Prometheus: A Methodology for Developing Intelligent Agents

As agents gain acceptance as a technology there is a growing need for practical methods for developing agent applications. This paper presents the Prometheus methodology, which has been developed over several years in collaboration with Agent Oriented Software. The methodology has been taught at industry workshops and university courses. It has proven effective in assisting developers to design, document, and build agent systems. Prometheus differs from existing methodologies in that it is a detailed and complete (start to end) methodology for developing intelligent agents which has evolved out of industrial and pedagogical experience. This paper describes the process and the products of the methodology illustrated by a running example.

[1]  Fausto Giunchiglia,et al.  The tropos software development methodology: processes, models and diagrams , 2002, AAMAS '02.

[2]  Onn Shehory,et al.  Evaluation of modeling techniques for agent-based systems , 2001, AGENTS '01.

[3]  Michael Winikoff,et al.  Simplifying the Development of Intelligent Agents , 2001, Australian Joint Conference on Artificial Intelligence.

[4]  Holger Knublauch,et al.  Tool-Supported Process Analysis and Design for the Development of Multi-agent Systems , 2002, AOSE.

[5]  Scott A. DeLoach,et al.  Multiagent Systems Engineering , 2001, Int. J. Softw. Eng. Knowl. Eng..

[6]  Alexis Drogoul,et al.  Agent Oriented Design of a Soccer Robot Team , 1996 .

[7]  Carlos Angel Iglesias,et al.  A Survey of Agent-Oriented Methodologies , 1998, ATAL.

[8]  Michael Papasimeon,et al.  Extending the UML for designing Jack agents , 2001, Proceedings 2001 Australian Software Engineering Conference.

[9]  Michael P. Georgeff,et al.  Modelling and Design of Multi-Agent Systems , 1997, ATAL.

[10]  Scott A. DeLoach,et al.  Analysis and Design using MaSE and agentTool , 2001 .

[11]  Gerd Wagner,et al.  The Agent-Object-Relationship metamodel: towards a unified view of state and behavior , 2003, Inf. Syst..

[12]  Nicholas R. Jennings,et al.  The Gaia Methodology for Agent-Oriented Analysis and Design , 2000, Autonomous Agents and Multi-Agent Systems.

[13]  Norbert Glaser.  The CoMoMAS Methodology and Enironment for Multi-Agent System Development , 1996, DAI.

[14]  Bernhard Bauer,et al.  Extending UML for agents , 2000 .

[15]  Michael Winikoff,et al.  Debugging multi-agent systems using design artifacts: the case of interaction protocols , 2002, AAMAS '02.

[16]  Nicholas R. Jennings,et al.  Integrating Intelligent Systems into a Cooperating Community for Electricity Distribution Management , 1994 .

[17]  Jorge J. Gómez-Sanz,et al.  Agent Oriented Analysis Using Message/UML , 2001, AOSE.

[18]  Carlos Angel Iglesias,et al.  Analysis and Design of Multiagent Systems Using MAS-Common KADS , 1997, ATAL.

[19]  Anand S. Rao,et al.  A Methodology and Modelling Technique for Systems of BDI Agents , 1996, MAAMAW.

[20]  Elizabeth A. Kendall,et al.  A Methodology for Developing Agent Based Systems , 1995, DAI.

[21]  M. Elammari,et al.  An Agent-Oriented Methodology: High-Level and Intermediate Models , 1999 .

[22]  José Carlos González,et al.  Analysis and Design of multiagent systems using MAS-CommonKADS , 1998 .

[23]  Birgit Burmeister,et al.  Models and Methodology for Agent-Oriented Analysis and Design , 2000 .

[24]  Nicholas R. Jennings,et al.  DESIRE: Modelling Multi-Agent Systems in a Compositional Formal Framework , 1997, Int. J. Cooperative Inf. Syst..

[25]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .