From Active Objects to Autonomous Agents

This paper studies how to extend the concept of active object into a structure of agent. It rst discusses the requirements for autonomous agents that are not covered by simple active objects. We propose then the extension of the single behavior of an active object into a set of behaviors (reactive or deliberative) with a meta-behavior supervising their interactions. To make a concrete proposal based on these ideas we describe how we extended a platform of active objects (named Actalk), into a generic multi-agent platform (named DIMA). We discuss how this extension has been implemented. We nally report on the application of DIMA to model economic agent evolution and to intensive care patient monitoring.