An optimized Takagi-Sugeno type neuro-fuzzy system for modeling robot manipulators

The present paper describes the development of a Takagi-Sugeno (TS)-type Neuro-fuzzy system (NFS) for dynamic modeling of robot manipulators. The NFS has been trained by a relatively new combinatorial metaheuristic optimization method, called particle swarm optimization (PSO). The development of such an intelligent, robust, dynamic models for robot manipulators can immensely help in deriving proper position/velocity control strategies in offline situations with these accurately developed models. The proposed PSO-based NFS has been successfully applied to two-link and three-link model robot manipulators.