Dynamic agent composition from semantic web services

The shift from Web pages to Web services enables programmatic access to the near limitless information on the World Wide Web. Autonomous agents should generate concise answers to complex questions by invoking the right services with the right data. However, traditional methods of programming automated query processing capabilities are inadequate for two reasons: as Web services become more abundant, it becomes difficult to manually formulate the query process; and, services may be temporarily unavailable - typically just when they are needed. We have created a tool called Meta-Planning for Agent Composition (MPAC) that dynamically builds agents to solve a user-defined goal using a select, currently available set of services. MPAC relies on a planning algorithm and semantic descriptions of services in the Web Ontology Language/Resource Description Framework (OWURDF) and the Web Ontology Language-Services (OWL-S) frameworks. Our novel approach for building these agents is domain independent. It assumes that semantic descriptions of services and a registry of currently available services will be available, as envisioned by the Semantic Web community. Once an information goal is expressed through the ontology of the Web service descriptions, MPAC determines the right sequence of service invocations. To illustrate our approach, we describe a proof-of-concept application in a maritime navigation domain.