Neuro-fuzzy control of a robot manipulator for a trajectory design

The primary weakness of previous methods for a trajectory design is the massive amount of computer time needed to obtain a solution. Neuro-fuzzy systems combined neural network and fuzzy logic offer not only the characteristics of parallel processing, but also the ability to learn the trajectory of a robot manipulator. In this paper, we studied a trajectory design problem of a robot manipulator using a neuro-fuzzy systems. The technique of this neuro-fuzzy system replaces the rule base of a traditional fuzzy logic system with a backpropagation neural network. The definition of the fuzzy membership functions used to the fuzzification and defuzzification of the input and output variables plays a significant role in the ability of the neuro-fuzzy controller to learn and generalize. Finally, the validity of the proposed technique was tested using a planar manipulator