Loading…

Output Feedback Self-tuning Wavenet Control for Underactuated Euler-Lagrange Systems

There exist some physical systems whose underactuation and limited sensing represent a challenge in engineering. The former requires a model-based nesting or virtual control schemes to control the underactuated degrees of freedom through the actuated ones, while the latter imposes stringent requirem...

Full description

Saved in:
Bibliographic Details
Published in:IFAC-PapersOnLine 2018, Vol.51 (13), p.633-638
Main Authors: Navarrete, M.A. Vega, Velasco, L.E. Ramos, Mayorga, C.R. Domínguez, Carreón, P.A. Arizpe, Hernández, J. Valle, Romero, V.M. Delgado, Parra-Vega, V., Vera, M.A. Marquéz
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:There exist some physical systems whose underactuation and limited sensing represent a challenge in engineering. The former requires a model-based nesting or virtual control schemes to control the underactuated degrees of freedom through the actuated ones, while the latter imposes stringent requirements to design the controller using only partial access to the state, called output feedback. In this paper, we address the output feedback control design of class of uncertain underactuated nonlinear systems that is not model-based neither require state estimation. Output feedback and underactuation are circumvented by synthesizing an efficient RFB-based superwavelets neural network that approximates inverse dynamics of the projected actuated subsystem. Using multiresolution scaling with only position, feedback gains are adapted online based on a self-tuning scheme. An illustrative simulation study is presented for the underactuated inverted pendulum-on-a-cart using only angular position.
ISSN:2405-8963
2405-8963
DOI:10.1016/j.ifacol.2018.07.351