Please use this identifier to cite or link to this item: https://doi.org/10.3724/SP.J.1004.2013.01889
Title: A comprehensive UAV indoor navigation system based on vision optical flow and laser FastSLAM
Authors: Wang, F.
Cui, J.-Q.
Chen, B.-M. 
Lee, T.H. 
Keywords: Indoor navigation
Laser FastSLAM
Optical flow
Simultaneous localization and mapping (SLAM)
Unmanned aerial vehicle (UAV) flight control
Issue Date: Nov-2013
Source: Wang, F.,Cui, J.-Q.,Chen, B.-M.,Lee, T.H. (2013-11). A comprehensive UAV indoor navigation system based on vision optical flow and laser FastSLAM. Zidonghua Xuebao/Acta Automatica Sinica 39 (11) : 1889-1900. ScholarBank@NUS Repository. https://doi.org/10.3724/SP.J.1004.2013.01889
Abstract: This paper presents a comprehensive control, navigation, localization and mapping solution for an indoor quadrotor unmanned aerial vehicle (UAV) system. Three main sensors are used onboard the quadrotor platform, namely an inertial measurement unit, a downward-looking camera and a scanning laser range finder. With this setup, the UAV is able to estimate its own velocity and position robustly, while flying along the internal walls of a room without collisions. After one complete flight, with the collected data the historic UAV path and the indoor environment can be well estimated. The autonomous navigation part of the system does not require any remote sensory information or off-line computational power, while the mapping is done off-line. Complete flight tests have been carried out to verify fidelity and performance the navigation solution. Copyright © 2013 Acta Automatica Sinica. All rights reserved.
Source Title: Zidonghua Xuebao/Acta Automatica Sinica
URI: http://scholarbank.nus.edu.sg/handle/10635/68081
ISSN: 02544156
DOI: 10.3724/SP.J.1004.2013.01889
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

28
checked on Dec 5, 2017

Page view(s)

111
checked on Dec 8, 2017

Google ScholarTM

Check

Altmetric


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