제어로봇시스템학회:학술대회논문집
- 2004.08a
- /
- Pages.640-645
- /
- 2004
Self-Recurrent Wavelet Neural Network Based Direct Adaptive Control for Stable Path Tracking of Mobile Robots
- You, Sung-Jin (Department of Electrical and Electronic Engineering, Yonsei University) ;
- Oh, Joon-Seop (Department of Electrical and Electronic Engineering, Yonsei University) ;
- Park, Jin-Bae (Department of Electrical and Electronic Engineering, Yonsei University) ;
- Choi, Yoon-Ho (School of Electronic Engineering, Kyonggi University)
- Published : 2004.08.25
Abstract
This paper proposes a direct adaptive control method using self-recurrent wavelet neural network (SRWNN) for stable path tracking of mobile robots. The architecture of the SRWNN is a modified model of the wavelet neural network (WNN). Unlike the WNN, since a mother wavelet layer of the SRWNN is composed of self-feedback neurons, the SRWNN has the ability to store the past information of the wavelet. For this ability of the SRWNN, the SRWNN is used as a controller with simpler structure than the WNN in our on-line control process. The gradient-descent method with adaptive learning rates (ALR) is applied to train the parameters of the SRWNN. The ALR are derived from discrete Lyapunov stability theorem, which are used to guarantee the stable path tracking of mobile robots. Finally, through computer simulations, we demonstrate the effectiveness and stability of the proposed controller.
Keywords
- Direct adaptive control;
- Self-recurrent wavelet neural network;
- Gradient-descent method;
- Adaptive learning rate;
- Mobile robot