Unpublished conference/Abstract (Scientific congresses, symposiums and conference proceedings)
Stereo Visual Odometry and Semantics based Localization of Aerial Robots in Indoor Environments
Bavle, Hriday; Manthe, Stephan; De La Puente, Paloma et al.
2018IEEE International Conference on Intelligent Robots and Systems
 

Files


Full Text
Bavle et al. - 2018 - Stereo Visual Odometry and Semantics based Localization of Aerial Robots in Indoor Environments-annotated.pdf
Publisher postprint (1.14 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Aerial Systems: Perception and Autonomy; Localizati
Abstract :
[en] In this paper we propose a particle filter localization approach, based on stereo visual odometry (VO) and semantic information from indoor environments, for mini-aerial robots. The prediction stage of the particle filter is performed using the 3D pose of the aerial robot estimated by the stereo VO algorithm. This predicted 3D pose is updated using inertial as well as semantic measurements. The algorithm processes semantic measurements in two phases; firstly, a pre-trained deep learning (DL) based object detector is used for real time object detections in the RGB spectrum. Secondly, from the corresponding 3D point clouds of the detected objects, we segment their dominant horizontal plane and estimate their relative position, also augmenting a prior map with new detections. The augmented map is then used in order to obtain a drift free pose estimate of the aerial robot. We validate our approach in several real flight experiments where we compare it against ground truth and a state of the art visual SLAM approach.
Disciplines :
Electrical & electronics engineering
Author, co-author :
Bavle, Hriday  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > Automation
Manthe, Stephan
De La Puente, Paloma
Rodriguez-Ramos, Alejandro
Sampedro, Carlos
Campoy, Pascual
External co-authors :
yes
Language :
English
Title :
Stereo Visual Odometry and Semantics based Localization of Aerial Robots in Indoor Environments
Publication date :
2018
Event name :
IEEE International Conference on Intelligent Robots and Systems
Event date :
1-10-2018 to 5-10-2018
Commentary :
9781538680940
Available on ORBilu :
since 19 May 2021

Statistics


Number of views
43 (0 by Unilu)
Number of downloads
251 (7 by Unilu)

Scopus citations®
 
14
Scopus citations®
without self-citations
13
WoS citations
 
9

Bibliography


Similar publications



Contact ORBilu