An intelligent hybrid artificial neural network-based approach for control of aerial robots
In this work, a learning model-free control method is proposed for accurate trajectory tracking and safe landing of unmanned aerial vehicles (UAVs). A realistic scenario is considered where the UAV commutes between stations at high-speeds, experiences a single motor failure while surveying an area,...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/141625 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-141625 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1416252020-07-29T07:52:25Z An intelligent hybrid artificial neural network-based approach for control of aerial robots Patel, Siddharth Sarabakha, Andriy Kircali, Dogan Kayacan, Erdal School of Electrical and Electronic Engineering School of Mechanical and Aerospace Engineering Library ST Engineering - NTU Corporate Lab Engineering::Electrical and electronic engineering Artificial Neural Networks Sliding Mode Control In this work, a learning model-free control method is proposed for accurate trajectory tracking and safe landing of unmanned aerial vehicles (UAVs). A realistic scenario is considered where the UAV commutes between stations at high-speeds, experiences a single motor failure while surveying an area, and thus requires to land safely at a designated secure location. The proposed challenge is viewed solely as a control problem. A hybrid control architecture – an artificial neural network (ANN)-assisted proportional-derivative controller – is able to learn the system dynamics online and compensate for the error generated during different phases of the considered scenario: fast and agile flight, motor failure, and safe landing. Firstly, it deals with unmodelled dynamics and operational uncertainties and demonstrates superior performance compared to a conventional proportional-integral-derivative controller during fast and agile flight. Secondly, it behaves as a fault-tolerant controller for a single motor failure case in a coaxial hexacopter thanks to its proposed sliding mode control theory-based learning architecture. Lastly, it yields reliable performance for a safe landing at a secure location in case of an emergency condition. The tuning of weights is not required as the structure of the ANN controller starts to learn online, each time it is initialised, even when the scenario changes – thus, making it completely model-free. Moreover, the simplicity of the neural network-based controller allows for the implementation on a low-cost low-power onboard computer. Overall, the real-time experiments show that the proposed controller outperforms the conventional controller. Accepted version 2020-06-09T08:44:47Z 2020-06-09T08:44:47Z 2019 Journal Article Patel, S., Sarabakha, A., Kircali, D., & Kayacan, E. (2020). An intelligent hybrid artificial neural network-based approach for control of aerial robots. Journal of Intelligent & Robotic Systems, 97, 387-398. doi:10.1007/s10846-019-01031-z 0921-0296 https://hdl.handle.net/10356/141625 10.1007/s10846-019-01031-z 2-s2.0-85065424799 97 387 398 en Journal of Intelligent & Robotic Systems © 2019 Springer Nature B.V. This is a post-peer-review, pre-copyedit version of an article published in Journal of Intelligent & Robotic Systems. The final authenticated version is available online at: http://dx.doi.org/10.1007/s10846-019-01031-z application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering Artificial Neural Networks Sliding Mode Control |
spellingShingle |
Engineering::Electrical and electronic engineering Artificial Neural Networks Sliding Mode Control Patel, Siddharth Sarabakha, Andriy Kircali, Dogan Kayacan, Erdal An intelligent hybrid artificial neural network-based approach for control of aerial robots |
description |
In this work, a learning model-free control method is proposed for accurate trajectory tracking and safe landing of unmanned aerial vehicles (UAVs). A realistic scenario is considered where the UAV commutes between stations at high-speeds, experiences a single motor failure while surveying an area, and thus requires to land safely at a designated secure location. The proposed challenge is viewed solely as a control problem. A hybrid control architecture – an artificial neural network (ANN)-assisted proportional-derivative controller – is able to learn the system dynamics online and compensate for the error generated during different phases of the considered scenario: fast and agile flight, motor failure, and safe landing. Firstly, it deals with unmodelled dynamics and operational uncertainties and demonstrates superior performance compared to a conventional proportional-integral-derivative controller during fast and agile flight. Secondly, it behaves as a fault-tolerant controller for a single motor failure case in a coaxial hexacopter thanks to its proposed sliding mode control theory-based learning architecture. Lastly, it yields reliable performance for a safe landing at a secure location in case of an emergency condition. The tuning of weights is not required as the structure of the ANN controller starts to learn online, each time it is initialised, even when the scenario changes – thus, making it completely model-free. Moreover, the simplicity of the neural network-based controller allows for the implementation on a low-cost low-power onboard computer. Overall, the real-time experiments show that the proposed controller outperforms the conventional controller. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Patel, Siddharth Sarabakha, Andriy Kircali, Dogan Kayacan, Erdal |
format |
Article |
author |
Patel, Siddharth Sarabakha, Andriy Kircali, Dogan Kayacan, Erdal |
author_sort |
Patel, Siddharth |
title |
An intelligent hybrid artificial neural network-based approach for control of aerial robots |
title_short |
An intelligent hybrid artificial neural network-based approach for control of aerial robots |
title_full |
An intelligent hybrid artificial neural network-based approach for control of aerial robots |
title_fullStr |
An intelligent hybrid artificial neural network-based approach for control of aerial robots |
title_full_unstemmed |
An intelligent hybrid artificial neural network-based approach for control of aerial robots |
title_sort |
intelligent hybrid artificial neural network-based approach for control of aerial robots |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/141625 |
_version_ |
1681058510982348800 |