Hierarchical finite state controllers for generalized planning

Segovia-Aguas, Javier; Jiménez, Sergio; Jonsson, Anders, 1973-

Hierarchical finite state controllers for generalized planning

Citation

Segovia-Aguas J, Jiménez S, Jonsson A. Hierarchical finite state controllers for generalized planning. In: Kambhampati S, editor. Proceedings of the 25th International Joint Conference on Artificial Intelligence; 2016 July 9-15; New York, United States. Palo Alto: AAAI Press; 2016. p. 2325-41.

Abstract

Finite State Controllers (FSCs) are an effective way/nto represent sequential plans compactly. By imposing/nappropriate conditions on transitions, FSCs/ncan also represent generalized plans that solve a/nrange of planning problems from a given domain./nIn this paper we introduce the concept of hierarchical/nFSCs for planning by allowing controllers/nto call other controllers. We show that hierarchical/nFSCs can represent generalized plans more compactly/nthan individual FSCs. Moreover, our call/nmechanism makes it possible to generate hierarchical/nFSCs in a modular fashion, or even to apply/nrecursion. We also introduce a compilation that/nenables a classical planner to generate hierarchical/nFSCs that solve challenging generalized planning/nproblems. The compilation takes as input a set of/nplanning problems from a given domain and outputs/na single classical planning problem, whose solution/ncorresponds to a hierarchical FSC.