Adaptive UAV Swarm Mission Planning by Temporal Difference Learning

Shreevanth Krishnaa Gopalakrishnan, Saba Al-Rubaye, Gokhan Inalhan

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

6 Citations (Scopus)

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.

Original languageEnglish
Title of host publication40th Digital Avionics Systems Conference, DASC 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665434201
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event40th IEEE/AIAA Digital Avionics Systems Conference, DASC 2021 - San Antonio, United States
Duration: 3 Oct 20217 Oct 2021

Publication series

NameAIAA/IEEE Digital Avionics Systems Conference - Proceedings
Volume2021-October
ISSN (Print)2155-7195
ISSN (Electronic)2155-7209

Conference

Conference40th IEEE/AIAA Digital Avionics Systems Conference, DASC 2021
Country/TerritoryUnited States
CitySan Antonio
Period3/10/217/10/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

  • Global Mission Planning
  • Precision Agriculture
  • Reinforcement Learning
  • Temporal Difference Learning
  • UAV

Fingerprint

Dive into the research topics of 'Adaptive UAV Swarm Mission Planning by Temporal Difference Learning'. Together they form a unique fingerprint.

Cite this