Self-Supervised Monocular Distance Learning on a Lightweight Micro Air Vehicle

Self-Supervised Monocular Distance Learning on a Lightweight Micro Air Vehicle

Lamers, K.

Hoekstra, J.M. (mentor)
De Croon, G.C.H.E. (mentor)
Tijmons, S. (mentor)
Guo, J. (mentor)

Aerospace Engineering

Control & Operations

2016-04-29

This thesis presents all the work performed in developing a novel method for estimating distances on a flapping wing micro air vehicle using a monocular camera. These distance estimates are useful for providing a way to avoid collisions while flying indoors. The proposed method is based on a self-supervised learning algorithm that uses a short range impact detector to learn camera based long range distance estimates. The first part of this thesis contains an extended version of the paper on this topic as was submitted to the 2016 International Conference on Intelligent Robots and Systems (IROS). The second part contains the preliminary thesis that was preparatory to the final work and gives an in-depth overview of the state-of-the-art of different aspects of the problem as found in literature.

http://resolver.tudelft.nl/uuid:55f9ab7a-2651-4a90-93a0-a8c9ddc7c6a9

2016-10-15

Student theses

master thesis

(c) 2016 Lamers, K.