This paper is focused on how a general-purpose hierarchical planning representation, based on the HTN paradigm, can be used to support the representation of oncology treatment protocols. The planning algorithm used is a temporally extended HTN planning process capable of interpreting such representation and generating oncology treatment plans that have been proven to support clinical decisions in the area of pediatrics oncology. MOTIVATION Hierarchical planning, and more concretely Hierarchical Task Networks (HTN) planning (Sacerdoti 1975; Tate 1977; Castillo et al. 2006), is a planning paradigm that supports the modeling of planning domains in terms of a compositional hierarchy of tasks representing compound and primitive tasks at different levels of abstraction. A hierarchical planning algorithm mainly decomposes compound tasks into (compound/primitive) subtasks, following the order constraints described in different (and possible alternative) decomposition methods, by means of a re...
Juan Fernández-Olivares, Luis A. Castillo,