3D Maps Registration and Path Planning for Autonomous Robot Navigation

Konstantinos Charalampous; Dimitrios Chrysostomou; Ioannis Kostavelis; Angelos A. Amanatiadis; Antonios Gasteratos

3D Maps Registration and Path Planning for Autonomous Robot Navigation

Konstantinos Charalampous, Dimitrios Chrysostomou, Ioannis Kostavelis, Angelos A. Amanatiadis, Antonios Gasteratos

Publikation: Konferencebidrag uden forlag/tidsskrift › Paper uden forlag/tidsskrift › Forskning › peer review

Abstract

Mobile robots dedicated in security tasks should
be capable of clearly perceiving their environment to competently
navigate within cluttered areas, so as to accomplish
their assigned mission. The paper in hand describes such an
autonomous agent designed to deploy competently in hazardous
environments equipped with a laser scanner sensor. During the
robot’s motion, consecutive scans are obtained to produce dense
3D maps of the area. A 3D point cloud registration technique
is exploited to merge the successively created maps during
the robot’s motion followed by an ICP refinement step. The
reconstructed 3D area is then top-down projected with great
resolution, to be fed in a path planning algorithm suitable
to trace obstacle-free trajectories in the explored area. The
main characteristic of the path planner is that the robot’s
embodiment is considered for producing detailed and safe
trajectories of 1 cm resolution. The proposed method has been
evaluated with our mobile robot in several indoor and outdoor
scenarios revealing remarkable performance.

Originalsprog	Engelsk
Publikationsdato	2013
Status	Udgivet - 2013
Udgivet eksternt	Ja
Begivenhed	International Workshop on Robots and Sensors integration in future rescue information system - Big Sight Conference Venue, Tokyo, Japan Varighed: 7 nov. 2013 → 7 nov. 2013 Konferencens nummer: 3

Workshop

Workshop	International Workshop on Robots and Sensors integration in future rescue information system
Nummer	3
Lokation	Big Sight Conference Venue
Land/Område	Japan
By	Tokyo
Periode	07/11/2013 → 07/11/2013

Adgang til dokumentet

http://arxiv.org/abs/1312.2822

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

1 Organisering af eller deltagelse i konference
1 Organisering af eller deltagelse i workshop, kursus, seminar, udstilling eller lignende

International Workshop on Robots and Sensors integration in future rescue information system
Dimitris Chrysostomou (Deltager)
7 nov. 2013
Aktivitet: Deltagelse i faglig begivenhed › Organisering af eller deltagelse i workshop, kursus, seminar, udstilling eller lignende
IEEE/RSJ International Conference on Intelligent Robots and Systems
Dimitrios Chrysostomou (Deltager)
3 nov. 2013 → 8 nov. 2013
Aktivitet: Deltagelse i faglig begivenhed › Organisering af eller deltagelse i konference

Citationsformater

@conference{2fbcf810a8d14ab2ae7c0081d6efe9fe,

title = "3D Maps Registration and Path Planning for Autonomous Robot Navigation",

abstract = "Mobile robots dedicated in security tasks shouldbe capable of clearly perceiving their environment to competentlynavigate within cluttered areas, so as to accomplishtheir assigned mission. The paper in hand describes such anautonomous agent designed to deploy competently in hazardousenvironments equipped with a laser scanner sensor. During therobot{\textquoteright}s motion, consecutive scans are obtained to produce dense3D maps of the area. A 3D point cloud registration techniqueis exploited to merge the successively created maps duringthe robot{\textquoteright}s motion followed by an ICP refinement step. Thereconstructed 3D area is then top-down projected with greatresolution, to be fed in a path planning algorithm suitableto trace obstacle-free trajectories in the explored area. Themain characteristic of the path planner is that the robot{\textquoteright}sembodiment is considered for producing detailed and safetrajectories of 1 cm resolution. The proposed method has beenevaluated with our mobile robot in several indoor and outdoorscenarios revealing remarkable performance.",

author = "Konstantinos Charalampous and Dimitrios Chrysostomou and Ioannis Kostavelis and Amanatiadis, {Angelos A.} and Antonios Gasteratos",

year = "2013",

language = "English",

note = "International Workshop on Robots and Sensors integration in future rescue information system, ROSIN ; Conference date: 07-11-2013 Through 07-11-2013",

}

3D Maps Registration and Path Planning for Autonomous Robot Navigation. / Charalampous, Konstantinos; Chrysostomou, Dimitrios; Kostavelis, Ioannis et al.
2013. Afhandling præsenteret på International Workshop on Robots and Sensors integration in future rescue information system, Tokyo, Japan.

Publikation: Konferencebidrag uden forlag/tidsskrift › Paper uden forlag/tidsskrift › Forskning › peer review

TY - CONF

T1 - 3D Maps Registration and Path Planning for Autonomous Robot Navigation

AU - Charalampous, Konstantinos

AU - Chrysostomou, Dimitrios

AU - Kostavelis, Ioannis

AU - Amanatiadis, Angelos A.

AU - Gasteratos, Antonios

N1 - Conference code: 3

PY - 2013

Y1 - 2013

N2 - Mobile robots dedicated in security tasks shouldbe capable of clearly perceiving their environment to competentlynavigate within cluttered areas, so as to accomplishtheir assigned mission. The paper in hand describes such anautonomous agent designed to deploy competently in hazardousenvironments equipped with a laser scanner sensor. During therobot’s motion, consecutive scans are obtained to produce dense3D maps of the area. A 3D point cloud registration techniqueis exploited to merge the successively created maps duringthe robot’s motion followed by an ICP refinement step. Thereconstructed 3D area is then top-down projected with greatresolution, to be fed in a path planning algorithm suitableto trace obstacle-free trajectories in the explored area. Themain characteristic of the path planner is that the robot’sembodiment is considered for producing detailed and safetrajectories of 1 cm resolution. The proposed method has beenevaluated with our mobile robot in several indoor and outdoorscenarios revealing remarkable performance.

AB - Mobile robots dedicated in security tasks shouldbe capable of clearly perceiving their environment to competentlynavigate within cluttered areas, so as to accomplishtheir assigned mission. The paper in hand describes such anautonomous agent designed to deploy competently in hazardousenvironments equipped with a laser scanner sensor. During therobot’s motion, consecutive scans are obtained to produce dense3D maps of the area. A 3D point cloud registration techniqueis exploited to merge the successively created maps duringthe robot’s motion followed by an ICP refinement step. Thereconstructed 3D area is then top-down projected with greatresolution, to be fed in a path planning algorithm suitableto trace obstacle-free trajectories in the explored area. Themain characteristic of the path planner is that the robot’sembodiment is considered for producing detailed and safetrajectories of 1 cm resolution. The proposed method has beenevaluated with our mobile robot in several indoor and outdoorscenarios revealing remarkable performance.

M3 - Paper without publisher/journal

T2 - International Workshop on Robots and Sensors integration in future rescue information system

Y2 - 7 November 2013 through 7 November 2013

ER -

3D Maps Registration and Path Planning for Autonomous Robot Navigation

Abstract

Workshop

Adgang til dokumentet

AUB Link

Fingeraftryk

Aktiviteter

International Workshop on Robots and Sensors integration in future rescue information system

IEEE/RSJ International Conference on Intelligent Robots and Systems

Citationsformater