Title :
A Neuro-fuzzy Model of the Inverse Kinematics of a 4 DOF Robotic Arm
Author :
Lazarevska, Elizabeta
Author_Institution :
Fac. of Electr. Eng. & Inf. Technol., Univ. St. Cyril & Methodius, Skopje, Macedonia
Abstract :
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.
Keywords :
control system synthesis; fuzzy neural nets; learning (artificial intelligence); neurocontrollers; robot kinematics; 4 DOF robotic arm; M. E. Tipping relevance vector machine; Takagi-Sugeno model; adopted learning algorithm; fuzzy rules; inverse kinematics; kinematic task; neurofuzzy modeling approach; relevance vector learning algorithm; robot control design; Data models; Kernel; Kinematics; Mathematical model; Robots; Support vector machines; Vectors; inverse kinematics; neuro-fuzzy model; relevance vector machine; robotic arm;
Conference_Titel :
Computer Modelling and Simulation (UKSim), 2012 UKSim 14th International Conference on
Conference_Location :
Cambridge
Print_ISBN :
978-1-4673-1366-7
DOI :
10.1109/UKSim.2012.51