Responsible agent behavior: a distributed computing perspective

Software agents that are autonomous, communicative, and possibly intelligent processes raise new questions for developers of distributed systems. Specifically, what is responsible agent behavior, and who, as the owner, is legally responsible for it? The answers involve an understanding of human-agent interaction, agent-oriented middleware, and social behavior. Some software agents will have a sufficiently large number of internal states to be capable of seemingly intelligent behavior. Hence, an agent's future external behavior cannot be guaranteed on the basis of its past behavior, even if that behavior has been monitored over time. Complete compliance tests of intelligent agents, therefore, may not be achievable because of the (possibly) large number of internal states. Thus, the best we can say is that an agent has not exhibited noncompliant behavior yet. Communication between agents implies a contract between owners, and the complexity of agents implies possibly unpredictable behavior. Therefore, an appropriate legal framework is required to underwrite the consequences of communicative actions and to provide safeguards against unlawful activities. The legal implications of agent technology require new ways of thinking about working with an agent, new requirements for agent-oriented middleware, and additional types of social behavior to be considered when designing a multiagent system     

Building intelligent collaborative interface agents with the ICAGENT development framework

This paper describes the implementation of intelligent collaborative interface agents using the intelligent collaborative agent (ICagent) development framework. In particular, the paper presents the implementation of a collaborative interface agent that acts as a tutor in the context of an educational software application. The agent deliberates socially with users following the SharedPlans model of collaborative activity. Social deliberation requires interface agents to make their desires and intentions clear to the application users, being in constant communication with them, to understand the context of their activity and to reconcile their own and users’ desires in the overall context of action. Reconciliation of users’ desires allows agents to recognize the situations where users need help. The paper briefly presents the ICagent development framework, describes the implementation of the interface agent, and discusses an example of the behavior of the agent during a collaboration session.     

Predicting Interactions Between Agents in Agent-Based Modeling and Simulation of Sociotechnical Systems

Agent-based modeling and simulation are a valuable research tools for the analysis of dynamic and emergent phenomena of large-scale complex sociotechnical systems. The dynamic behavior of such systems includes both the individual behavior of heterogeneous agents within the system and the emergent behavior arising from interactions between agents; both must be accurately modeled and efficiently executed in simulations. This paper provides a timing and prediction mechanism for the accurate modeling of interactions among agents, correspondingly increasing the computational efficiency of agent-based simulations. A method for assessing the accuracy of interaction prediction methods is described based on signal detection theory. An intelligent interaction timing agent framework that uses a neural network to predict the timing of interactions between heterogeneous agents is presented; this framework dramatically improves the accuracy of interaction timing without requiring detailed scenario-specific modeling efforts for each simulation configuration.      

Learning goal hierarchies from structured observations and expert annotations

We describe a relational learning by observation framework that automatically creates cognitive agent programs that model expert task performance in complex dynamic domains. Our framework uses observed behavior and goal annotations of an expert as the primary input, interprets them in the context of background knowledge, and returns an agent program that behaves similar to the expert. We map the problem of creating an agent program on to multiple learning problems that can be represented in a “supervised concept learning’’ setting. The acquired procedural knowledge is partitioned into a hierarchy of goals and represented with first order rules. Using an inductive logic programming (ILP) learning component allows our framework to naturally combine structured behavior observations, parametric and hierarchical goal annotations, and complex background knowledge. To deal with the large domains we consider, we have developed an efficient mechanism for storing and retrieving structured behavior data. We have tested our approach using artificially created examples and behavior observation traces generated by AI agents. We evaluate the learned rules by comparing them to hand-coded rules. Editor: Rui Camacho     

A Framework for Coordinated Control of Multiagent Systems and Its Applications

In this paper, a framework is proposed for the distributed control and coordination of multiagent systems (MASs). In the proposed framework, the control of MASs is regarded as achieving decentralized control and coordination of agents. Each agent is modeled as a coordinated hybrid agent, which is composed of an intelligent coordination layer and a hybrid control layer. The intelligent coordination layer takes the coordination input, plant input, and workspace input. In the proposed framework, we describe the coordination mechanism in a domain-independent way, i.e., as simple abstract primitives in a coordination rule base for certain dependence relationships between the activities of different agents. The intelligent coordination layer deals with the planning, coordination, decision making, and computation of the agent. The hybrid control layer of the proposed framework takes the output of the intelligent coordination layer and generates discrete and continuous control signals to control the overall process. To verify the feasibility of the proposed framework, experiments for both heterogeneous and homogeneous MASs are implemented. The proposed framework is applied to a multicrane system, a multiple robot system, and a MAS consisting of an overhead crane, a mobile robot, and a robot manipulator. It is demonstrated that the proposed framework can model the three MASs. The agents in these systems are able to cooperate and coordinate to achieve a global goal. In addition, the stability of systems modeled using the proposed framework is also analyzed.     

Generating a multiplicity of policies for agent steering in crowd simulation

Pedestrian steering algorithms range from completely procedural to entirely data‐driven, but the former grossly generalize across possible human behaviors and suffer computationally, whereas the latter are limited by the burden of ever‐increasing data samples. Our approach seeks the balanced middle ground by deriving a collection of machine‐learned policies based on the behavior of a procedural steering algorithm through the decomposition of the space of possible steering scenarios into steering contexts. The resulting algorithm scales well in the number of contexts, the use of new data sets to create new policies, and in the number of controlled agents as the policies become a simple evaluation of the rules asserted by the machine‐learning process. We also explore the use of synthetic data from an “oracle algorithm” that serves as an as‐needed source of samples, which can be stochastically polled for effective coverage. We observe that our approach produces pedestrian steering similar to that of the oracle steering algorithm, but with a significant performance boost. Runtime was reduced from hours under the oracle algorithm with 10 agents to on the order of 10 frames per second (FPS) with 3000 agents. We also analyze the nature of collisions in such a framework with no explicit collision avoidance. Copyright © 2014 John Wiley & Sons, Ltd.     

智能控制中的多Agent系统

根据智能控制的安全、经济和舒适三大目标,提出一种新的基于BACnet(楼宇自动控制网络数据通信协议)的MAS(多Agent系统)框架．此框架通过不同层次、不同功能的Agent的自治能力及协作协调,使得智能控制系统的各个相对分散的子系统能够有效地结合在一起．全局Agent负责整体功能的实现,而每个子系统均设置自身的Agent组．此外,还提出了基于MAS框架的SAS(安防自动化系统)逻辑结构,同时遵循FIPA(智能物理Agent基金)标准设计了此MAS系统的Agent通信语言,并对SAS系统进行了重点分析和研究,包括CCTV(闭路电视监控)系统和基于Auto-ID(自动识别)的系统．     

Development of a collaborative virtual maintenance environment with agent technology

This paper proposed a virtual environment with agent technology to facilitate the integration and cooperation of product maintenance process. The agent-based system framework, in which various intelligent agents worked together to perform product maintenance tasks in an autonomous and collaborative way, is addressed. The functional definition of each intelligent agent is presented and the agent internal structure is designed. Moreover, ontology-based agents communication mechanism and agents co-operation model are proposed, and an intelligent algorithm based on fuzzy comprehensive evaluation is designed to solve competition conflicts among the agents. Finally, the prototype system is developed and the algorithm is proved feasible and efficient.     

Agent-based framework to individual tracking in unconstrained environments

Agents with intelligent perceptual capabilities are considered state-of-the-art in advanced intelligent systems. In addition, a multiagent system is considered an enabling technology for applications that rely on distributed and parallel processing, including data, information and knowledge in complex computing environments. With the aim of creating advanced intelligent systems with visual perception, this paper presents an agent-based framework to individual tracking in unconstrained environments. The framework has three types of agents that interact using the Contract Net Protocol. The face detector and tracker agents perform fully automatic single-sample face recognition using the Viola-Jones and the Scale Invariant Feature Transform/Speeded Up Robust Features algorithms. The experimental results show that the framework adequately recognizes and tracks individuals in unconstrained environments, indicating the path the individuals have taken and the time they spent in the field of view of the surveillance agents. Some of the open source framework advantages are the distribution in heterogeneous infrastructures, the expansion with new agents using different face recognition algorithms (e.g., Eigenfaces), and the individual tracking logs that can be used in different ways, e.g., improve security in surveillance areas such as automated teller machines, self-paying kiosks, movie box offices, and malls.     

群集系统的软控制

考虑欧氏空间中群集动态系统的"软控制"问题,即在不改变群集系统中个体间现有规则的条件下,通过增加一个或多个可控智能体干扰群集个体的行为,使群集中心转移到期望的位置.给出了可控智能体的控制规则,并利用粒子群(PSO)算法讨论了群集系统软控制的最优收敛问题.实例研究表明了"软控制"在群集系统中的可行性.     

智能Agent建模的一种模板结构

文中讨论了设计和建造智能Ａｇｎｅｔ的一些热点问题。通过对一些基本概念和定义的评述,总结了智能Ａｇｅｎｔ应具的若干主要性质的属性。     

Can a rational agent afford to be affectless? a formal approach

In this article, we expose some of the issues raised by the critics of the neoclassical approach to rational agent modeling and we propose a formal approach for the design of artificial rational agents that includes some of the functions of emotions found in the human system. We suggest that emotions and rationality are closely linked in the human mind (and in the body, for that matter) and, therefore, need to be included in architectures for designing rational artificial agents, whether these agents are to interact with humans, to model humans' behaviors and actions, or both. We describe an Affective Knowledge Representation (AKR) scheme to represent emotion schemata, which we developed to guide the design of a variety of socially intelligent artificial agents. Our approach focuses on the notion of "social expertise" of socially intelligent agents in terms of their external behavior and internal motivational goal-based abilities. AKR, which uses probabilistic frames, is derived from combining multiple emotion theories into a hierarchical model of affective phenomena useful for artificial agent design. AKR includes a taxonomy of affect, mood, emotion, and personality, and a framework for emotional state dynamics using probabilistic Markov Models.     

A multi-agent fuzzy consensus model in a Situation Awareness framework

In order to define systems enabling the automatic identification of occurring situations, numerous approaches employing intelligent software agents to analyse data coming from deployed sensors have been proposed. Thus, it is possible that more agents are committed to monitor the same phenomenon in the same environment. Redundancy of sensors and agents is needed, for instance, in real world applications in order to mitigate the risk of faults and threats. One of the possible side effects produced by redundancy is that agents, observing the same phenomenon, could provide discordant opinions. Indeed, solid mechanisms for reaching an agreement among these agents and produce a shared consensus on the same observations are needed. This paper proposes an approach to integrate a fuzzy-based consensus model into a Situation Awareness framework. The main idea is to consider intelligent agents as experts claiming their opinions (preferences) on a phenomenon of interest.     

基于Agent的入侵检测系统框架研究

文章在CIDF(通用入侵检测框架)的基础上,引入了静态智能Agent和移动Agent,提出了基于Agent的入侵检测系统框架的构想,采用静态智能Agent实现事件组件和分析组件的功能,采用移动Agent实现响应组件的功能。此框架的特点包括可扩展性、可动态配置、集成性、有效性、便于维护、升级和可自动响应等等,从而极大地改善了入侵检测系统的性能。     

Inter-agent Dialogues in Electronic Marketplaces

This paper presents an overall framework for carrying out different types of dialogues between intelligent and autonomous agents acting in an electronic marketplace. Such dialogues take place during various commercial transactions concerning requests and offers of products and services. The proposed dialogue framework has been adopted in the communication and collaboration protocols of an already implemented system, which enables buyers and sellers delegate a variety of tasks to their personal agents. Much attention has been paid to the personalization of collaborative agents, which may permanently live and interact in the market representing their owners' interests. Our overall approach builds on a modular decomposition of the agents involved, and a formal and operational modeling of the associated dialogues. Features of our framework are demonstrated through an illustrative example of dialogues deployed during interagent transactions on the establishment of a combined reservation for dinner and a movie. The main contribution of this work is that the proposed framework is capable to represent disparate dialogues taking place among agents having adopted diverse strategies for carrying out e-commerce transactions.     

Towards the design and implementation of computer-modeled opponents for use in entertainment and educational software: Some initial considerations

While advances in computer technology have led to major improvements in the presentation and appearance of modern computer games, there has been no equivalent improvement in the artificial intelligence (AI) performance of these games. Traditional AI designs have had surprisingly little impact on the development of game-based intelligent systems. New approaches to AI, particularly those using autonomous software agents encapsulated in software robots (softbots), have the potential to make an enormous impact on game-based AI systems.Softbot-based autonomous software agents provide a framework capable of supporting psychologically based models of human behavior in a game environment. Used in this manner, softbots provide a new set of tools to explore the synthesis of human-like reasoning in complex and dynamic environments.This paper explores some initial attempts to develop an exploratory, game-based, experimental environment capable of hosting softbot-based, psychological models of human behavior. Some preliminary work in the design and implementation of a simple, extensible, softbot-based, computer-modeled opponent is also discussed.     

Negotiation within a multi-agent system for the collaborative design of light industrial buildings

This paper is a review of intelligent agents with respect to their use within the Agent-Based Support for The Collaborative Design of Light Industrial Buildings (ADLIB) project. In the ADLIB project, the core objective is to develop a multi-agent system (MAS) framework for the representation of activities and processes involved in collaborative design of light industrial buildings. This includes the planning and fabrication of steel structural components. ADLIB intelligent agents are concerned with modelling action and knowledge in a collaborative environment. The design process that ADLIB's agents are trying to automate is the interaction and negotiation between specialist design team members. Each team member with a different area of expertise will be primarily concerned with his own area of interest. This paper starts with an introduction to intelligent agents. It then moves on to a discussion of agent classification systems and negotiation theories and their applications in MAS. The last section analyses the needs of agents within the ADLIB project. A negotiation protocol and strategy are then presented.     

Scaling up agent coordination strategies

Deploying intelligent agents to do peoples' bidding in environments ranging from Internet marketplaces to Mars has received much attention. Exactly what an agent is and in what sense a computational agent can behave intelligently remain the subject of considerable debate. However, most would agree that coordination, an agent's fundamental capability to decide on its own actions in the context of the activities of other agents around it, is a central concern of intelligent agency. The value of an intelligent agent coordination strategy lies in how well it scales along various dimensions of stress. Understanding the agent population, its task environment, and expectations about its collective behavior are central to mapping the space of potential approaches. The paper discusses agent coordination and dimensions of coordination stress     

Agent-Based Supply Chain Integration

Supply chain management represents a critical competency in today's fast-paced, global business environment. However, in the current transition from EDI to Web-based supply chain technologies, much of the capability for process integration is being lost. And the integration of buyer and seller supply chain processes is critical for speed and responsiveness in today's hypercompetitive product and service markets. Intelligent agent technology offers the potential to overcome many limitations of current supply chain technologies. This paper presents intelligent supply chain agents that represent and autonomously conduct business on behalf of product users, buyers and vendors. We classify and present numerous extant agent applications and extend a technological framework to compare and contrast intelligent agents with other classes of information technology. We then describe an agent-based supply chain process design, along with its developmental techniques, and the structure and behavior of an agent federation used for integration in a major enterprise. We present results of this exploratory research in terms of technical feasibility and process performance in the enterprise context. This work is novel in that it integrates process-level knowledge from operational enterprises with distributed agent technologies. And it makes a contribution by demonstrating how agent-based supply chain integration can be effected along a large-scale, operational, inter-organizational process.     

Engineering framework for agent-based manufacturing control

MAS (multi-agent systems) and HMS (holonic manufacturing systems) are enabling the vision of the Plug & Play Factory and paving the way for future autonomous production systems. This paper reviews the state of the art in implementations of agent-based manufacturing systems, and identifies the lack of engineering tools as a technological gap for widespread industrial adoption of the paradigm. The lack of tools limits the implementation of agent-based manufacturing systems within reach of only a handful of domain experts. One of the current challenges for the design and implementation of intelligent agents is the simulation and visualization of the agent societies. This issue is significant as soon as the software agent is embedded into a mechatronic device or machine resulting in a physical intelligent agent with 3D-mechanical restrictions. These mechanical restrictions must be considered in the negotiations between agents in order to coordinate the execution of physical operations. This paper presents an engineering framework that contributes towards overcoming the identified technology gap. The framework consists of a comprehensive set of software tools that facilitate the creation, simulation and visualization of agent societies. The 3D framework is innovative in fully emulating the deployed agents, recreating multi-agent negotiations and societies that coordinate and execute control of assembly operations. The documented research describes the methodology for the 3D representation of individual physical agents, the related identified objects present in the interaction protocols, and the assembly features and clustering algorithms.