Semantic Mapping and Object Detection for Indoor Mobile Robots

S. Kowalewski, Adrian Llopart Maurin, Jens Christian Andersen*

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

63 Downloads (Pure)

Abstract

In this paper the authors present a full solution for object-level semantic perception of the environment by indoor mobile robots. The proposed solution not only provides means for semantic mapping but also division of the environment into clusters representing singular object instances. The robot is provided with information that not only allows it to avoid collisions with obstacles present in the environment, but also information about the localization, the class and the shape of each encountered object instance. This level of perception enhances the robot's ability to interact with the environment. The state-of-the-art deep learning solution, Mask-RCNN, is used for the image segmentation task. The image processing network is combined with an RTAB-Map SLAM algorithm to generate semantic pointclouds of the environment. The final part of the paper is focused on pointcloud processing: providing methods for instance extraction and instance processing. To verify the performance of the proposed methodology multiple experiments are conducted. Through the evaluation of the results it is possible to identify possible improvements.
Original languageEnglish
Article number012012
JournalIOP Conference Series: Materials Science and Engineering
Volume517
Issue number1
Number of pages10
ISSN1757-8981
DOIs
Publication statusPublished - 2019

Cite this

@article{210bc6307e8f433b92fceb30309134c3,
title = "Semantic Mapping and Object Detection for Indoor Mobile Robots",
abstract = "In this paper the authors present a full solution for object-level semantic perception of the environment by indoor mobile robots. The proposed solution not only provides means for semantic mapping but also division of the environment into clusters representing singular object instances. The robot is provided with information that not only allows it to avoid collisions with obstacles present in the environment, but also information about the localization, the class and the shape of each encountered object instance. This level of perception enhances the robot's ability to interact with the environment. The state-of-the-art deep learning solution, Mask-RCNN, is used for the image segmentation task. The image processing network is combined with an RTAB-Map SLAM algorithm to generate semantic pointclouds of the environment. The final part of the paper is focused on pointcloud processing: providing methods for instance extraction and instance processing. To verify the performance of the proposed methodology multiple experiments are conducted. Through the evaluation of the results it is possible to identify possible improvements.",
author = "S. Kowalewski and Maurin, {Adrian Llopart} and Andersen, {Jens Christian}",
year = "2019",
doi = "10.1088/1757-899X/517/1/012012",
language = "English",
volume = "517",
journal = "I O P Conference Series: Materials Science and Engineering",
issn = "1757-8981",
publisher = "IOP Publishing",
number = "1",

}

Semantic Mapping and Object Detection for Indoor Mobile Robots. / Kowalewski, S.; Maurin, Adrian Llopart; Andersen, Jens Christian.

In: IOP Conference Series: Materials Science and Engineering, Vol. 517, No. 1, 012012, 2019.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Semantic Mapping and Object Detection for Indoor Mobile Robots

AU - Kowalewski, S.

AU - Maurin, Adrian Llopart

AU - Andersen, Jens Christian

PY - 2019

Y1 - 2019

N2 - In this paper the authors present a full solution for object-level semantic perception of the environment by indoor mobile robots. The proposed solution not only provides means for semantic mapping but also division of the environment into clusters representing singular object instances. The robot is provided with information that not only allows it to avoid collisions with obstacles present in the environment, but also information about the localization, the class and the shape of each encountered object instance. This level of perception enhances the robot's ability to interact with the environment. The state-of-the-art deep learning solution, Mask-RCNN, is used for the image segmentation task. The image processing network is combined with an RTAB-Map SLAM algorithm to generate semantic pointclouds of the environment. The final part of the paper is focused on pointcloud processing: providing methods for instance extraction and instance processing. To verify the performance of the proposed methodology multiple experiments are conducted. Through the evaluation of the results it is possible to identify possible improvements.

AB - In this paper the authors present a full solution for object-level semantic perception of the environment by indoor mobile robots. The proposed solution not only provides means for semantic mapping but also division of the environment into clusters representing singular object instances. The robot is provided with information that not only allows it to avoid collisions with obstacles present in the environment, but also information about the localization, the class and the shape of each encountered object instance. This level of perception enhances the robot's ability to interact with the environment. The state-of-the-art deep learning solution, Mask-RCNN, is used for the image segmentation task. The image processing network is combined with an RTAB-Map SLAM algorithm to generate semantic pointclouds of the environment. The final part of the paper is focused on pointcloud processing: providing methods for instance extraction and instance processing. To verify the performance of the proposed methodology multiple experiments are conducted. Through the evaluation of the results it is possible to identify possible improvements.

U2 - 10.1088/1757-899X/517/1/012012

DO - 10.1088/1757-899X/517/1/012012

M3 - Journal article

VL - 517

JO - I O P Conference Series: Materials Science and Engineering

JF - I O P Conference Series: Materials Science and Engineering

SN - 1757-8981

IS - 1

M1 - 012012

ER -