Novel Robust Walking for Biped Robot Using Adaptive Neural PID Controller

DOI

10.2991/acta-14.2014.22How to use a DOI?

Keywords

Biped robot; Adaptive Neural PID (AN-PID) controller; Auto-Tuning Gain Scheduling; Robust Walking

Abstract

This paper presents the design, development and implementation of a novel adaptive neural PID (AN-PID) controller suitable for real-time robust walking biped robot control application. The unique feature of the proposed AN-PID controller is that it has highly simple and dynamic self-organizing structure, fast online-tuning speed and flexibility in online-updating. The proposed adaptive algorithm focuses on efficiently optimizing Gain Scheduling and PID weighting parameters of neural MLPNN model integrated in the proposed AN-PID controller. This implemented AN-PID controller aims to successfully control the robust walking of the highly nonlinear full-sized biped robot HUBOT-3. The performance of this novel neural-based PID controller was found to be outperforming in comparison with conventional PID controller.

Copyright

© 2014, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Anh Ho Pham Huy
AU  - Huan Tran Thien
AU  - Nam Nguyen Thanh
PY  - 2014/06
DA  - 2014/06
TI  - Novel Robust Walking for Biped Robot Using Adaptive Neural PID Controller
BT  - 2014 International Conference on Automatic Control Theory and Application
PB  - Atlantis Press
SP  - 86
EP  - 89
SN  - 2352-5398
UR  - https://doi.org/10.2991/acta-14.2014.22
DO  - 10.2991/acta-14.2014.22
ID  - HoPhamHuy2014/06
ER  -