Integrating Effective Planning Horizons into an Intelligent Systems Architecture

One metric of the intelligence of a system is its ability to perform tasks in the face of dynamic changes to the environment. This requires that an autonomous system be capable of responding appropriately to such changes. One such response is to effectively adapt the allocation of resources from planning to execution. By adapting the resource allocation between cognition and execution, an intelligent system can produce shorter plans more frequently in environments with high levels of uncertainty, while producing longer, more complex plans when the environment offers the opportunity to successfully execute complex plans. The effective planning horizon is developed from an analysis of mathematical models of classic autonomous system and from current research in cognitive science. Experimental results are presented showing the performance gain from an effective planning horizon based system. From this simplified feedback control model, the Effective Planning Horizon concept is extended to a more realistic intelligent system architecture, and the concepts of bounded rationality, intelligent heuristics and the judgment analysis "lens model" are shown to be analogs of the effective planning horizon.