A Brain-Inspired Model of Hierarchical Planner

Hierarchical planning is an approach of planning by composing and executing hierarchically arranged plans to solve some problems. Most symbolic-based hierarchical planners have been devised to allow the knowledge to be described expressively. However, a great challenge is to automatically seek and acquire new plans on the fly. This paper presents a novel neural-based model of hierarchical planning that can seek and acquired new plans on-line if the necessary knowledge are lacking. Inspired by findings in neuropsychology, plans can be inherently learnt, retrieved, and manipulated simultaneously rather than discretely processed like in most symbolic approaches. Using a multi-channel adaptive resonance theory (fusion ART) neural network as the basic building block, the so called iFALCON architecture can capture and manipulate sequential and hierarchical relations of plans on the fly. Case studies using a blocks world domain and unreal tournament video game demonstrate that the model can be used to execute, plan, and discover plans and procedural knowledge through experiences.