6D SLAM with GPGPU computation

Janusz Bedkowski; Geert De Cubber; Andrzej Masłowski

6D SLAM with GPGPU computation

Janusz Bedkowski, Geert De Cubber, Andrzej Masłowski

Robotics & Autonomous Systems

Research output: Contribution to journal › Article › peer-review

Abstract

The main goal was to improve a state of the art 6D SLAM algorithm with a new GPGPU-based implementation of data registration module. Data registration is based on ICP (Iterative Closest Point) algorithm that is fully implemented in the GPU with NVIDIA FERMI architecture. In our research we focus on mobile robot inspection intervention systems applicable in hazardous environments. The goal is to deliver a complete system capable of being used in real life. In this paper we demonstrate our achievements in the field of on line robot localization and mapping. We demonstrated an experiment in real large environment. We compared two strategies of data alingment - simple ICP and ICP using so called meta scan.

Original language	Undefined/Unknown
Pages (from-to)	275-280
Number of pages	6
Journal	Pomiary Automatyka Robotyka
Volume	16
Issue number	2
Publication status	Published - 2012

Access to Document

http://www.par.pl/en/content/download/14036/170476/file/275_280.pdf

ICARUS: The ICARUS tools consist of assistive unmanned air, ground and sea vehicles, equipped with victim detection sensors
Bosschaerts, W. (Promotor)
1/02/12 → 31/01/16
Project: Research

Cite this

@article{7339b51186844e859362e28e8528bf15,

title = "6D SLAM with GPGPU computation",

abstract = "The main goal was to improve a state of the art 6D SLAM algorithm with a new GPGPU-based implementation of data registration module. Data registration is based on ICP (Iterative Closest Point) algorithm that is fully implemented in the GPU with NVIDIA FERMI architecture. In our research we focus on mobile robot inspection intervention systems applicable in hazardous environments. The goal is to deliver a complete system capable of being used in real life. In this paper we demonstrate our achievements in the field of on line robot localization and mapping. We demonstrated an experiment in real large environment. We compared two strategies of data alingment - simple ICP and ICP using so called meta scan.",

author = "Janusz Bedkowski and {De Cubber}, Geert and Andrzej Mas{\l}owski",

year = "2012",

language = "Ongedefinieerd/onbekend",

volume = "16",

pages = "275--280",

journal = "Pomiary Automatyka Robotyka",

number = "2",

}

TY - JOUR

T1 - 6D SLAM with GPGPU computation

AU - Bedkowski, Janusz

AU - De Cubber, Geert

AU - Masłowski, Andrzej

PY - 2012

Y1 - 2012

N2 - The main goal was to improve a state of the art 6D SLAM algorithm with a new GPGPU-based implementation of data registration module. Data registration is based on ICP (Iterative Closest Point) algorithm that is fully implemented in the GPU with NVIDIA FERMI architecture. In our research we focus on mobile robot inspection intervention systems applicable in hazardous environments. The goal is to deliver a complete system capable of being used in real life. In this paper we demonstrate our achievements in the field of on line robot localization and mapping. We demonstrated an experiment in real large environment. We compared two strategies of data alingment - simple ICP and ICP using so called meta scan.

AB - The main goal was to improve a state of the art 6D SLAM algorithm with a new GPGPU-based implementation of data registration module. Data registration is based on ICP (Iterative Closest Point) algorithm that is fully implemented in the GPU with NVIDIA FERMI architecture. In our research we focus on mobile robot inspection intervention systems applicable in hazardous environments. The goal is to deliver a complete system capable of being used in real life. In this paper we demonstrate our achievements in the field of on line robot localization and mapping. We demonstrated an experiment in real large environment. We compared two strategies of data alingment - simple ICP and ICP using so called meta scan.

M3 - Artikel

VL - 16

SP - 275

EP - 280

JO - Pomiary Automatyka Robotyka

JF - Pomiary Automatyka Robotyka

IS - 2

ER -

6D SLAM with GPGPU computation

Abstract

Access to Document

Projects

ICARUS: The ICARUS tools consist of assistive unmanned air, ground and sea vehicles, equipped with victim detection sensors

Cite this