A model of feedback error learning based on Kalman estimator - Details

Author：

Ruan, Xiaogang (Ruan, Xiaogang.) | Liu, Liang (Liu, Liang.) | Yu, Naigong (Yu, Naigong.) (Scholars：于乃功) | Ding, Mingxiao (Ding, Mingxiao.)

Indexed by：

EI Scopus

Abstract：

Based　on　the　Feedback　error　learning　(FEL)　method　and　Michael　et　al.＇s　research　work　on　dynamical　state　estimation,　a　new　model　of　motor　control　system　is　proposed　to　overcome　the　drawback　deriving　from　time　delay.　In　the　new　model,　the　supervised　signal　derives　from　both　the　output　of　the　Kalman　estimator　and　the　feedback　motor　command,　and　this　comprehensive　signal　provides　the　instructive　information　to　train　the　forward　neural　network　in　the　cerebellar　cortex.　The　effectiveness　of　the　proposed　new　model　is　demonstrated　by　simulation　experiments　on　inverted　pendulum.　©2006　IEEE.

Keyword：

Kalman filters Information retrieval Error analysis Feedback Mathematical models Learning systems Computer simulation

Author Community：

[ 1 ] [Ruan, Xiaogang]Department of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China
[ 2 ] [Liu, Liang]Department of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China
[ 3 ] [Yu, Naigong]Department of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China
[ 4 ] [Ding, Mingxiao]Department of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100022, China