This paper proposes a computational technique based on deep unfolding to solve the finite-time maximum hands-off control problem for discrete-timenonlinear stochastic systems . We seek a sparse control inputsequence that stabilizes the system such that the expected value of the square of the final states is small by training a deep neural network .

Author(s) : Masako Kishida, Masaki Ogura

Links : PDF - Abstract

Code :

https://github.com/nhynes/abc


Coursera

Keywords : deep - control - maximum - unfolding - hands -

Leave a Reply

Your email address will not be published. Required fields are marked *