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

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

doi:10.3182/20090630-4-ES-2003.00147

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

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

Technical University of Munich

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-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 language	English
Title of host publication	7. IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes
Publication date	2009
Pages	893-898
ISBN (Print)	978-3-902661-46-3
DOIs	https://doi.org/10.3182/20090630-4-ES-2003.00147
Publication status	Published - 2009
Event	7th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes - Barcelona, Spain Duration: 30 Jun 2009 → 3 Jul 2009 Conference number: 7 http://safeprocess09.upc.es/

Conference

Conference	7th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes
Number	7
Country/Territory	Spain
City	Barcelona
Period	30/06/2009 → 03/07/2009
Internet address	http://safeprocess09.upc.es/

Keywords

Other applications
Sensor and actuator faults

Access to Document

10.3182/20090630-4-ES-2003.00147

OpenUrl availability

Full text

Cite this

@inproceedings{a36d113610044607b9b2599b59466899,

title = "Fault-tolerant 3D Mapping with Application to an Orchard Robot",

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.",

keywords = "Other applications, Sensor and actuator faults",

author = "Blas, {Morten Rufus} and Mogens Blanke and Rusu, {Radu Bogan} and Michael Beetz",

year = "2009",

doi = "10.3182/20090630-4-ES-2003.00147",

language = "English",

isbn = "978-3-902661-46-3",

pages = "893--898",

booktitle = "7. IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes",

note = "7th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, SAFEPROCESS 2009 ; Conference date: 30-06-2009 Through 03-07-2009",

url = "http://safeprocess09.upc.es/",

}

Blas, MR, Blanke, M, Rusu, RB & Beetz, M 2009, Fault-tolerant 3D Mapping with Application to an Orchard Robot. in 7. IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes. pp. 893-898, 7th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes, Barcelona, Spain, 30/06/2009. https://doi.org/10.3182/20090630-4-ES-2003.00147

TY - GEN

T1 - Fault-tolerant 3D Mapping with Application to an Orchard Robot

AU - Blas, Morten Rufus

AU - Blanke, Mogens

AU - Rusu, Radu Bogan

AU - Beetz, Michael

N1 - Conference code: 7

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

KW - Other applications

KW - Sensor and actuator faults

U2 - 10.3182/20090630-4-ES-2003.00147

DO - 10.3182/20090630-4-ES-2003.00147

M3 - Article in proceedings

SN - 978-3-902661-46-3

SP - 893

EP - 898

BT - 7. IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes

T2 - 7th IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes

Y2 - 30 June 2009 through 3 July 2009

ER -

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

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this