|
|
# Visual SLAM for Terrain Reconstruction and Autonomous Flight
|
|
|
by Adrian Marxer (adrian.marxer@student.uibk.ac.at)
|
|
|
|
|
|
Author:
|
|
|
* Adrian Marxer (adrian.marxer@student.uibk.ac.at)
|
|
|
|
|
|
Supervised by:
|
|
|
* Justus Piater (justus.piater@uibk.ac.at)
|
|
|
* Simon Haller (simon.haller@uibk.ac.at)
|
|
|
|
|
|
License: TBA
|
|
|
|
|
|
Bug tracker: TBA
|
|
|
|
|
|
Source: TBA
|
|
|
|
|
|
## 1. Overview
|
|
|
|
|
|
This project is a feasibility study of Visual SLAM for terrain reconstruction on an unmanned aerial vehicle. The goal is to use an existing SLAM algorithm to create a 3D map of an unknown environment by a quadrocopter in remote-controlled or autonomous flight. Optimally the algorithm will run on the vehicle itself, but if that is not practical a remote machine will be used.
|
|
|
|
|
|
## 2. Task
|
|
|
### Motivation
|
|
|
The main motivation behind this project is the approach by two Innsbrucker companys: Laserdata and Grid-IT. They are using LiDAR devices mounted on UAVs to build comprehensive geographic information maps. But the resulting point clouds contain errors due to unstable flight. The integrated IMUs are not fast/accurate enough to compensate for the drift. They are now searching for methods to complement their existing technique.
|
|
|
|
|
|
## 2. Installation
|
|
|
TBA
|
|
|
|
|
|
## 3. Usage
|
|
|
TBA
|
|
|
|
|
|
## 4. Platform
|
|
|
This Bachelor theses was done using the quadcopter provided by the MCI Management Center Innsbruck.
|
|
|
|
|
|
A general wiki page about the used quadcopter can be found [here](http://mci-quadrocopterws-2014-automation-project.wikia.com/wiki/MCI_Quadrocopter%28WS_2014_Automation_Project%29_Wiki).
|
|
|
|
|
|
### 2.1. Problem
|
|
|
## 5. Visual SLAM Algorithm
|
|
|
TBA
|
|
|
|
|
|
### 2.2. Goal
|
|
|
## 6. Autonomous exploration
|
|
|
TBA
|
|
|
|
|
|
## 3. Platform |
|
|
\ No newline at end of file |
|
|
## 7. Change log
|
|
|
TBA |
|
|
\ No newline at end of file |