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

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.

A Practical Neuro-fuzzy Mapping and Control for a 2 DOF Robotic Arm System

“…Furthermore, Lazarevska [8] have introduced a Neurofuzzy modeling network for the issue of inverse kinematics problem of a 4 DOF robotic arm. In this context, the manuscript presented a detailed structure of Neuro-fuzzy model of the inverse kinematics of 4 DOF robotic arm employing the relevance vector learning algorithm.…”

“…In this context, the manuscript presented a detailed structure of Neuro-fuzzy model of the inverse kinematics of 4 DOF robotic arm employing the relevance vector learning algorithm. Lazarevska [8] has stated that, "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". Hence, the presented model was based on the use of a TakagiSugeno 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.…”

Hybrid learning model and MMSVM classification for on-line visual imitation of a human with 3-D motions

“…To accomplish the corresponding task, the computation time of inverse kinematics (IK) must be short enough. In addition, one-to-many or one-to-none mapping of IK is difficult to deal with (e.g., [21][22][23][24][25]). To enhance one-to-one mapping of IK, the work space of each arm is partitioned into four subwork spaces.…”

Neural Net Control of High Nonlinear 2-DOF Nonlinear Robotic Arm

“…In their research efforts, they presented a novel Neuro-fuzzy controller synthesis for robotic manipulators control. Other similar efforts are also mentioned in [4], [5], and [6]. One of the ANN applications is done by Bogdanov and Timofeev [7] where a ANN controller is used to compensate dynamics approximation errors in the model of the two link robotic system thus providing robust control.…”