Comparative Study of Compensating Schemes for Robotic Manipulators  

Oleh:

Meng Joo Er ; Deng, Chang

Jenis: Article from Article
Dalam koleksi: Final Program and Book of Abstracts: The 4th Asian Control Conference, September 25-27, 2002 (Sep. 2002), page 1350-1355.
Topik: Robotic Manipulators; Radial Basis Function; RBF Neural Network; Dynamic Fuzzy
Fulltext: AC021612.PDF (269.96KB)

Isi artikel

This paper compares performances of two tracking control schemes for robots in joint space. Both control algorithms are based on the conventional Proportional and Derivative (PD) controller and a compensating scheme. However, the compensating scheme is realized by different approaches. One uses a static Radial Basis Function (RBF) neural network, which is designed to guarantee system stability and to improve tracking performance of the robot manipulator. The other approach uses the dynamic fuzzy neural network, which is designed to learn the manipulator’s inverse characteristics and employs the inverse dynamic model to generate the compensating control signal. In this approach, robot models are not required and simulation studies show that the tracking error of the latter approach converges to zero faster than the fixed-structure RBF compensating scheme

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali