Fuzzy estimation of the robot load
| Authors: | Rojko Andreja, University of Maribor, Faculty of electrical engineering, Slovenia
Jezernik Karel, University of Maribor, Faculty of electrical engineering, Slovenia |
|---|
| Topic: | 3.2 Cognition and Control ( AI, Fuzzy, Neuro, Evolut.Comp.) |
|---|
| Session: | Adaptive Neuro-fuzzy Control |
|---|
| Keywords: | motion control, adaptive control, robot dynamics, fuzzy system |
|---|
Abstract
This paper considers the problem of the robot motion control in a presence of the major uncertainties such as the varying load. The proposed adaptive fuzzy system (FLS) is employed to estimate dynamic influence of the varying load and also the major part of the mechanism dynamics. Carefully designed membership functions and rules preserve the interpretability of FLS as each rule works toward estimation of the specific part of dynamics. The fuzzy estimator is implemented in the control scheme similar to the computed torque control. The effectiveness of the approach is demonstrated through the application on the three degree of freedom direct drive robot.
