Collaborative Multi-vehicle SLAM with moving object tracking

Although simultaneous localization and mapping (SLAM) algorithms are widely appreciated in mobile robot navigation, they can be further improved to suit practical applications in dynamic environmental conditions. One such important improvement is the detection and tracking of moving objects present...

Full description

Bibliographic Details
Main Authors: Moratuwage, D., Vo, Ba-Ngu, Wang, D
Other Authors: N/A
Format: Conference Paper
Published: IEEE 2013
Online Access:http://hdl.handle.net/20.500.11937/5964
_version_ 1848744943109013504
author Moratuwage, D.
Vo, Ba-Ngu
Wang, D
author2 N/A
author_facet N/A
Moratuwage, D.
Vo, Ba-Ngu
Wang, D
author_sort Moratuwage, D.
building Curtin Institutional Repository
collection Online Access
description Although simultaneous localization and mapping (SLAM) algorithms are widely appreciated in mobile robot navigation, they can be further improved to suit practical applications in dynamic environmental conditions. One such important improvement is the detection and tracking of moving objects present in the sensor field of view (FOV). In this paper we propose to extend our recently introduced CollaborativeMulti-vehicle SLAM (CMSLAM) solution based on the random finite set (RFS) representation of the feature map and measurements, by tracking both static and dynamic features. We represent static features observed during the SLAM process, along with dynamic features present in the current sensor FOV, as an augmented RFS. The corresponding probability density is propagated using a Bayes recursion, from which the static feature map and the estimates of dynamic feature locations can be obtained. Measurement update in the CMSLAM process is carried out only using the static feature map to take advantage of obvious accuracy improvements.
first_indexed 2025-11-14T06:09:29Z
format Conference Paper
id curtin-20.500.11937-5964
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:09:29Z
publishDate 2013
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-59642017-09-13T14:42:16Z Collaborative Multi-vehicle SLAM with moving object tracking Moratuwage, D. Vo, Ba-Ngu Wang, D N/A Although simultaneous localization and mapping (SLAM) algorithms are widely appreciated in mobile robot navigation, they can be further improved to suit practical applications in dynamic environmental conditions. One such important improvement is the detection and tracking of moving objects present in the sensor field of view (FOV). In this paper we propose to extend our recently introduced CollaborativeMulti-vehicle SLAM (CMSLAM) solution based on the random finite set (RFS) representation of the feature map and measurements, by tracking both static and dynamic features. We represent static features observed during the SLAM process, along with dynamic features present in the current sensor FOV, as an augmented RFS. The corresponding probability density is propagated using a Bayes recursion, from which the static feature map and the estimates of dynamic feature locations can be obtained. Measurement update in the CMSLAM process is carried out only using the static feature map to take advantage of obvious accuracy improvements. 2013 Conference Paper http://hdl.handle.net/20.500.11937/5964 10.1109/ICRA.2013.6631397 IEEE restricted
spellingShingle Moratuwage, D.
Vo, Ba-Ngu
Wang, D
Collaborative Multi-vehicle SLAM with moving object tracking
title Collaborative Multi-vehicle SLAM with moving object tracking
title_full Collaborative Multi-vehicle SLAM with moving object tracking
title_fullStr Collaborative Multi-vehicle SLAM with moving object tracking
title_full_unstemmed Collaborative Multi-vehicle SLAM with moving object tracking
title_short Collaborative Multi-vehicle SLAM with moving object tracking
title_sort collaborative multi-vehicle slam with moving object tracking
url http://hdl.handle.net/20.500.11937/5964