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
2 AMA - Analyse de données, Modélisation et Apprentissage automatique [Grenoble]

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.

Domaines: Robotique [cs.RO]

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⟩