PASSI: a Process for Specifying and Implementing Multi-Agent Systems Using UML

Multi-agent systems (MAS) differ from non-agent based systems because agents are intended to be autonomous units of intelligent functionality. As a consequence, agent-based software engineering methods must complement standard design activities and representations with models of the agent society. Some methods coming from artificial intelligence community address social knowledge and relationships but have high-level design abstractions as their end points. This paper describes PASSI a step-by-step requirement-to-code method for developing multiagent software that integrates design models and philosophies from both object-oriented software engineering and MAS using UML notation. The method has evolved through several stages; it has been previously applied in the synthesis of embedded robotics software and we are currently exploring its applications to the design of various agent-based information systems.