Title
Fast and Stable Learning of Dynamical Systems Based on Extreme Learning Machine
Abstract
The approach of dynamical system (DS) is promising for modeling robot motion, and provides a flexible means of realizing robot learning and control. Accuracy, stability, and learning speed are the three main factors to be considered when learning robot movements from human demonstrations with DS. Some approaches yield stable dynamical systems, but these may result in a poor reproduction performanc...
Year
DOI
Venue
2019
10.1109/TSMC.2017.2705279
IEEE Transactions on Systems, Man, and Cybernetics: Systems
Keywords
Field
DocType
Stability analysis,Asymptotic stability,Training,Trajectory,Robot motion,Dynamics
Robot learning,Online machine learning,Stability (learning theory),Active learning (machine learning),Extreme learning machine,Computer science,Control theory,Dynamical systems theory,Artificial intelligence,Computational learning theory,Robot,Machine learning
Journal
Volume
Issue
ISSN
49
6
2168-2216
Citations 
PageRank 
References 
10
0.53
9
Authors
6
Name
Order
Citations
PageRank
Jianghua Duan1122.26
Yongsheng Ou224342.32
Jianbing Hu3242.62
Zhiyang Wang4100.87
Shaokun Jin5102.22
Chao Xu613633.20