System Identification: Sparse Nonlinear Models with Control

preview_player
Показать описание
This lecture explores an extension of the sparse identification of nonlinear dynamics (SINDy) algorithm to include inputs and control. The resulting SINDY with control (SINDYc) can be used with model predictive control for nonlinear systems.

Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
E. Kaiser, J. N. Kutz, and S. L. Brunton, arxiv 2017.

This video was produced at the University of Washington
Рекомендации по теме
Комментарии
Автор

Great lecture! All clear! I used SINDY in my research of algorithms of target tracking for automotive transportation systems. Special thanks for picture from "Nu pahadi!"- favourite Soviet cartoon of my childhood on 4:24. Greetings from Russia!

aliscander
Автор

Amazing research and presentation. Thank you so much for putting out these videos here - the best I've seen until now!

BenjaminKelm
Автор

how can this be applied on a real plant data set in an n x m matrix where n>m

TheTibasiima
Автор

I have not seen an application of nonlinear control in the workplace ever. I find this stuff super cool but lack the motivation to learn it if I can never apply it. Can you provide a video that details th inspiration for these methods?

closingtheloop
Автор

How does this work for multi (n) input systems? Do you just make n columns and proceed similarly?

joelhwee
Автор

Can not we use Support Vector Machine (SVM) or Random Forest Regression etc. for this?

indramal
Автор

please what's the link to the video of the original SInDy?

AdeyemiAlabi