View planning for 3D reconstruction of unknown objects with Leading Edge Scanner (LES)

Master Thesis (2021)
Author(s)

T.M. Akaltun (TU Delft - Aerospace Engineering)

Contributor(s)

Roger Groves – Mentor (TU Delft - Structural Integrity & Composites)

Timo Wassenaar – Graduation committee member (Royal Netherlands Aerospace Centre NLR)

Dino Spirtovic – Mentor (Royal Netherlands Aerospace Centre NLR)

Faculty
Aerospace Engineering
Copyright
© 2021 Taha Akaltun
More Info
expand_more
Publication Year
2021
Language
English
Copyright
© 2021 Taha Akaltun
Graduation Date
07-12-2021
Awarding Institution
Delft University of Technology, Royal Netherlands Aerospace Centre NLR
Programme
['Aerospace Engineering']
Faculty
Aerospace Engineering
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Automation has come knocking at the door of the world of aircraft maintenance. The general trend shows that the total aircraft fleet size of the world increases in contrast to the number of technicians, which decreases. Therefore, the Royal Netherlands Aerospace Center (NLR) launched a project and setup called Leading Edge Scanner (LES) to automate technician performed inspections on aircraft for partial or total replacement of this service. Automated three-dimensional (3D) reconstruction of known or unknown objects requires robots and sensors. The LES, a robotic arm, will automatically detect and classify anomalies on aircraft components. As several images from different viewpoints are needed to reconstruct a 3D computerized object, a view planning strategy is required to find the Next-Best-View (NBV). The challenging problem of finding the NBV has been studied since the 1980s.

Files

License info not available