Learning Based Framework for Joint Task Allocation and System Design in Stochastic Multi-UAV Systems

Inwook Kim, James R. Morrison

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

7 Scopus citations

Abstract

We consider a system of UAVs, depots, service stations and tasks in a stochastic environment. Our goal is to jointly determine the system resources (system design), task allocation and waypoint selection. To our knowledge, none have studied this joint decision problem in the stochastic context. We formulate the problem as a Markov decision process (MDP) and resort to deep reinforcement learning (DRL) to obtain state-based decisions. Numerical studies are conducted to assess the performance of the proposed approach. In small examples for which an optimal policy can be found, the DRL based approach is much faster than value iteration and obtained nearly optimal solutions. In large examples, the DRL based approach can find efficient designs and policies.

Original languageEnglish
Title of host publication2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages324-334
Number of pages11
ISBN (Print)9781538613535
DOIs
StatePublished - Aug 31 2018
Event2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018 - Dallas, United States
Duration: Jun 12 2018Jun 15 2018

Publication series

Name2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018

Conference

Conference2018 International Conference on Unmanned Aircraft Systems, ICUAS 2018
Country/TerritoryUnited States
CityDallas
Period06/12/1806/15/18

Fingerprint

Dive into the research topics of 'Learning Based Framework for Joint Task Allocation and System Design in Stochastic Multi-UAV Systems'. Together they form a unique fingerprint.

Cite this