Cover Image

Stability-certified deep reinforcement learning strategy for UAV and lagrangian floating platform

This paper presents a robust technique for an Unmanned Aerial Vehicle (UAV) with the ability to fly above a moving platform autonomously. The purpose of the study is to investigate the problem of certifying stability of reinforcement learning policy when linked with nonlinear dynamical systems since...

Full description

Saved in:
Bibliographic Details
Main Authors: Muslim, M. S. M., Ismail, Z. H.
Format: Conference or Workshop Item
Published: 2021
Subjects:
T Technology (General)
Online Access:http://eprints.utm.my/id/eprint/95750/
http://dx.doi.org/10.1109/ECTI-CON51831.2021.9454688
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.95750
record_format eprints
spelling my.utm.957502022-05-31T13:18:40Z http://eprints.utm.my/id/eprint/95750/ Stability-certified deep reinforcement learning strategy for UAV and lagrangian floating platform Muslim, M. S. M. Ismail, Z. H. T Technology (General) This paper presents a robust technique for an Unmanned Aerial Vehicle (UAV) with the ability to fly above a moving platform autonomously. The purpose of the study is to investigate the problem of certifying stability of reinforcement learning policy when linked with nonlinear dynamical systems since conventional control methods often fail to properly account for complex effects. However, deep reinforcement learning algorithms have been designed to monitor the robust stability of a UAV's position in three-dimensional space, such as altitude and longitude-latitude location, so that the UAV can fly over a moving platform in a stable manner. Plus, the input-output policy gradient method is regulated and capable of approving a large number of stabilization controllers to obtain robust stability by exploiting problem-specific structure. Inside the stability-certified parameter space, reinforcement learning agents will attain high efficiency while also exhibiting consistent learning behaviors over time, according to a formula assessment on a decentralized control task involving flight creation. 2021 Conference or Workshop Item PeerReviewed Muslim, M. S. M. and Ismail, Z. H. (2021) Stability-certified deep reinforcement learning strategy for UAV and lagrangian floating platform. In: 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2021, 19 May 2021 - 22 May 2021, Chiang Mai. http://dx.doi.org/10.1109/ECTI-CON51831.2021.9454688
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic T Technology (General)
spellingShingle T Technology (General)
Muslim, M. S. M.
Ismail, Z. H.
Stability-certified deep reinforcement learning strategy for UAV and lagrangian floating platform
description This paper presents a robust technique for an Unmanned Aerial Vehicle (UAV) with the ability to fly above a moving platform autonomously. The purpose of the study is to investigate the problem of certifying stability of reinforcement learning policy when linked with nonlinear dynamical systems since conventional control methods often fail to properly account for complex effects. However, deep reinforcement learning algorithms have been designed to monitor the robust stability of a UAV's position in three-dimensional space, such as altitude and longitude-latitude location, so that the UAV can fly over a moving platform in a stable manner. Plus, the input-output policy gradient method is regulated and capable of approving a large number of stabilization controllers to obtain robust stability by exploiting problem-specific structure. Inside the stability-certified parameter space, reinforcement learning agents will attain high efficiency while also exhibiting consistent learning behaviors over time, according to a formula assessment on a decentralized control task involving flight creation.
format Conference or Workshop Item
author Muslim, M. S. M.
Ismail, Z. H.
author_facet Muslim, M. S. M.
Ismail, Z. H.
author_sort Muslim, M. S. M.
title Stability-certified deep reinforcement learning strategy for UAV and lagrangian floating platform
title_short Stability-certified deep reinforcement learning strategy for UAV and lagrangian floating platform
title_full Stability-certified deep reinforcement learning strategy for UAV and lagrangian floating platform
title_fullStr Stability-certified deep reinforcement learning strategy for UAV and lagrangian floating platform
title_full_unstemmed Stability-certified deep reinforcement learning strategy for UAV and lagrangian floating platform
title_sort stability-certified deep reinforcement learning strategy for uav and lagrangian floating platform
publishDate 2021
url http://eprints.utm.my/id/eprint/95750/
http://dx.doi.org/10.1109/ECTI-CON51831.2021.9454688
_version_ 1735386842678689792
score 13.244745

Similar Items