English

Temporal Deep Unfolding for Nonlinear Maximum Hands-off Control

Optimization and Control 2021-08-16 v2 Systems and Control Systems and Control

Abstract

This paper proposes a computational technique based on "deep unfolding" to solving the finite-time maximum hands-off control problem for discrete-time nonlinear stochastic systems. In particular, we seek a sparse control input sequence that stabilizes the system such that the expected value of the square of the final states is small by training a deep neural network. The proposed technique is demonstrated by a numerical experiment.

Keywords

Cite

@article{arxiv.2104.01755,
  title  = {Temporal Deep Unfolding for Nonlinear Maximum Hands-off Control},
  author = {Masako Kishida and Masaki Ogura},
  journal= {arXiv preprint arXiv:2104.01755},
  year   = {2021}
}

Comments

Accepted as a position paper for SICE Annual Conference 2021

R2 v1 2026-06-24T00:50:50.313Z