Walking pattern analysis of humanoid robot using support vector regression

Authors:
Dongwon Kim;Gwi-Tae Park
Affiliations:
Department of Electrical Engineering, Korea University, Seoul, Korea;Department of Electrical Engineering, Korea University, Seoul, Korea
Venue:
KES'06 Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part III
Year:
2006

Citing 3
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
Fuzzy support vector machines

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work presents walking pattern analysis of a humanoid robot using support vector regression. The humanoid robot is highly suitable to work in human environments but the dynamics involved are highly nonlinear and unstable. So we are establishing empirical relationships based on the walking pattern analysis as dynamic stability of motion. Zero moment point is usually used as a basic component for dynamically stable motion. Kernel method and support vector machines (SVM) have become very popular as methods for learning from examples. We apply SVM to analyze humanoid robot walking. The experimental results show that the SVM based on the kernel substitution provides a promising alternative to model robot movements but also to control actual humanoid robots.