Unsupervised and online non-stationary obstacle discovery and modeling using a laser range finder

Guillaume Duceux 1, 2 David Filliat 1, 2
2 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : Using laser range finders has shown its efficiency to perform mapping and navigation for mobile robots. However, most of existing methods assume a mostly static world and filter away dynamic aspects while those dynamic aspects are often caused by non-stationary objects which may be important for the robot task. We propose an approach that makes it possible to detect, learn and recognize these objects through a multi-view model, using only a planar laser range finder. We show using a supervised approach that despite the limited information provided by the sensor, it is possible to recognize efficiently up to 22 different object, with a low computing cost while taking advantage of the large field of view of the sensor. We also propose an online, incremental and unsupervised approach that make it possible to continuously discover and learn all kind of dynamic elements encountered by the robot including people and objects.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01061406
Contributor : David Filliat <>
Submitted on : Friday, September 5, 2014 - 4:56:40 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:05 AM
Long-term archiving on : Saturday, December 6, 2014 - 11:45:00 AM

File

Duceux_IROS14.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01061406, version 1

Citation

Guillaume Duceux, David Filliat. Unsupervised and online non-stationary obstacle discovery and modeling using a laser range finder. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Sep 2014, Chicago, United States. 7 p. ⟨hal-01061406⟩

Share

Metrics

Record views

403

Files downloads

380