Fault-tolerant 3D Mapping with Application to an Orchard Robot

Morten Rufus Blas, Mogens Blanke, Radu Bogan Rusu, Michael Beetz

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

In this paper we present a geometric reasoning method for dealing with noise as well as faults present in 3D depth maps. These maps are acquired using stereo-vision sensors, but our framework makes no assumption about the origin of the underlying data. The method is based on observations made on the environment from dierent camera poses (viewpoints), where the occupied space as well as uncertainties in the range measurement are modelled using dynamic octree structures. This scheme allows us to detect and diagnose faulty range measurements in an ecient manner. We present results on the acquisition of comprehensive 3D maps for an agricultural robot operating in an orchard.
Original languageEnglish
Title of host publication7. IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes
Publication date2009
Pages893-898
ISBN (Print)978-3-902661-46-3
DOIs
Publication statusPublished - 2009
Event7th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes - Barcelona, Spain
Duration: 30 Jun 20093 Jul 2009
Conference number: 7
http://safeprocess09.upc.es/

Conference

Conference7th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes
Number7
Country/TerritorySpain
CityBarcelona
Period30/06/200903/07/2009
Internet address

Keywords

  • Other applications
  • Sensor and actuator faults

Fingerprint

Dive into the research topics of 'Fault-tolerant 3D Mapping with Application to an Orchard Robot'. Together they form a unique fingerprint.

Cite this