Onboard Mission- and Contingency Management based on Behavior Trees for Unmanned Aerial Vehicles
Journal Title
Journal ISSN
Volume Title
Sähkötekniikan korkeakoulu |
Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Author
Date
2023-10-09
Department
Major/Subject
Autonomous Systems
Mcode
ELEC3055
Degree programme
Master's Programme in ICT Innovation
Language
en
Pages
79
Series
Abstract
Unmanned Aerial Vehicles (UAVs) have gained significant attention for their potential in various sectors, including surveillance, logistics, and disaster management. This thesis focuses on developing a novel onboard mission and contingency management system based on Behavior Trees for UAVs. The study aims to assert if behavior trees can be effectively applied to this domain and how they perform with respect to other modelling architectures. Furthermore, this document explores which tree structures are more efficient, good-design practices and behavior tree limitations. Overall, this thesis addresses the challenge of autonomous onboard decision-making of UAVs in complex and dynamic environments, particularly in the context of delivery missions in off-shore wind farms. The developed architecture is tested in a simulated environment. The research integrates a Skill Manager, a Mission Planner, and a Mission and Contingency Manager. The architecture leverages Behavior Trees to facilitate both mission execution and contingency management. The thesis also presents a quantitative analysis of key performance indicators, providing a comparative evaluation against traditional architectures like Finite State Machines. The results indicate that the proposed system is efficient in mission execution and effective in handling contingencies. This study offers a comprehensive structure targeting onboard planning, contingency management and concurrent actions execution. It also presents a quantitative analysis of Behavior Trees' performance in UAV mission execution and reactivity to contingent situations. It contributes to the ongoing discourse on UAV autonomy, offering insights beneficial for the broader deployment of UAVs in various industrial applications.Description
Supervisor
Zhou, QuanThesis advisor
Schopferer, SimonKeywords
autonomy, mission management, flight management system, behavior trees, UAV
