Random Finite Sets for Robot Mapping and SLAM

New Concepts in Autonomous Robotic Map Representations

  • John Mullane
  • Ba-Ngu Vo
  • Martin Adams
  • Ba-Tuong Vo

Part of the Springer Tracts in Advanced Robotics book series (STAR, volume 72)

Table of contents

  1. Front Matter
  2. Introduction

    1. John Mullane, Ba-Ngu Vo, Martin Adams, Ba-Tuong Vo
      Pages 1-8
  3. Part I: Random Finite Sets

    1. Front Matter
      Pages 9-9
    2. John Mullane, Ba-Ngu Vo, Martin Adams, Ba-Tuong Vo
      Pages 11-25
    3. John Mullane, Ba-Ngu Vo, Martin Adams, Ba-Tuong Vo
      Pages 27-42
  4. Part II: Random Finite Set Based Robotic Mapping

    1. Front Matter
      Pages 43-43
    2. John Mullane, Ba-Ngu Vo, Martin Adams, Ba-Tuong Vo
      Pages 45-76
  5. Part III: Random Finite Set Based Simultaneous Localisation and Map Building

    1. Front Matter
      Pages 77-77
    2. John Mullane, Ba-Ngu Vo, Martin Adams, Ba-Tuong Vo
      Pages 79-96
    3. John Mullane, Ba-Ngu Vo, Martin Adams, Ba-Tuong Vo
      Pages 97-126
    4. John Mullane, Ba-Ngu Vo, Martin Adams, Ba-Tuong Vo
      Pages 127-136
  6. Back Matter

About this book


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.

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.


(SLAM) Autonomous Navigation Autonomous Robotics Bayes Optimality Random Finite Set Random Finite Sets (RFS) and Finite Set Simultaneous Localisation and Map Building Statistics (FISST)

Authors and affiliations

  • John Mullane
    • 1
  • Ba-Ngu Vo
    • 2
  • Martin Adams
    • 3
  • Ba-Tuong Vo
    • 2
  1. 1.School of Electrical & Electronic EngineeringNanyang Technological UniversitySingaporeSingapore
  2. 2.School of Electrical, Electronic & Computer EngineeringThe University of Western AustraliaCrawleyAustralia
  3. 3.Department of Electrical EngineeringUniversidad de ChileSantiagoChile

Bibliographic information

  • DOI
  • Copyright Information Springer Berlin Heidelberg 2011
  • Publisher Name Springer, Berlin, Heidelberg
  • eBook Packages Engineering Engineering (R0)
  • Print ISBN 978-3-642-21389-2
  • Online ISBN 978-3-642-21390-8
  • Series Print ISSN 1610-7438
  • Series Online ISSN 1610-742X
  • Buy this book on publisher's site