)theory and an improved Multi-Agent Deep Deterministic Policy Gradient(MADDPG-D2)algorithm with a dual experience replay pool and a dual noise based on multi-agent architecture is proposed to improve the efficiency of DTA.The algorithm is based on the traditional Multi-Agent Deep Deterministic Policy Gradient(MADDPG)algorithm,and considers the introduction of a double noise mechanism to increase the action exploration space in the early stage of the algorithm,and the introduction of a double experience pool to improve the data utilization rate;at the same time,in order to accelerate the training speed and efficiency of the agents,and to solve the cold-start problem of the training,the a priori knowledge technology is applied to the training of the algorithm.Finally,the MADDPG-D2 algorithm is compared and analyzed based on the digital battlefield of ground and air confrontation.The experimental results show that the agents trained by the MADDPG-D2 algorithm have higher win rates and average rewards,can utilize the resources more reasonably,and better solve the problem of the traditional single agent algorithms facing the difficulty of solving the problem in the high-dimensional decision space.The MADDPG-D2 algorithm based on multi-agent architecture proposed in this paper has certain superiority and rationality in DTA.

Optimal Design of Drying Process of the Potatoes withMulti-Agent Reinforced Deep Learning

Heat and mass transport through evaporation or drying processes occur in many applications such as food processing,pharmaceutical products,solar-driven vapor generation,textile design,and electronic cigarettes.In this paper,the transport of water from a fresh potato considered as a wet porous media with laminar convective dry air fluid flow governed by Darcy’s law in two-dimensional is highlighted.Governing equations of mass conservation,momentumconservation,multiphase fluid flowin porousmedia,heat transfer,and transport of participating fluids and gases through evaporation from liquid to gaseous phase are solved simultaneously.In this model,the variable is block locations,the object function is changing water saturation inside the porous medium and the constraint is the constant mass of porous material.It shows that there is an optimal configuration for the purpose of water removal from the specimen.The results are compared with experimental and analyticalmethods Benchmark.Then for the purpose of configuration optimization,multi-agent reinforcement learning(MARL)is used while multiple porous blocks are considered as agents that transfer their moisture content with the environment in a real-world scenario.MARL has been tested and validated with previous conventional effective optimization simulations and its superiority proved.Our study examines and proposes an effective method for validating and testing multiagent reinforcement learning models and methods using a multiagent simulation.

Performance Evaluation ofMulti-Agent Reinforcement Learning Algorithms

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.

Application of a Multi-Agent System (MAS) to Rational Credit Rating

A Multi-Agent System （ MAS ） is a promising approach to build complex system. This paper introduces the research of the Inner-Enterprise Credit Rating MAS （ IECRMAS）. To raise the rating accuracy, we not only consider the rating-target＇s information, but also focus on the evaluators＇ feature information and propose the rational rating-group formation algorithm based on an anti-bias measurement of the group. We also propose the rational rating individual, which consists of the evaluator and the assistant rating agent. A rational group formation protocol is designed to coordinate autonomous agents to perform the rating job.

MULTI-AGENT BASED DISTRIBUTED MANUFACTURING EXECUTION SYSTEM MODEL

A multi-agent based manufacturing execution system (MES) model is presented. It is open, modula-rized, distributed, configurable, integratable and maintainable. By analyzing the MES domain in manufacturing systems, this paper proposes a multi-agent based MES model and analyzes the partitioned functions of MES in the model using unified modeling language (UML) diagrams, and establishes the ongoing implemented MES architecture. This MES can be facilely integrated with the enterprise resource planning (ERP), the floor control system (FCS), and the other manufacturing applications.

基于Multi-Agent的无人机集群体系自主作战系统设计

针对无人集群自主作战体系设计中的关键问题,提出基于Multi-Agent的无人集群自主作战系统设计方法。建立无人集群各节点的Agent模型及其推演规则;对于仿真系统模块化和通用化的需求,设计系统互操作式接口和无人集群自主作战的交互关系;开展无人集群系统仿真推演验证。仿真结果表明,所提设计方案不仅能够有效开展并完成自主作战网络生成-集群演化-效能评估的全过程动态演示验证,而且能够通过重复随机试验进一步评估无人集群的协同作战效能,最后总结了集群协同作战的策略和经验。

基于Multi-Agent的水电站变压器故障诊断系统

为了精准、快速完成水电站变压器的故障诊断,设计基于Multi-Agent的水电站变压器故障诊断系统。变压器状态监控agent将检测到的变压器故障信息发送给系统管理agent,系统管理agent通过通信agent将变压器故障信息发送给变压器故障诊断agent,变压器故障诊断agent利用小波变换方法提取变压器故障特征,并将其作为IFOA-SVM模型输入,完成变压器故障分类后,获取变压器故障诊断结果,该结果通过通信agent显示给用户。实验表明,该系统可有效诊断变压器故障诊断,诊断成功率受系统故障信息丢失率的影响较小,诊断耗时、耗能小,并具有较高故障诊断成功率。

烟草果胶和纤维素含量^(13)C MultiCP/MAS NMR同时测量

果胶和纤维素是烟草细胞壁的重要组成成分,其含量对烟草品质与安全性产生重要影响。传统分析方法难以实现果胶和纤维素的同时定量。本文在优化核磁共振波谱序列条件的基础上,采用固体^(13)C多重交叉极化/魔角旋转核磁共振波谱分析技术(^(13)C MultiCP/MAS NMR)建立了烟草果胶和纤维素含量的同时测量新方法。方法以聚半乳糖醛酸和微晶纤维素为标准物质,以3-(三甲基甲硅烷基)丙酸-d4钠盐(TMSP)做为内标物质,分别建立内标法标准曲线,相关系数R2为0.999 0和0.998 2。果胶测量的检出限和定量限分别为0.38和1.28 mg·g^(–1),精密度(RSD,n=5)小于3.05%。纤维素测量的检出限和定量限为1.01和3.32 mg·g^(–1),精密度(RSD,n=5)小于2.74%。应用本方法测量烟梗、烟草薄片和烟叶等不同类型样品中的果胶和纤维素含量,并对比烟草行业标准方法的测量结果,果胶含量的相对误差在-0.95%至4.51%之间,纤维素含量的相对误差在0.77%至2.46%之间。表明^(13)C MultiCP/MAS NMR方法快速,准确,适合批量样品的分析测量,为果胶和纤维素等细胞壁类大分子的同时定量分析提供重要技术支持。

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

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.

抗奥合剂通过p38 MAPK/NF-κB信号通路和ACE2/Ang1-7/Mas轴缓解急性肺损伤研究

目的探讨抗奥合剂(KAHJ)治疗小鼠急性肺损伤(ALI)的作用及机制,为其可能作为缓解新型冠状病毒(COVID-19)感染后症状的药物提供依据。方法采用网络药理学方法预测KAHJ治疗ALI的主要活性成分、潜在靶点和相关信号通路。将C57BL/6J小鼠随机分为对照组、LPS组和LPS+KAHJ组。LPS+KAHJ组小鼠灌胃KAHJ(4.76 g·kg^(-1)·d^(-1),8.8 mL·kg^(-1)·d^(-1)),其余组小鼠灌胃生理盐水(8.8 mL·kg^(-1)·d^(-1))。14 d后,腹腔注射LPS(5 mg·kg^(-1))诱导ALI模型。收集小鼠血清和肺组织,通过组织病理学观察肺组织的病理变化。采用Western blot、qPCR、ELISA和IHC等方法评估KAHJ对ALI的改善作用。结果通过网络药理学筛选出疾病和药物共同的70个核心靶基因,并显示与多个信号通路密切相关,如MAPK、NF-κB、Apoptosis、COVID-19和肾素-血管紧张素系统(Ras)信号通路等。此外,通过实验验证发现KAHJ能改善小鼠ALI后的炎症和细胞凋亡,减少肺损伤和肺水肿,抑制肺纤维化。同时,KAHJ的作用机制与p38 MAPK和NF-κB的磷酸化以及ACE2/Ang1-7/Mas轴的调控也有着密切关系。结论KAHJ可能通过抑制p38 MAPK/NF-κB信号通路和调控ACE2/Ang1-7/Mas轴缓解ALI,为缓解COVID-19感染后症状提供了补充和替代药物。

Multi-agent Based Hierarchy Simulation Models of Carrier-based Aircraft Catapult Launch

With the aid of multi-agent based modeling approach to complex systems, the hierarchy simulation models of carrier-based aircraft catapult launch are developed. Ocean, carrier, aircraft, and atmosphere are treated as aggregation agents, the detailed components like catapult, landing gears, and disturbances are considered as meta-agents, which belong to their aggregation agent. Thus, the model with two layers is formed i.e. the aggregation agent layer and the meta-agent layer. The information communication among all agents is described. The meta-agents within one aggregation agent communicate with each other directly by information sharing, but the meta-agents, which belong to different aggregation agents exchange their information through the aggregation layer first, and then perceive it from the sharing environment, that is the aggregation agent. Thus, not only the hierarchy model is built, but also the environment perceived by each agent is specified. Meanwhile, the problem of balancing the independency of agent and the resource consumption brought by real-time communication within multi-agent system （MAS） is resolved. Each agent involved in carrier-based aircraft catapult launch is depicted, with considering the interaction within disturbed atmospheric environment and multiple motion bodies including carrier, aircraft, and landing gears. The models of reactive agents among them are derived based on tensors, and the perceived messages and inner frameworks of each agent are characterized. Finally, some results of a simulation instance are given. The simulation and modeling of dynamic system based on multi-agent system is of benefit to express physical concepts and logical hierarchy clearly and precisely. The system model can easily draw in kinds of other agents to achieve a precise simulation of more complex system. This modeling technique makes the complex integral dynamic equations of multibodies decompose into parallel operations of single agent, and it is convenient to expand, maintain, and reuse the program codes.

Consensus tracking protocol and formation control of multi-agent systems with switching topology

Consensus tracking control problems for single-integrator dynamics of multi-agent systems with switching topology are investigated. In order to design effective consensus tracking protocols for a more general class of networks, which are aimed at ensuring that the concerned states of agents converge to a constant or time-varying reference state, new consensus tracking protocols with a constant and time-varying reference state are proposed, respectively. Particularly, by contrast with spanning tree, an improved condition of switching interaction topology is presented. And then, convergence analysis of two consensus tracking protocols is provided by Lyapunov stability theory. Moreover, consensus tracking protocol with a time-varying reference state is extended to achieve the fbrmation control. By introducing formation structure set, each agent can gain its individual desired trajectory. Finally, several simulations are worked out to illustrate the effectiveness of theoretical results. The test results show that the states of agents can converge to a desired constant or time-varying reference state. In addition, by selecting appropriate structure set, agents can maintain the expected formation under random switching interaction topologies.

Consensus and formation control of discrete-time multi-agent systems

Consensus problems for discrete-time multi-agent systems were focused on. In order to design effective consensus protocols, which were aimed at ensuring that the concerned states of agents converged to a common value, a new consensus protocol for general discrete-time multi-agent system was proposed based on Lyapunov stability theory. For discrete-time multi-agent systems with desired trajectory, trajectory tracking and formation control problems were studied. The main idea of trajectory tracking problems was to design trajectory controller such that each agent tracked desired trajectory. For a type of formation problem with fixed formation structure, the formation structure set was introduced. According to the formation structure set, each agent can track its individual desired trajectory. Finally, simulations were provided to demonstrate the effectiveness of the theoretical results. The mlmerical results show that the states of agents converge to zero with consensus protocol, which is said to achieve a consensus asymptotically. In addition, through designing appropriate trajectory controllers, the simulation results show that agents converge to the desired trajectory asymptotically and can form different formations.

Distributed formation control for a multi-agent system with dynamic and static obstacle avoidances

Formation control and obstacle avoidance for multi-agent systems have attracted more and more attention. In this paper, the problems of formation control and obstacle avoidance are investigated by means of a consensus algorithm. A novel distributed control model is proposed for the multi-agent system to form the anticipated formation as well as achieve obstacle avoidance. Based on the consensus algorithm, a distributed control function consisting of three terms （formation control term, velocity matching term, and obstacle avoidance term） is presented. By establishing a novel formation control matrix, a formation control term is constructed such that the agents can converge to consensus and reach the anticipated formation. A new obstacle avoidance function is developed by using the modified potential field approach to make sure that obstacle avoidance can be achieved whether the obstacle is in a dynamic state or a stationary state. A velocity matching term is also put forward to guarantee that the velocities of all agents converge to the same value. Furthermore, stability of the control model is proven. Simulation results are provided to demonstrate the effectiveness of the proposed control.

基于ACE2-Ang(1-7)-Mas轴研究参芪地黄汤对2型糖尿病模型大鼠认知功能的影响

目的:观察参芪地黄汤对2型糖尿病(T2DM)认知障碍的改善作用,通过对ACE2-Ang-(1-7)-Mas轴的研究进一步探讨参芪地黄汤改善糖尿病认知功能障碍的可能机制。方法:24只雄性SD大鼠采用高脂高糖饲料喂养联合链脲佐菌素(STZ)腹腔注射构建T2DM大鼠模型,随机分为模型组和参芪地黄汤低、中、高剂量组,每组6只,另设6只为空白对照组。给药组灌胃相应剂量药物(低中高剂量分别为10.8、21.6、32.4 g/kg)连续8周。Morris水迷宫实验观察大鼠行为学变化;HE染色观察大鼠海马组织的病理学改变;ELISA检测大鼠血清中胰岛素含量,海马中血管紧张素(1-7)[Ang(1-7)],白细胞介素1β(IL-1β),白细胞介素18(IL-18)和肿瘤坏死因子-α(TNF-α)的含量;免疫组化,Western blot检测海马中血管紧张素Ⅱ(AngⅡ)、血管紧张素转换酶2(ACE2)、Mas受体(MasR)、NOD样受体蛋白3(NLRP3)、半胱氨酸天冬酶-1(Caspase-1)蛋白。结果:与对照组比较,模型组空腹血糖水平升高;大鼠平均逃避潜伏时间显著延长,而穿越平台的次数则显著减少(P<0.01);海马组织结构疏松,炎细胞浸润明显,小胶质细胞显著增多。与模型组比较,各给药组空腹血糖水平均降低,胰岛素水平均升高;参芪地黄汤中、高剂量组大鼠潜伏期显著缩短,穿越平台次数显著增多(P<0.05);大鼠神经元结构较完整,炎细胞浸润、小胶质细胞显著减少。与对照组比较,模型组组织中Ang-(1-7)和IL-1β、IL-18和TNF-α等细胞因子水平显著上升(P<0.01),海马中ACE2、Mas表达显著下降(P<0.05),而AngⅡ、NLRP3、Caspase-1表达则显著上升(P<0.05);与模型组相比,经过给药后各组海马中AngⅡ、NLRP3、Caspase-1表达显著下降(P<0.05),ACE2、Mas则显著升高(P<0.05)。结论:参芪地黄汤可能通过调节ACE2-Ang-(1-7)-Mas轴抑制NLRP3炎性小体的激活,减少炎症级联反应从而改善T2DM模型大鼠认知功能障碍。