Multi-Agent System Based on Psychological Models for Mobile Robots

This paper describes the design of and experimentation with the Knowledge Query and Manipulation Language( KQML), a new language and protocol for exchanging information and knowledge. This work is part a larger effort, the ARPA Knowledge Sharing Effort which is aimed at developing techniques and methodology for building large-scale knowledge bases which are sharable and reusable. KQML is both a message format and a message-handling protocol to support run-time knowledge sharing among agents. KQML can be used as a language for an application program to interact with an intelligent system or for two or more intelligent systems to share knowledgein support of cooperative problem solving. KQML focuses on an extensible set of performatives, which defines the permissible operations that agents may attempt on each other’s knowledge and goal stores. The performatives comprise a substrate on which to develop higher-level models of inter-agent interaction such as contract nets and negotiation. In addition, KQML provides a basic architecture for knowledge sharing through a special class of agent called communication facilitators which coordinate the interactions of other agents The ideas which underlie the evolving design of KQML are currently being explored through experimental prototype systems which are being used to support several testbeds in such areas as concurrent engineering, intelligent design and intelligent planning and scheduling.

Our analysis of the KQML (Knowledge Query and Manipulation Language) model yielded some conclusions on the knowledge level of communication in agent-oriented program. First, the agent state and transition model were given for analyzing the necessary conditions for interaction with the synchronal and asynchronous KQML model respectively. Second, we analyzed the deadlock and starvation problems in the KQML communication, and gave the solution. At last, the advantages and disadvantages of the synchronal and asynchronous KQML model were listed respectively, and the choosing principle was given.

This chapter discusses the desirable features of languages and protocols for communication among intelligent information agents. These desiderata are divided into seven categories: form, content, semantics, implementation, networking, environment, and reliability. The Knowledge Query and Manipulation Language (KQML) is a new language and protocol for exchanging information and knowledge. This work is part of a larger effort, the ARPA Knowledge Sharing Effort, which is aimed at developing techniques and methodologies for building large-scale knowledge bases that are sharable and reusable. KQML is both a message format and a message-handling protocol to support run-time knowledge sharing among agents. KQML is described and evaluated as an agent communication language relative to the desiderata.KeywordsMultiagent SystemSoftware AgentCommunication LanguageContent LanguageAgent Communication LanguageThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This paper describes the design of and experimentation with the Knowledge Query and Manipulation Language (KQML), a new language and protocol for exchanging information and knowledge. This work is part of a larger effort, the ARPA Knowledge Sharing Effort which is aimed at developing techniques and methodology for building large-scale knowledge bases which are sharable and reusable. KQML is both a message format and a message-handling protocol to support run-time knowledge sharing among agents. KQML focuses on an extensible set of performatives, which defines the permissible "speech acts" agents may use and comprise a substrate on which to develop higher-level models of interagent interaction such as contract nets and negotiation. In addition, KQML provides a basic architecture for knowledge sharing through a special class of agent called communication facilitors which coordinate the interactions of other agents. The ideas which underlie the evolving design of KQML are currently being explored through experimental prototype systems which are being used to support several testbeds in such areas as concurrent engineering, intelligent design and intelligent planning and scheduling.

The rise of the Internet and the growth of distributed computing have led to a major paradigm shift in software engineering and computer science. Until recently, the notion of computation has been variously construed as numerical calculation, as information processing, or as intelligent symbol analysis, but increasingly, it is now viewed as distributed cognition and interaction between intelligent entities [60]. This new view has major implications for the conceptualization, design, engineering and control of software systems, most profoundly expressed in the concept of systems of intelligent software agents, or multi-agent systems [99]. Agents are software entities with control over their own execution; the design of such agents, and of multi-agent systems of them, presents major research and software engineering challenges to computer scientists. One key challenge is the design of means of communication between intelligent agents. Considerable research effort has been expended on the design of artificial languages for agent communications, such as DARPA’s Knowledge Query and Manipulation Language (KQML) [33] and the Foundation for Intelligent Physical Agents’ (now IEEE FIPA) Agent Communications Language (FIPA ACL) [35]. These languages, and languages like them, have been designed to be widely applicable. As well as being a strength, this feature can also be a weakness: agents participating in conversations have too many choices of what to utter at each turn, and thus agent dialogues may endure a state-space explosion. Allowing sufficient flexibility of expression while avoiding state-space explosion had led agent communications researchers to the study of formal dialogue games; these are rule-governed interactions between two or more players (or agents), where

The ever increasing complexity of network and system management has lead to some changes in the organisation of management: we have moved to a more distributed approach. This approach uses two or three management levels, mainly management agents (SNMP agents) and a management station, but we forecast that this distribution trend will continue, towards a fully distributed solution. We call this solution intelligent agent-based management. In this context, cooperation between individual management agents is essential for them to solve complex management problems. We focus our contribution on the architecture which allows this cooperation. Agents must exchange tasks and information (like any management agent), but also functionality. Messages may be of the type query/response or knowledge exchange and may be sent from one agent to another, to several others or to all. We have examined protocols that could suit communication between our intelligent agents, but none entirely fulfils our requirements. KeML (Knowledge Query and Manipulation Language) was chosen as our communication language and CORBA as our transport language. This combination, named COBALT, constitutes the base of our architecture for intelligent agent-based management.

An Agent Communication Language (ACL) is a collection of speech-act-like message types, with agreed-upon semantics, which facilitate the knowledge and information exchange between software agents. From Knowledge Query and Manipulation Language (KQML) to FIPA ACL, ACL's have been a cornerstone for the development of systems of communicating agents, and simultaneously they have been the subject of intensive standardization efforts.Standardization's goal is usability. As a result, although the initial focus on ACL's revolved around establishing the semantics of ACL's, a variety of usability-related questions have entered the picture of standardizing communication among agents. In this article, we present these questions and the work that addresses them, alongside the historical evolution of ACL's, their semantics and the results of their standardization.

The MPEG Query Format (MPQF) which MPEG Group is developing is to standardize query interface for XML-based multimedia retrieval systems. MPQF provides query types for Information Retrieval and Data Retrieval over XML Database in the current draft. As more and more multimedia metadata modeled with semantic ontology like RDFS and OWL are stored in the Knowledge Base, there is a requirement for querying multimedia information over Knowledge-Based system. In this paper we propose the necessary extension (QueryByKQML type) which will allow MPQF to support Knowledge-Based Multimedia Information Retrieval based on Knowledge Query and Manipulation Language (KQML).

This paper presents the research and design of a KQML(knowledge query and manipulation language) speaking and CORBA-based intelligent multi-agent system (MAS). The MAS uses KQML as the agent communication language (ACL) and uses the CORBA event service and CORBA object trading service to implement the communication and facilitation mechanisms of the MAS. The functionality of the intelligent MAS is demonstrated with the UCAV (uninhabited combat aerial vehicle) operator control sharing application.

Efficient management of product information is critical to the enhancement of corporate competitiveness. This paper explains the design and development of a distributed, open, and intelligent product data management system. First, the requirements for Product Data Management (PDM) systems are summarized and then explained using a design scenario. Since product data are often managed in distributed computing environments, Common Object Request Broker Architecture (CORBA) is employed to ensure interoperability among distributed objects. Standard formats of data and knowledge, such as STandard for Exchange of Product model data (STEP) and Knowledge Query and Manipulation Language (KQML), are used to achieve the openness. A workflow management system has been developed that provides integrated management of task processes and information flows. While designing the system, the main emphasis is placed on dynamic process adaptation which is demanded by product development processes. Use of intelligent agents is proposed to achieve the adaptation at run time. A method of agent cooperation and communication is described. The agents are also used to implement content search for enhanced product data services.

In this paper, the basic architecture of an agent is proposed and a federated agent system based on the basic architecture is implemented. The basic architecture consists of a knowledge query and manipulation language (KQML) handler, a knowledge interchange format (KIF) interpreter, and design flow control codes. The KQML handler is a module for managing KQML performatives received from an agent. The KIF interpreter provides the support services of content-based routing, translation using a matching scheme, and simple inference. A Java template package was used for communication between agents. A federated agent system was then applied to a preliminary ship design to show the handling process of the agent system and its applicability in a distributed design environment.

The development of an agent-based distributed Multi-axis surface machining system is described in this paper. The proposed system has successfully applied software agent-based technology in constructing a distributed freeform surface multi-axis machining environment. There are six domain software agents in the developed system and these agents communicate via pre-defined performatives in knowledge query and manipulation language (KQML) for exchanging surface machining information.

We investigate the semantics for Knowledge Query Manipulation Language (KQML) and we propose a semantic framework for the language. KQML is a language and a protocol to support communication between software agents. Based on ideas from speech act theory, we propose a semantic description for KQML that associates descriptions of the cognitive states of agents with the use of the language's primitives (performatives). We use this approach to describe the semantics for the basic set of KQML performatives. We also investigate implementation issues related to our semantic approach. We suggest that KQML can offer an all purpose communication language for software agents that requires no limiting pre-commitments on the agents' structure and implementation. KQML can provide the Distributed AI, Cooperative Distributed Problem Solving and Software Agents communities with an all purpose language and environment for intelligent inter-agent communication.

ISIS (Intelligent Speech for Information Systems) is a trilingual spoken dialog system in the stocks domain. It supports the three languages commonly used in Hong Kong (Cantonese, Putonghua and English), and serves as a test-bed for our research in various speech and language technologies. ISIS also features combined interaction and delegation dialogs, and automatic assimilation of newly listed stock names into the system’s knowledge base. This paper focuses on the architecture and multi-modality of ISIS. We use the CORBA middleware to implement a distributed system that is interoperable across platforms. We also describe the incorporation of KQML (Knowledge Query and Manipulation Language) software agents in ISIS to handle delegation dialogs. The latest enhancement supports multi-modal and mixed-modal input which suit the natural affordances of certain interactions in order to improve usability. Input modalities include speaking, typing or mouse-clicking. Output media include synthesized speech, text, tables and graphics.

Autonomous robot soccer system consists of a multi-agent system that need to cooperate in unknown, dynamic, and competitive environment. Thus, it is a crucial issue how to realize effective and real time communications among soccer robots. There are three problems need to solve about the communication, they are dialog management, communication language, and communication protocol. Thereinto, communication language is a intermedium to transport information and exchange knowledge among agents. In this paper, we introduce the communication mechanism of autonomous robot soccer system, and its practical and reliable communication language based on KQML (Knowledge Query and Manipulation Language), which is designed for cooperative problem solving and knowledge sharing of the multi-robot system. It is shown that the communication mechanism is effective, efficient robust.