Axioms in Model-based Planners

TL;DR

This paper explores the integration of axioms into model-based planners, demonstrating that they can reduce search space and plan length by leveraging answer set programming and integer programming techniques.

Contribution

It introduces axiom-aware planning methods based on answer set programming and integer programming, expanding the applicability of axioms beyond state-space search planners.

Findings

Axioms enable smaller search spaces and shorter plans.

Answer set programming and integer programming effectively utilize axioms.

Axioms increase expressivity in PDDL planning domains.

Abstract

Axioms can be used to model derived predicates in domain- independent planning models. Formulating models which use axioms can sometimes result in problems with much smaller search spaces and shorter plans than the original model. Previous work on axiom-aware planners focused solely on state- space search planners. We propose axiom-aware planners based on answer set programming and integer programming. We evaluate them on PDDL domains with axioms and show that they can exploit additional expressivity of axioms.