Grid-based localization and online mapping with moving objects detection and tracking: new results

Trung-Dung Vu 1 Julien Burlet 1 Olivier Aycard 2
1 E-MOTION - Geometry and Probability for Motion and Action
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
Abstract : In this paper, we present a real-time algorithm for local simultaneous localization and mapping (SLAM) with detection and tracking of moving objects (DATMO) in dynamic outdoor environments from a moving vehicle equipped with a laser scanner. To correct vehicle location from odometry we introduce a new fast implementation of incremental scan matching method that can work reliably in dynamic outdoor environments. After a good vehicle location is estimated, the surrounding map is updated incrementally and moving objects are detected without a priori knowledge of the targets. Detected moving objects are finally tracked by a multiple hypothesis tracker (MHT) coupled with an adaptive IMM (interacting multiple models) filter. The experimental results on datasets collected from different scenarios such as: urban streets, country roads and highways demonstrate the efficiency of the proposed algorithm on a Daimler Mercedes demonstrator in the framework of the European Project PReVENT-ProFusion2.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01023306
Contributor : Trung-Dung Vu <>
Submitted on : Friday, July 11, 2014 - 10:59:30 PM
Last modification on : Thursday, October 11, 2018 - 8:48:04 AM
Document(s) archivé(s) le : Saturday, October 11, 2014 - 1:16:22 PM

File

iv08.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Trung-Dung Vu, Julien Burlet, Olivier Aycard. Grid-based localization and online mapping with moving objects detection and tracking: new results. Intelligent Vehicles Symposium, 2008 IEEE, 2008, Netherlands. pp.684 - 689, ⟨10.1109/IVS.2008.4621305⟩. ⟨hal-01023306⟩

Share

Metrics

Record views

375

Files downloads

466