Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models

被引：526

作者：

Khansari-Zadeh, S. Mohammad ^{[1
]}

Billard, Aude ^{[1
]}

机构：

[1] Ecole Polytech Fed Lausanne, Sch Engn, CH-1015 Lausanne, Switzerland

来源：

IEEE TRANSACTIONS ON ROBOTICS | 2011年 / 27卷 / 05期

关键词：

Dynamical systems (DS); Gaussian mixture model; imitation learning; point-to-point motions; stability analysis;

D O I：

10.1109/TRO.2011.2159412

中图分类号：

TP24 [机器人技术];

学科分类号：

080202 ; 1405 ;

摘要：

This paper presents a method to learn discrete robot motions from a set of demonstrations. We model a motion as a nonlinear autonomous (i.e., time-invariant) dynamical system (DS) and define sufficient conditions to ensure global asymptotic stability at the target. We propose a learning method, which is called Stable Estimator of Dynamical Systems (SEDS), to learn the parameters of the DS to ensure that all motions closely follow the demonstrations while ultimately reaching and stopping at the target. Time-invariance and global asymptotic stability at the target ensures that the system can respond immediately and appropriately to perturbations that are encountered during the motion. The method is evaluated through a set of robot experiments and on a library of human handwriting motions.

引用

页码：943 / 957

页数：15

共 50 条

[11] Nonlinear prediction for Gaussian mixture image models
Zhang, J
Ma, DH
VISUAL COMMUNICATIONS AND IMAGE PROCESSING 2001, 2001, 4310 : 99 - 110
[12] Variational Bayesian mixture of experts models and sensitivity analysis for nonlinear dynamical systems
Baldacchino, Tara
Cross, Elizabeth J.
Worden, Keith
Rowson, Jennifer
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2016, 66-67 : 178 - 200
[13] Parametric Manifold Learning of Gaussian Mixture Models
Liu, Ziquan
Yu, Lei
Hsiao, Janet H.
Chan, Antoni B.
PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 3073 - 3079
[14] Generalized Competitive Learning of Gaussian Mixture Models
Lu, Zhiwu
Ip, Horace H. S.
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2009, 39 (04): : 901 - 909
[15] Incremental Learning of Multivariate Gaussian Mixture Models
Engel, Paulo Martins
Heinen, Milton Roberto
ADVANCES IN ARTIFICIAL INTELLIGENCE - SBIA 2010, 2010, 6404 : 82 - 91
[16] Efficient greedy learning of Gaussian mixture models
Verbeek, JJ
Vlassis, N
Kröse, B
NEURAL COMPUTATION, 2003, 15 (02) : 469 - 485
[17] Entropy Penalized Learning for Gaussian Mixture Models
Wang, Boyu ksa
Wan, Feng
Mak, Peng Un
Mak, Pui In
Vai, Mang I.
2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2011, : 2067 - 2073
[18] Multidirectional Gaussian Mixture Models for Nonlinear Uncertainty Propagation
Vittaldev, V.
Russell, R. P.
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES, 2016, 111 (01): : 83 - 117
[19] Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systems
Schlaginhaufen, Andreas
Wenk, Philippe
Krause, Andreas
Dorfler, Florian
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
[20] Machine Learning in Nonlinear Dynamical Systems
Sayan Roy
Debanjan Rana
Resonance, 2021, 26 : 953 - 970

← 1 2 3 4 5 →