Hierarchical Goal Networks and Goal-Driven Autonomy: Going where AI Planning Meets Goal Reasoning
Vikas Shivashankar, Ron Alford, Ugur Kuter, Dana S. Nau · 2013
Planning systems are typically told what goals to pursue and cannot modify them. Some methods (e.g., for contingency planning, dynamic replanning) can respond to execution failures, but usually ignore opportunities and do not reason about the goals themselves. Goal-Driven Autonomy (GDA) relaxes some common assumptions of classical planning (e.g., static environments, fixed goals, no unpredictable exogenous events). This paper describes our Hierarchical Goal Network formalism and algorithms that we have been working on for some time now and discusses how this particular planning formalism relates to GDA and may help address some of GDA’s challenges. 1.