Unscented Kalman Filter-Trained Neural Networks for Slip Model Prediction.

Unscented Kalman Filter-Trained Neural Networks for Slip Model Prediction.

The purpose of this work is to investigate the accurate trajectory tracking control of a wheeled mobile robot (WMR) based on the slip model prediction. Generally, a nonholonomic WMR may increase the slippage risk, when traveling on outdoor unstructured terrain (such as longitudinal and lateral slipp...

Full description

Bibliographic Details
Main Authors: Zhencai Li, Yang Wang, Zhen Liu
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2016-01-01
Series:PLoS ONE
Online Access:http://europepmc.org/articles/PMC4965072?pdf=render
id doaj-70bd653e1ca4420cb0153d2262b07117
record_format Article
spelling doaj-70bd653e1ca4420cb0153d2262b071172020-11-24T22:12:25ZengPublic Library of Science (PLoS)PLoS ONE1932-62032016-01-01117e015849210.1371/journal.pone.0158492Unscented Kalman Filter-Trained Neural Networks for Slip Model Prediction.Zhencai LiYang WangZhen LiuThe purpose of this work is to investigate the accurate trajectory tracking control of a wheeled mobile robot (WMR) based on the slip model prediction. Generally, a nonholonomic WMR may increase the slippage risk, when traveling on outdoor unstructured terrain (such as longitudinal and lateral slippage of wheels). In order to control a WMR stably and accurately under the effect of slippage, an unscented Kalman filter and neural networks (NNs) are applied to estimate the slip model in real time. This method exploits the model approximating capabilities of nonlinear state-space NN, and the unscented Kalman filter is used to train NN's weights online. The slip parameters can be estimated and used to predict the time series of deviation velocity, which can be used to compensate control inputs of a WMR. The results of numerical simulation show that the desired trajectory tracking control can be performed by predicting the nonlinear slip model.http://europepmc.org/articles/PMC4965072?pdf=render
collection DOAJ
language English
format Article
sources DOAJ
author Zhencai Li
Yang Wang
Zhen Liu
spellingShingle Zhencai Li
Yang Wang
Zhen Liu
Unscented Kalman Filter-Trained Neural Networks for Slip Model Prediction.
PLoS ONE
author_facet Zhencai Li
Yang Wang
Zhen Liu
author_sort Zhencai Li
title Unscented Kalman Filter-Trained Neural Networks for Slip Model Prediction.
title_short Unscented Kalman Filter-Trained Neural Networks for Slip Model Prediction.
title_full Unscented Kalman Filter-Trained Neural Networks for Slip Model Prediction.
title_fullStr Unscented Kalman Filter-Trained Neural Networks for Slip Model Prediction.
title_full_unstemmed Unscented Kalman Filter-Trained Neural Networks for Slip Model Prediction.
title_sort unscented kalman filter-trained neural networks for slip model prediction.
publisher Public Library of Science (PLoS)
series PLoS ONE
issn 1932-6203
publishDate 2016-01-01
description The purpose of this work is to investigate the accurate trajectory tracking control of a wheeled mobile robot (WMR) based on the slip model prediction. Generally, a nonholonomic WMR may increase the slippage risk, when traveling on outdoor unstructured terrain (such as longitudinal and lateral slippage of wheels). In order to control a WMR stably and accurately under the effect of slippage, an unscented Kalman filter and neural networks (NNs) are applied to estimate the slip model in real time. This method exploits the model approximating capabilities of nonlinear state-space NN, and the unscented Kalman filter is used to train NN's weights online. The slip parameters can be estimated and used to predict the time series of deviation velocity, which can be used to compensate control inputs of a WMR. The results of numerical simulation show that the desired trajectory tracking control can be performed by predicting the nonlinear slip model.
url http://europepmc.org/articles/PMC4965072?pdf=render
work_keys_str_mv AT zhencaili unscentedkalmanfiltertrainedneuralnetworksforslipmodelprediction
AT yangwang unscentedkalmanfiltertrainedneuralnetworksforslipmodelprediction
AT zhenliu unscentedkalmanfiltertrainedneuralnetworksforslipmodelprediction
_version_ 1725803817481535488

Similar Items