Vol.3, No 15, 2003 pp.1039-1054
UDC 62-52+681.53+681.58
Invited Paper

---

APPLICATION OF THE TAKAGI-SUGENO
FUZZY CONTROLLER FOR SOLVING
THE ROBOTS' INVERSE KINEMATICS PROBLEM
Vesna Ranković, Ilija Nikolić
Faculty of Mechanical Engineering,
Sestre Janjić 6, 34000 Kragujevac, Serbia and Montenegro, e-mail: inikolic@ptt.yu

---

Abstract. For mapping from external to internal coordinates the Takagi-Sugeno controller is used, implemented within the framework of adaptive network, which is similar, by its architecture, to RBF neural network, so it is also called the neuro-fuzzy system. During the learning process, the parameters of the membership functions of the primary fuzzy sets and parameters of the consequences of the Takagi-Sugeno controller were adapted. The results are presented for the straight-line trajectory tracking, with the constant velocity of the gripper and with the triangular velocity profile.

---

PRIMENA TAKAGI-SUGENO FUZZY KONTROLERA ZA RE[AVANJE PROBLEMA INVERZNE KINEMATIKE ROBOTA Za preslikavanje iz spoljašnjih u unutrašnje koordinate je korišćen Takagi-Sugeno kontroler, implementiran u adaptivnu mrežu, koji je po arhitekturi sličan RBF neuronskoj mreži, pa se takodje naziva neuro fuzzy sistemom. Tokom procesa učenja su adaptirani parametri funkcija pripadnosti primarnih fuzzy skupova i parametri posledica Takagi-Sugeno kontrolera. Prikazani rezultati se odnose na praćenje pravolinijske trajektorije sa konstantnom brzinom hvataljke i trougaonim profilom brzine.