Planning as Abductive Updating

Abstract

In this paper we show how planning can be achieved by means of abduction, a form of non-monotonic reasoning, in the LUPS language. LUPS employs the recently introduced notion of Dynamic Logic Programming, whereby the knowledge representation rules, namely those representing actions, can dynamically change, crucial when agents are to be situated in evolving environments. By integrating into a single framework several recent developments in the logic programming and non-monotonic reasoning field of research, this work contributes to a better modeling and understanding of rational agents. At the same time, it enjoys the advantages of a declarative and implementable specification, shortening the usual gap between theory and practice often found in logical based approaches to agents. The system integrating Dynamic Logic Programming, LUPS and Abduction, in order to achieve this form of planning, has been implemented.