Why and How to Avoid the Flipped Quaternion Multiplication

Autor: Hannes Sommer, Igor Gilitschenski, Michael Bloesch, Stephan Weiss, Roland Siegwart, Juan Nieto

Publikováno v: Aerospace, Vol 5, Iss 3, p 72 (2018)

Over the last decades quaternions have become a crucial and very successful tool for attitude representation in robotics and aerospace. However, there is a major problem that is continuously causing trouble in practice when it comes to exchanging for

Externí odkaz: https://doaj.org/article/3046de01e5414b27a72e8db5c577796a

Comparing View-Based and Map-Based Semantic Labelling in Real-Time SLAM

Autor: Stefan Leutenegger, Fabian Falck, Zoe Landgraf, Andrew J. Davison, Michael Bloesch

Publikováno v: ICRA

Generally capable Spatial AI systems must build persistent scene representations where geometric models are combined with meaningful semantic labels. The many approaches to labelling scenes can be divided into two clear groups: view-based which estim

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::088ad410b048be70f2a73dd9a84322b3
http://arxiv.org/abs/2002.10342

KO-Fusion: Dense Visual SLAM with Tightly-Coupled Kinematic and Odometric Tracking

Autor: Charlie Houseago, Michael Bloesch, Stefan Leutenegger

Publikováno v: ICRA
International Conference on Robotics and Automation (ICRA)

Dense visual SLAM methods are able to estimate the 3D structure of an environment and locate the observer within them. They estimate the motion of a camera by matching visual information between consecutive frames, and are thus prone to failure under

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fcc838ae346e6f0002606cd662a438e8
https://doi.org/10.1109/icra.2019.8793471

MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM

Autor: Dimos Tzoumanikas, Michael Bloesch, Wenbin Li, Andrew J. Davison, Binbin Xu, Stefan Leutenegger

Publikováno v: ICRA 2019-IEEE International Conference on Robotics and Automation
ICRA
Xu, B, Li, W, Tzoumanikas, D, Bloesch, M, Davison, A & Leutenegger, S 2019, MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM . in IEEE International Conference on Robotics and Automation . International Conference On Robotics and Automation .

We propose a new multi-instance dynamic RGB-D SLAM system using an object-level octree-based volumetric representation. It can provide robust camera tracking in dynamic environments and at the same time, continuously estimate geometric, semantic, and

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0b7002b7e2590cf6210a97975961a3ec
http://arxiv.org/abs/1812.07976

CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM

Autor: Jan Czarnowski, Stefan Leutenegger, Michael Bloesch, Andrew J. Davison, Ronald Clark

Publikováno v: CVPR
IEEE Computer Vision and Pattern Recognition 2018

The representation of geometry in real-time 3D perception systems continues to be a critical research issue. Dense maps capture complete surface shape and can be augmented with semantic labels, but their high dimensionality makes them computationally

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6819f06f985d25478de867ab36806ed8
https://doi.org/10.1109/cvpr.2018.00271