En säker landning av drönare via ett artificiellt neuralt nätverk

Examensarbete på grundnivå

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/300033
Download file(s):
File Description SizeFormat 
CSE 19-08 CPL Hyttring Gustafsson.pdfCSE Hyttring Gustafsson14.46 MBAdobe PDFThumbnail
Bibliographical item details
Type: Examensarbete på grundnivå
Title: En säker landning av drönare via ett artificiellt neuralt nätverk
Authors: Hyttring, Adam
Gustafsson, Hannes
Abstract: Modern drones are often supplied with a built-in landing function. The function is usually primitive and rarely involves any advanced risk assessment. In this report, we propose a solution to transfer the human component of the risk assessment to the drone in the form of a neural network. It has previously been found advantageous to make valuable information more explicit before using it as an input in a neural network. Two different types of network models are compared in the work. One network only uses the drone’s camera frames as input variables, reducing its complexity. The second network performs more transformations on the drone’s camera frames to first extract valuable information from the images to make them explicit. The network then uses the explicit information in combination with the drone’s frames as input variables. In this report, a broader comparison is also presented about what impact on the network’s precision more explicit data has. The result of the work shows that networks that use explicit, valuable information have higher precision, but that the magnitude of the precision difference depends on the properties of the task. We also show that a neural network can, with good precision, perform a risk assessment of a drone’s landing.
Keywords: Artificial Intelligence;Automatic landing;Neural network;Explicit/Implicit information;Drones
Issue Date: 2019
Publisher: Chalmers tekniska högskola / Institutionen för data och informationsteknik
URI: https://hdl.handle.net/20.500.12380/300033
Collection:Examensarbeten på grundnivå // Basic Level Theses

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.