A fuzzy-logic autonomous agent, applied as a supervisory controller in a simulated environment

Abstract

An unsupervised learning system, implemented as an autonomous agent is presented. A simulation of a challenging path-planning problem is used to illustrate the agent design and demonstrate its problem solving ability. The agent, dubbed the ORG, employs fuzzy logic and clustering techniques to efficiently represent and retrieve knowledge and uses innovative sensor modeling and attention focus to process a large number of discrete stimuli. Simple initial rules are used to influence behavior and communicate intent to the agent. Self-reflection is utilized so the agent can learn from its environmental constraints and modify its own state. Speculation is utilized in the simulated environment, to produce new rules and fine-tune performance and internal parameters. Several resulting paths of the agent design are shown, and desirable side effects of the agent design are discussed.