A simplifying diagrammatic representation of crisp and fuzzy teleo-reactive semantic circuitry for application in robotic agent task control

摘要

The Teleo-Reactive paradigm for computing and organizing actions for autonomous agents in dynamic environments is intended to enable the construction of semantic circuitry for the continuous computation of parameters and conditions on which agent action is based. However both crisp and fuzzy semantic circuitry suffers from complexity growth. The paper describes a representation for simplifying semantic circuits capable of realizing both crisp and fuzzy Teleo-Reactive sequences. The new representation supports any combination of primitive actions, action sets, and non-primitive sub-circuit actions while reducing the semantic circuitry complexity. The proposed representation is constructed by identifying the repetition of semantic components and abstracting them into a standard EISA model.