A Random-Finite-Set Approach to Bayesian SLAM

This paper proposes an integrated Bayesian frame work for feature-based simultaneous localization and map building (SLAM) in the general case of uncertain feature number and data association. By modeling the measurements and feature map as random finite sets (RFSs), a formulation of the feature-base...

Full description

Bibliographic Details
Main Authors: Mullane, J., Vo, Ba-Ngu, Adams, M., Vo, Ba Tuong
Format: Journal Article
Published: IEEE Press 2011
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/35643
_version_ 1848754551258087424
author Mullane, J.
Vo, Ba-Ngu
Adams, M.
Vo, Ba Tuong
author_facet Mullane, J.
Vo, Ba-Ngu
Adams, M.
Vo, Ba Tuong
author_sort Mullane, J.
building Curtin Institutional Repository
collection Online Access
description This paper proposes an integrated Bayesian frame work for feature-based simultaneous localization and map building (SLAM) in the general case of uncertain feature number and data association. By modeling the measurements and feature map as random finite sets (RFSs), a formulation of the feature-based SLAM problem is presented that jointly estimates the number and location of the features, as well as the vehicle trajectory. More concisely, the joint posterior distribution of the set-valued map and vehicle trajectory is propagated forward in time as measurements arrive, thereby incorporating both data association and feature management into a single recursion. Furthermore, the Bayes optimality of the proposed approach is established. A first-order solution, which is coined as the probability hypothesis density (PHD) SLAM filter, is derived, which jointly propagates the posterior PHD of the map and the posterior distribution of the vehicle trajectory. A Rao-Blackwellized (RB) implementation of the PHD-SLAM filter is proposed based on the Gaussian-mixture PHD filter (for the map) and a particle filter (for the vehicle trajectory). Simulated and experimental results demonstrate the merits of the proposed approach, particularly in situations of high clutter and data association ambiguity.
first_indexed 2025-11-14T08:42:12Z
format Journal Article
id curtin-20.500.11937-35643
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:42:12Z
publishDate 2011
publisher IEEE Press
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-356432017-09-13T15:27:37Z A Random-Finite-Set Approach to Bayesian SLAM Mullane, J. Vo, Ba-Ngu Adams, M. Vo, Ba Tuong point process probability hypothesis density (PHD) Bayesian simultaneous localization and mapping (SLAM) random finite set (RFS) feature-based map This paper proposes an integrated Bayesian frame work for feature-based simultaneous localization and map building (SLAM) in the general case of uncertain feature number and data association. By modeling the measurements and feature map as random finite sets (RFSs), a formulation of the feature-based SLAM problem is presented that jointly estimates the number and location of the features, as well as the vehicle trajectory. More concisely, the joint posterior distribution of the set-valued map and vehicle trajectory is propagated forward in time as measurements arrive, thereby incorporating both data association and feature management into a single recursion. Furthermore, the Bayes optimality of the proposed approach is established. A first-order solution, which is coined as the probability hypothesis density (PHD) SLAM filter, is derived, which jointly propagates the posterior PHD of the map and the posterior distribution of the vehicle trajectory. A Rao-Blackwellized (RB) implementation of the PHD-SLAM filter is proposed based on the Gaussian-mixture PHD filter (for the map) and a particle filter (for the vehicle trajectory). Simulated and experimental results demonstrate the merits of the proposed approach, particularly in situations of high clutter and data association ambiguity. 2011 Journal Article http://hdl.handle.net/20.500.11937/35643 10.1109/TRO.2010.2101370 IEEE Press restricted
spellingShingle point process
probability hypothesis density (PHD)
Bayesian simultaneous localization and mapping (SLAM)
random finite set (RFS)
feature-based map
Mullane, J.
Vo, Ba-Ngu
Adams, M.
Vo, Ba Tuong
A Random-Finite-Set Approach to Bayesian SLAM
title A Random-Finite-Set Approach to Bayesian SLAM
title_full A Random-Finite-Set Approach to Bayesian SLAM
title_fullStr A Random-Finite-Set Approach to Bayesian SLAM
title_full_unstemmed A Random-Finite-Set Approach to Bayesian SLAM
title_short A Random-Finite-Set Approach to Bayesian SLAM
title_sort random-finite-set approach to bayesian slam
topic point process
probability hypothesis density (PHD)
Bayesian simultaneous localization and mapping (SLAM)
random finite set (RFS)
feature-based map
url http://hdl.handle.net/20.500.11937/35643