Deep Robust Control of a Mechatronic System With Parametric Uncertainties

Daulet Baimukashev, Yerzhan Rzagaliyev, Matteo Rubagotti, Huseyin Atakan Varol

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a method for controller approximation via neural network in the presence of parametric perturbations. The neural network is based on long short-term memory blocks and is trained to approximate a numerical optimal control law, solved for different parameter values. Using this approach, the obtained approximate control law learns to generate the control inputs based on different optimal control solutions for different parameters: as compared to training the neural network only based on the optimal control law defined for the nominal parameters, the overall system performance greatly improves when parameter variations are present, and does not degrade when the nominal parameters are used for testing. The proposed approach is validated experimentally on an inverted pendulum with dual-axis reaction wheels.

Original languageEnglish
Title of host publication2022 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1031-1038
Number of pages8
ISBN (Electronic)9781665413084
DOIs
Publication statusPublished - 2022
Event2022 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2022 - Sapporo, Japan
Duration: Jul 11 2022Jul 15 2022

Publication series

NameIEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM
Volume2022-July

Conference

Conference2022 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2022
Country/TerritoryJapan
CitySapporo
Period7/11/227/15/22

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications
  • Software

Fingerprint

Dive into the research topics of 'Deep Robust Control of a Mechatronic System With Parametric Uncertainties'. Together they form a unique fingerprint.

Cite this