Random Finite Sets for Robot Mapping & SLAM

New Concepts in Autonomous Robotic Map Representations
2011
ISBN: 978-3-642-21389-2
Verlag: Springer

Buch, Englisch, Band 72, 148 Seiten, Format (B × H): 160 mm x 241 mm, Gewicht: 462 g

Reihe: Springer Tracts in Advanced Robotics

Simultaneous Localisation and Map (SLAM) building algorithms, which rely on random vectors to represent sensor measurements and feature maps are known to be extremely fragile in the presence of feature detection and data association uncertainty. Therefore new concepts for autonomous map representations are given in this book, based on random finite sets (RFSs). It will be shown that the RFS representation eliminates the necessity of fragile data association and map management routines. It fundamentally differs from vector based approaches since it estimates not only the spatial states of features but also the number of map features which have passed through the field(s) of view of a robot's sensor(s), an attribute which is necessary for SLAM.

The book also demonstrates that in SLAM, a valid measure of map estimation error is critical. It will be shown that under an RFS-SLAM representation, a consistent metric, which gauges both feature number as well as spatial errors, can be defined.

The concepts of RFS map representations are accompanied with autonomous SLAM experiments in urban and marine environments. Comparisons of RFS-SLAM with state of the art vector based methods are given, along with pseudo-code implementations of all the RFS techniques presented.

Zielgruppe

Research

Autoren/Hrsg.

Mullane, John Stephen

Vo, Ba-Tuong

Vo, Ba-Ngu

Adams, Martin David

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Technische Wissenschaften Elektronik | Nachrichtentechnik Elektronik Robotik

Inhaltsverzeichnis

Part I Random Finite Sets.- Why Random Finite Sets?.- Estimation with Random Finite Sets.- Part II Random Finite Set Based Robotic Mapping.- An RFS Theoretic for Bayesian Feature-Based Robotic
Mapping.- An RFS ‘Brute Force’ Formulation for Bayesian SLAM.- Rao-Blackwellised RFS Bayesian SLAM.- Extensions with RFSs in SLAM.

Über Autor(innen)

Adams, Martin David
Martin Adams is Professor in autonomous robotics research, University of Chile. He holds bachelors, masters and doctoral degrees from Oxford University.

Vo, Ba-Tuong
Ba-Tuong Vo is Assistant Professor, UWA. He received his B.Sc, B.E and Ph.D. degrees from UWA.

Mullane, John Stephen
John Mullane received the B.E.E. degree from University College Cork, Ireland, and Ph.D degree from Nanyang Technological University (NTU), Singapore.

Vo, Ba-Ngu
Ba-Ngu Vo is Winthrop Professor and Chair of Signal Processing, University of Western Australia (UWA). He received joint Bachelor degrees (Science and Elec. Eng.), UWA, and Ph.D., Curtin University.

John Mullane received the B.E.E. degree from University College Cork, Ireland, and Ph.D degree from Nanyang Technological University (NTU), Singapore.

Ba-Ngu Vo is Winthrop Professor and Chair of Signal Processing, University of Western Australia (UWA). He received joint Bachelor degrees (Science and Elec. Eng.), UWA, and Ph.D., Curtin University.

Martin Adams is Professor in autonomous robotics research, University of Chile. He holds bachelors, masters and doctoral degrees from Oxford University.

Ba-Tuong Vo is Assistant Professor, UWA. He received his B.Sc, B.E and Ph.D. degrees from UWA.