Agent Communication Language Research Articles

Open networks of agents

This paper presents developed by authors P2P agent platform, a special software product. Instances of P2P agent platform are deployed in the nodes of P2P network over standard P2P service and altogether produce distribute knowledge database, intended for organizing of semantic agents’ interaction with each other. Agents of applied system are deployed in the nodes of P2P network over instances of P2P agent platform. The functional architecture, intended for further implementation and standardization, developed by FIPA working group was taken as basis of development. Implemented program product supports such mechanisms as P2P agents’ interacting on the basis of ACL — agent communication language, white and yellow pages. These mechanisms are also were developed by authors of this paper. The role, functions and functioning process are shown using two implemented examples, which are quite important from practical point of view. These examples were also used to test and verify main system mechanisms, proposed in this paper, in particular, registering and deregistering of agents and their services in white and yellow pages, distributed searching of agents and their services in the network.

Organizational and Agent-based Automated Negotiation Model for Carpooling

In the carpooling, individuals need to communicate, negotiate and in most cases adapt their daily schedule to enable cooperation. Through negotiation, agents (individuals) can reach complex agreements in an iterative way which meet the criteria for successful negotiation. The result of the negotiation depends on “negotiation mechanism” used to match and on the behavior of the agents involved in the negotiation process. This paper presents an organizational and agent-based model for commuting by candidate carpoolers using a simple negotiation mechanism aimed at finding an acceptable agreement between agents to carpool. Initially, the agents involved in exploration process, search for their partners via some kind of Agent Communication Language (ACL); after finding potential partners, they start a negotiation to find matched partner to carpool. After having found a good match, the agents can carpool for a specified time period. The agents join the carpool group when the negotiation is successful and leave the carpool group when the agreed time period is expired. Agents can be part of several carpool groups sequentially. The first implementation used home and work locations as well as preferred trip start times and carpool periods determined by uniformly sampling given sets. Furthermore a simplistic negotiation mechanism used roughly to produce possible results for the synthetic data. An automated negotiation model is implemented and validated through simulation. The Janus multi-agent platform is used. Future research will mainly focus on the development of behaviorally sound negotiation mechanism.

Exploring Semi-Autonomous Structure for Emergency Logistics Multi-Agent System

Due to the command and control relationship in emergency logistics process, the emergency logistics agent shows some semi-autonomous features as it is not completely autonomous. Aiming at the implementation of the semi-autonomous feature, this paper presents a control structure as the basis of communication among the role agents in emergency logistics multi-agent system. The suggested control structure is composed by the controller, communicator and control property set. The control property set and its corresponding ACL primitive is the core of the whole structure for representing the semi-autonomous feature, which can simulate the control behavior in the practical emergency logistics process. By means of the control property set, the controller can set the control property to the preparing information for transmission, and the communicator can encapsulate the preparing information into the FIPA ACL message with the extended control primitive. Finally, an illustrative example of multi-agent communication is proposed to validate the effectiveness of the suggested semi-autonomous structure.

Data mining agent conversations: A qualitative approach to multiagent systems analysis

This paper presents a novel method for analysing the behaviour of multiagent systems on the basis of the semantically rich information provided by agent communication languages and interaction protocols specified at the knowledge level. More low-level communication mechanisms only allow for a quantitative analysis of the occurrence of message types, the frequency of message sequences, and the empirical distributions of parameter values. Quite differently, the semantics of languages and protocols in multiagent systems can help to extract qualitative properties of observed conversations among agents. This can be achieved by interpreting the logical constraints associated with protocol execution paths or individual messages as the context of an observed interaction, and using them as features of learning samples. The contexts “mined” from such analyses, or context models, can then be used for various tasks, e.g. for predicting others’ future responses (useful when trying to make strategic communication decisions to achieve a particular outcome), to support ontological alignment (by comparing the properties of logical constraints attached to messages across participating agents), or to assess the trustworthiness of agents (by verifying the logical coherence of their behaviour). This paper details a formal approach that describes our notion of context models in multiagent conversations, an implementation of this approach in a practical tool for mining qualitative context models, and experimental results to illustrate its use and utility.

Distributed multi-agent communication system based on dynamic ontology mapping

Communication is the most important feature for meaningful interaction among agents in distributed multi-agent systems. Communication enables agent's interaction to achieve their goals. Agent communication languages provide a standard in the protocol and language used in the communication, but cannot provide a standard in ontology, because ontology depends on the subject and concept of the communication. This lack of standardisation is known as interoperability problem. In order to obtain semantic interoperability, agents need to agree on the basis of different ontologies. In this paper, a communication layer is proposed to outline the communication between agents, multiplatform communication system (MPCS) architecture is proposed to provide a highly flexible and scalable system. In addition a dynamic ontology mapping system for agent communication (DOMAC) is proposed based on different mapping approaches.

The Extension of KQML Primitive in Large Database Operation

In Multi-Agent system, the communication among the Agents is the basic problem. The Agent communication language design, especially for large database operation, has been the important part for improving the Multi-Agent system performance. Based on the Multi-Agent large scale database operation, this paper extends the KQML's Primitive for Agents communication. The extended KQML's Primitive can improve the Agent communication performance and the database query performance.

Towards a satisfactory conversion of messages among agent-based information systems

Over the last years, there has been a change of perspective concerning the management of information systems, since they are no longer isolated and need to communicate with others. However, from a semantic point of view, real communication is difficult to achieve due to the heterogeneity of the systems. We present a proposal which, considering information systems are represented by software agents, provides a framework that favors a semantic communication among them, overcoming the heterogeneity of their agent communication languages. The main components of the framework are a suite of ontologies – conceptualizing communication acts – that will be used for generating the communication conversion, and an Event Calculus interpretation of the communications, which will be used for formalizing the notion of a satisfactory conversion. Moreover, we present a motivating example in order to complete the explanation of the whole picture.

An agent-based framework for collaboration among critical mechanical devices working in a cluster

Critical mechanical devices, such as high-pressure air compressors, are crucial for industrial production. Critical mechanical devices are independently distributed devices that work in a cluster, but have high power requirements and need large amounts of space. Thus, the efficient control and coordination of a cluster of critical mechanical devices to achieve task goals is beset with difficulties. Motivated by an example of high-pressure air compressors in a cluster, this paper proposes an agent-based framework for realizing collaboration among critical mechanical devices that work in a cluster. The proposed agent-based framework endows critical mechanical devices with abilities such as autonomy, interaction and collaboration. The framework comprises three core components: (i) an agent-based control approach to the design of critical mechanical device agents to create autonomy; (ii) a type of critical mechanical device agent communication language to create interaction among critical mechanical devices; and (iii) a total working time-based collaboration algorithm that fully considers the physical characteristics of critical mechanical devices to create collaboration among critical mechanical device clusters. A type of critical mechanical device agent controller is implemented using the proposed approach. The agent-based framework has been successfully applied and evaluated in a real-world project. The results obtained in that case study show that the proposed framework can achieve collaboration among critical mechanical device clusters allowing them to realize their predefined goals efficiently and safely.

AN AGENT-ORIENTED APPROACH FOR IMAGE CLASSIFICATION WITH ICA-COLOR SIFT

This paper discusses the research conducted on developing a Multi-Agent System (MAS) for solving an image classification task. The aim of this research is to equip agents in MAS with reusable autonomous capabilities. The system provides a flexible framework for developing the communication aspects within an agent-oriented architecture to program agents that dynamically acquire functionality at runtime using event based messaging. In this research agents are equipped with unique image processing capabilities and required to interact and cooperate to achieve the goal. Complementary research on a variety of agent tools (specifically JACK, JADE and CIAgent) and communication languages (ACL, KQML, FIPA and SOAP) has been reviewed to glean knowledge that enables these agents to adapt those capabilities. The system has generated encouraging results.

An obligation-based framework for web service composition via agent conversations

This paper presents a framework for web service composition based on social norms, particularly obligations. Web services are implemented and orchestrated by agents. Agent interaction is defined by means of obligations. Then, obligation-based agent conversations are translated into a web service composition method. Web services' functionalities are conceived as a set of actions with preconditions and effects, both expressed in terms of obligations that are adopted by agents as goals. In addition, an agent communication language that defines how messages affect agents' states, and as a consequence, the access to the services is presented. Moreover, a method for automatically creating generic composer agents is proposed. Composer agents are capable of managing and composing web services by means of inducing obligations to agents that implement and orchestrate web services.

Analysis and Design of Highway Monitoring System Based on MAS

The highway monitoring system is an open, intelligent, distributed complex information processing system. Analysis of the agent (Agent), Multi-Agent System (MAS) and Agent-oriented software design (AOP), the framework of the MAS- based highway monitoring system, and its composition were analyzed, and discussed the various types of agent of the function and structure, to design a Universal Agent template. Finally, the Agent Communication Language Agent Description Language is discussed.

A Collaborative Framework for Multiagent Systems

In this paper, the authors demonstrate the use of software agents to extend the role of humans in a collaborative work process. The extended roles to agents provide a convenient means for humans to delegate mundane tasks to software agents. The framework employs the FIPA ACL communication protocol which implements communication between agents. An interface for each agent implements the communication between humans and agents. Such interface and the subsequent communication performed by agents and between agents contribute to the achievement of shared goals.

Time and defeasibility in FIPA ACL semantics

Inferences about speech acts are often conditional, non-monotonic, and involve the issue of time. Most agent communication languages, however, ignore these issues, due to the difficulty to combine them in a single formalism. This paper addresses such issues in defeasible logic, and shows how to express a semantics for ACLs in order to make non-monotonic inferences on the basis of speech acts.

Agent-based simulation framework for virtual prototyping of advanced livestock precision feeding systems

On-farm implementation of the concept of precision livestock farming requires the design and development of new, advanced and often complex equipment. This article proposes an agent-based simulation framework to meet the challenges of designing, testing and evaluating the performance of the new, automated precision feeding equipment for farms. In this context, an agent is a piece of software performing defined system functions such as exchanging information or requesting services to other agents via a high-level agent communication language. The proposed approach sees each main component of the actual precision feeding system represented by a virtual domain agent. The agents are then assembled within a multi-agent system that models the automatic precision feeding equipment as a whole. The operational capacity of the virtual prototype is achieved through communication and collaboration between the multiple agents that make up the system. The capacity for dynamic modification of parameters such as workload during the simulation process helps analyze the behavior, robustness and performance of the system prior to its actual use and thus providing a computer-aid tool helping in the design process. One case study shows that agent-based composable simulation can predict the behavior and performance of the system as a whole.

Agent Communication Language for Automated Negotiation Online

Current research in automated negotiation is lack of a unified technical standard, which is an obstacle for the system to be applied practically. The existing standard KQML (Knowledge Query Manipulation Language) has obvious flaws in its semantics definition; moreover, its function is insufficient for describing negotiation. The contribution of the work is twofold. On one hand, it expands the speech acts of KQML, and defines semantics of the new proposed speech acts. On the other hand, it designs a general interaction mechanism among negotiating agents, in which the negotiation language and ontology used by agents is defined. The work has been attempted in such a way so as to provide general support for a wide variety of commercial negotiation circumstances, and therefore to be particularly suitable for electronic commerce.

A Survey of Software Agent and Ontology

Software agent is the one of the most recent contribution in the field of Information Technology. The field of software agents is a broad and rapidly developing area of research, which encompasses a diverse range of topics and interests. In order to study the various methodologies for agent design, implementation, commercial use of it, a sample survey is required. This paper gives an overview of recent research on the software agents, agent communication languages (ACL), the different ontology use for software agent, also the summary of ACL and different tool kits for developing a software agent.

Integrating Ontologies into Multi-Agent Systems Engineering (MaSE) for University Teaching Environment

Multi-agent systems have received much attention in recent years because of their many advantages in complex and distributed environments. There are a number of methodologies have been proposed for multi- agent engineering process such as Multi-agent System Engineering (MaSE). I have used the MaSE engineering process for the development of my ontology based multi- agent system for the Academic Institute. In the era of Semantic Web, the ontology has established as a powerful tool to enable knowledge sharing and it is an important means in Semantic Web to achieve the semantic interoperability among heterogeneous distributed systems. Both ontology and agent technologies are central to the semantic web, and their combined use will enable the sharing of heterogeneous, autonomous knowledge sources in a capable, adaptable and extensible manner. Ontology is used throughout the multi-agent system to assist the interactions among different agents as well as to improve the quality of the service provided by each agent. This paper focuses on the utilization of combining both Ontology and Multi-Agent System (MAS) structure towards system integration for University teaching environment. In this paper, I include system prototype for ontology based multi-agent system. I have used Web Ontology Language (OWL) for the development of domain ontology for the Academic Institute and KQML as an agent communication language. Finally I have developed ontology-based multi- agent system for the university teaching environment by taking the benefits of both renowned technologies.

COMMUNICATION LANGUAGES FOR MULTIAGENT SYSTEMS

Agent Communication Languages (ACLs) have recently acquired a primary role in open multiagent systems, which need a standard communication framework shared by all interacting heterogeneous agents. According to the most important ACL standard proposals so far, agents are supposed to carry out the communication process by performing actions of a specific type, namely, communicative acts, whose semantics is defined in terms of the agents' mental states. Although following the mainstream guidelines inspired by the Speech Act Theory, our work illustrates an alternative model of agent communication, by shifting the focus from agents' mental states to their social state. Taking an existing communicative act library, we provide a semantics for a significant set of acts based on the concept of commitment, and prove that our approach tackles some issues that have not been dealt with in an effective way yet and that may have hindered the rise of an universally accepted ACL standard.

The design of a semantic web compatible content language for agent communication

Abstract: Current standards on agent communication languages explain communication by changes in the mental states of agents. It is rather a striking issue that none of the popular agent middleware adheres to this semantics in a formal way. Therefore, this paper tries to close the gap between agent communication theory and practice by implementing a logic that is capable of representing agents' beliefs and intentions. An interesting property of this language, named , is that it is a hybrid of modal and description logics. Due to its description logic foundation, it can also be used as an ontology definition language. Thus, it is well suited for agents working on the semantic web. In this paper, a sound and complete decision algorithm as well as other reasoning services for the logic are presented. Finally, the application of the language in a multi-agent development framework is discussed.

XML-based agent communication, migration and computation in mobile agent systems

This article presents the research work that exploits using XML (Extensible Markup Language) to represent different types of information in mobile agent systems, including agent communication messages, mobile agent messages, and other system information. The goal of the research is to build a programmable information base in mobile agent systems through XML representations. The research not only studies using XML in binary agent system space such as representing agent communication messages and mobile agent messages, but also explores interpretive XML data processing to avoid the need of an interface layer between script mobile agents and system data represented in XML. These XML-based information representations have been implemented in Mobile-C, a FIPA (The Foundation for Intelligent Physical Agents) compliant mobile agent platform. Mobile-C uses FIPA ACL (Agent Communication Language) messages for both inter-agent communication and inter-platform migration. Using FIPA ACL messages for agent migration in FIPA compliant agent systems simplifies agent platform, reduces development effort, and easily achieves inter-platform migration through well-designed communication mechanisms provided in the system. The ability of interpretive XML data processing allows mobile agents in Mobile-C directly accessing XML data information without the need of an extra interface layer.