Adaptive UAV Swarm Mission Planning by Temporal Difference Learning

Shreevanth Krishnaa Gopalakrishnan; Saba Al-Rubaye; Gokhan Inalhan

doi:10.1109/DASC52595.2021.9594300

Adaptive UAV Swarm Mission Planning by Temporal Difference Learning

Shreevanth Krishnaa Gopalakrishnan, Saba Al-Rubaye, Gokhan Inalhan

Cranfield University

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

6 Atıf (Scopus)

Özet

The prevalence of Unmanned Aerial Vehicles (UAVs) in precision agriculture has been growing rapidly. This paper tackles the UAV global mission planning problem by incorporating a greater capacity for human-machine teaming in the architecture of a flexibly autonomous, near-fully-distributed Mission Management System for UAV swarms. Subsequently, the two problems of global mission planning are solved simultaneously using an integrated solution. This consists of a geometric clustering algorithm which prioritizes the minimization of overall mission time, and an off-policy, model-free Temporal Difference Learning global agent capable of learning about an initially unknown mission environment through simulations. The latter component makes the solution adaptive to missions with different requirements.

Orijinal dil	İngilizce
Ana bilgisayar yayını başlığı	40th Digital Avionics Systems Conference, DASC 2021 - Proceedings
Yayınlayan	Institute of Electrical and Electronics Engineers Inc.
ISBN (Elektronik)	9781665434201
DOI'lar	https://doi.org/10.1109/DASC52595.2021.9594300
Yayın durumu	Yayınlandı - 2021
Harici olarak yayınlandı	Evet
Etkinlik	40th IEEE/AIAA Digital Avionics Systems Conference, DASC 2021 - San Antonio, United States Süre: 3 Eki 2021 → 7 Eki 2021

Yayın serisi

Adı	AIAA/IEEE Digital Avionics Systems Conference - Proceedings
Hacim	2021-October
ISSN (Basılı)	2155-7195
ISSN (Elektronik)	2155-7209

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	40th IEEE/AIAA Digital Avionics Systems Conference, DASC 2021
Ülke/Bölge	United States
Şehir	San Antonio
Periyot	3/10/21 → 7/10/21

Bibliyografik not

Publisher Copyright:
© 2021 IEEE.

Finansman

ACKNOWLEDGMENT This research was supported by the grants received from Innovation UK under the program of Future Flight Challenge Phase 2: Strand 1, Development (Grant No #71017-Project Rise).

Finansörler	Finansör numarası
Innovation UK

BM SKH

Bu sonuç, aşağıdaki Sürdürülebilir Kalkınma Hedefine/Hedeflerine katkıda bulunur

Belgeye Erişim

10.1109/DASC52595.2021.9594300

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Gopalakrishnan, S. K., Al-Rubaye, S., & Inalhan, G. (2021). Adaptive UAV Swarm Mission Planning by Temporal Difference Learning. In 40th Digital Avionics Systems Conference, DASC 2021 - Proceedings (AIAA/IEEE Digital Avionics Systems Conference - Proceedings; Hac. 2021-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DASC52595.2021.9594300

@inproceedings{dca2ab938c084552968ad1536f8551f4,

title = "Adaptive UAV Swarm Mission Planning by Temporal Difference Learning",

abstract = "The prevalence of Unmanned Aerial Vehicles (UAVs) in precision agriculture has been growing rapidly. This paper tackles the UAV global mission planning problem by incorporating a greater capacity for human-machine teaming in the architecture of a flexibly autonomous, near-fully-distributed Mission Management System for UAV swarms. Subsequently, the two problems of global mission planning are solved simultaneously using an integrated solution. This consists of a geometric clustering algorithm which prioritizes the minimization of overall mission time, and an off-policy, model-free Temporal Difference Learning global agent capable of learning about an initially unknown mission environment through simulations. The latter component makes the solution adaptive to missions with different requirements.",

keywords = "Global Mission Planning, Precision Agriculture, Reinforcement Learning, Temporal Difference Learning, UAV",

author = "Gopalakrishnan, {Shreevanth Krishnaa} and Saba Al-Rubaye and Gokhan Inalhan",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 40th IEEE/AIAA Digital Avionics Systems Conference, DASC 2021 ; Conference date: 03-10-2021 Through 07-10-2021",

year = "2021",

doi = "10.1109/DASC52595.2021.9594300",

language = "English",

series = "AIAA/IEEE Digital Avionics Systems Conference - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "40th Digital Avionics Systems Conference, DASC 2021 - Proceedings",

address = "United States",

}

Gopalakrishnan, SK, Al-Rubaye, S & Inalhan, G 2021, Adaptive UAV Swarm Mission Planning by Temporal Difference Learning. in 40th Digital Avionics Systems Conference, DASC 2021 - Proceedings. AIAA/IEEE Digital Avionics Systems Conference - Proceedings, hac. 2021-October, Institute of Electrical and Electronics Engineers Inc., 40th IEEE/AIAA Digital Avionics Systems Conference, DASC 2021, San Antonio, United States, 3/10/21. https://doi.org/10.1109/DASC52595.2021.9594300

Adaptive UAV Swarm Mission Planning by Temporal Difference Learning. / Gopalakrishnan, Shreevanth Krishnaa; Al-Rubaye, Saba; Inalhan, Gokhan.
40th Digital Avionics Systems Conference, DASC 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. (AIAA/IEEE Digital Avionics Systems Conference - Proceedings; Hac. 2021-October).

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

TY - GEN

T1 - Adaptive UAV Swarm Mission Planning by Temporal Difference Learning

AU - Gopalakrishnan, Shreevanth Krishnaa

AU - Al-Rubaye, Saba

AU - Inalhan, Gokhan

PY - 2021

Y1 - 2021

N2 - The prevalence of Unmanned Aerial Vehicles (UAVs) in precision agriculture has been growing rapidly. This paper tackles the UAV global mission planning problem by incorporating a greater capacity for human-machine teaming in the architecture of a flexibly autonomous, near-fully-distributed Mission Management System for UAV swarms. Subsequently, the two problems of global mission planning are solved simultaneously using an integrated solution. This consists of a geometric clustering algorithm which prioritizes the minimization of overall mission time, and an off-policy, model-free Temporal Difference Learning global agent capable of learning about an initially unknown mission environment through simulations. The latter component makes the solution adaptive to missions with different requirements.

AB - The prevalence of Unmanned Aerial Vehicles (UAVs) in precision agriculture has been growing rapidly. This paper tackles the UAV global mission planning problem by incorporating a greater capacity for human-machine teaming in the architecture of a flexibly autonomous, near-fully-distributed Mission Management System for UAV swarms. Subsequently, the two problems of global mission planning are solved simultaneously using an integrated solution. This consists of a geometric clustering algorithm which prioritizes the minimization of overall mission time, and an off-policy, model-free Temporal Difference Learning global agent capable of learning about an initially unknown mission environment through simulations. The latter component makes the solution adaptive to missions with different requirements.

KW - Global Mission Planning

KW - Precision Agriculture

KW - Reinforcement Learning

KW - Temporal Difference Learning

KW - UAV

UR - http://www.scopus.com/inward/record.url?scp=85122810015&partnerID=8YFLogxK

U2 - 10.1109/DASC52595.2021.9594300

DO - 10.1109/DASC52595.2021.9594300

M3 - Conference contribution

AN - SCOPUS:85122810015

T3 - AIAA/IEEE Digital Avionics Systems Conference - Proceedings

BT - 40th Digital Avionics Systems Conference, DASC 2021 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 40th IEEE/AIAA Digital Avionics Systems Conference, DASC 2021

Y2 - 3 October 2021 through 7 October 2021

ER -

Adaptive UAV Swarm Mission Planning by Temporal Difference Learning

Özet

Yayın serisi

???event.eventtypes.event.conference???

Bibliyografik not

Finansman

BM SKH

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap