A Neuro-fuzzy Model of the Inverse Kinematics of a 4 DOF Robotic Arm

The paper presents a neuro-fuzzy model of the inverse kinematics of 4 DOF robotic arm employing the relevance vector learning algorithm. Although the direct kinematics of the robotic arm can be modeled with ease by the same approach, the paper focuses on the much more interesting kinematic task, since its solution presents a basis for robot control design. The presented model is of a Takagi-Sugeno type, but its parameters and number of fuzzy rules are automatically generated and optimized through the adopted learning algorithm based on M. E. Tipping's relevance vector machine. The presented model illustrates the effectiveness of the adopted neuro-fuzzy modeling approach.