Model-free Based Reinforcement Learning Control Strategy of Aircraft Attitude Systems

Dingcui Huang, Jiangping Hu, Zhinan Peng, Bo Chen, Mingrui Hao, Bijoy Kumar Ghosh

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Traditional aircraft control algorithms have a strong dependence on system models, and are difficult to cope with the increasingly complex battlefield environment for intelligent aircrafts. In this paper, a model-free reinforcement learning is proposed to solve an attitude stabilization problem of an aircraft based online intelligent control strategy. The attitude control problem is firstly formulated as an optimal control problem, and then an adaptive dynamic programming (ADP) technology is applied to compute the corresponding nonlinear Hamilton-Jacobi-Bellman (HJB) equation. Then, an actor-critic neural network structure is established to learn the optimal controller online not requiring the information of the aircraft dynamics. The proposed intelligent control strategy enables the aircraft to adjust its attitude according to the actual mission targets and environments under the proposed online control strategy, so that autonomous learning and intelligent operation can be realized. Finally, simulation examples are presented to validate the proposed model-free based control strategy.

Original languageEnglish
Title of host publicationProceedings - 2020 Chinese Automation Congress, CAC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages743-748
Number of pages6
ISBN (Electronic)9781728176871
DOIs
StatePublished - Nov 6 2020
Event2020 Chinese Automation Congress, CAC 2020 - Shanghai, China
Duration: Nov 6 2020Nov 8 2020

Publication series

NameProceedings - 2020 Chinese Automation Congress, CAC 2020

Conference

Conference2020 Chinese Automation Congress, CAC 2020
CountryChina
CityShanghai
Period11/6/2011/8/20

Keywords

  • Actor-Critic Neural Network
  • Aircraft Attitude System
  • Model-Free Control
  • Reinforcement Learning

Fingerprint Dive into the research topics of 'Model-free Based Reinforcement Learning Control Strategy of Aircraft Attitude Systems'. Together they form a unique fingerprint.

Cite this