Hybrid Dynamic Fuzzy Cognitive Maps Evolution for autonomous navigation system

Abstract

This work develops a knowledge-based system to autonomous navigation using Fuzzy Cognitive Maps (FCM). A new variant of FCM, named Hybrid-Dynamic Fuzzy Cognitive Maps (HD-FCM), is used to model decision tasks and/or to make inference into a mobile navigation context. Fuzzy Cognitive Maps are a tool that model qualitative structured knowledge through concepts and causal relationships. The proposed model allows representing the dynamic behavior of a mobile robot in presence of environment changes. A brief review of correlated works in the navigation area, using FCM evolutions, is presented. Some simulation results are discussed and compared with Weighted Fuzzy System for shows the ability of the mobile to navigate among obstacles in different scenarios (navigation environment).