A Deep Learning Framework for Robust Semantic SLAM

Azzam, R; Taha, T; Huang, S; Zweiri, Y

A Deep Learning Framework for Robust Semantic SLAM

Azzam, R Taha, T Huang, S

Zweiri, Y

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2020 Advances in Science and Engineering Technology International Conferences (ASET), 2020, 00, pp. 1-7
Issue Date:: 2020-06-16

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted Manuscript VersionAdobe PDF (1.78 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Azzam, R
dc.contributor.author	Taha, T
dc.contributor.author	Huang, S https://orcid.org/0000-0002-6124-4178
dc.contributor.author	Zweiri, Y
dc.date	2020-02-04
dc.date.accessioned	2021-03-30T04:43:59Z
dc.date.available	2021-03-30T04:43:59Z
dc.date.issued	2020-06-16
dc.identifier.citation	2020 Advances in Science and Engineering Technology International Conferences (ASET), 2020, 00, pp. 1-7
dc.identifier.isbn	978-1-7281-4641-6
dc.identifier.uri	http://hdl.handle.net/10453/147661
dc.description.abstract	Semantic simultaneous localization and mapping (SLAM) is susceptible to several sources of noise that hinder the accuracy of its trajectory and map estimates. Such sources include inaccurate landmark pose estimation and sensor limitations. In this paper, a novel deep learning based approach is proposed to improve the accuracy of semantic SLAM by reducing the trajectory estimation error. A deep neural network consisting of various non-linear activation functions is structured and pre-trained by means of an unsupervised greedy layer-wise pre-training technique. The network is then fine-tuned using the adaptive moment estimation (Adam) optimizer. The training datasets were collected using several simulated and realtime experiments and are composed of two parts, the estimated trajectory and the corresponding ground truth. Ground truth trajectories were obtained using a motion capture system in realtime experiments. The effectiveness of the proposed approach was shown through simulated experiments, real-time experiments, and a sequence from the Technical University of Munich (TUM) RGB-D dataset. The performance of the deep neural network (DNN) was tested with different pre-training techniques and the proposed unsupervised greedy layer-wise pre-training technique proved to perform the best across training, validation, and testing datasets in terms of reducing the mean absolute trajectory error (ATE).
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2020 Advances in Science and Engineering Technology International Conferences (ASET)
dc.relation.ispartof	2020 Advances in Science and Engineering Technology International Conferences
dc.relation.isbasedon	10.1109/aset48392.2020.9118181
dc.rights	© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.rights	info:eu-repo/semantics/openAccess
dc.title	A Deep Learning Framework for Robust Semantic SLAM
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Dubai, United Arab Emirates
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAS - Centre for Autonomous Systems
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
utslib.copyright.status	open_access	*
dc.date.updated	2021-03-30T04:43:57Z
pubs.finish-date	2020-04-09
pubs.publication-status	Published
pubs.start-date	2020-02-04
pubs.volume	00

Abstract:

Semantic simultaneous localization and mapping (SLAM) is susceptible to several sources of noise that hinder the accuracy of its trajectory and map estimates. Such sources include inaccurate landmark pose estimation and sensor limitations. In this paper, a novel deep learning based approach is proposed to improve the accuracy of semantic SLAM by reducing the trajectory estimation error. A deep neural network consisting of various non-linear activation functions is structured and pre-trained by means of an unsupervised greedy layer-wise pre-training technique. The network is then fine-tuned using the adaptive moment estimation (Adam) optimizer. The training datasets were collected using several simulated and realtime experiments and are composed of two parts, the estimated trajectory and the corresponding ground truth. Ground truth trajectories were obtained using a motion capture system in realtime experiments. The effectiveness of the proposed approach was shown through simulated experiments, real-time experiments, and a sequence from the Technical University of Munich (TUM) RGB-D dataset. The performance of the deep neural network (DNN) was tested with different pre-training techniques and the proposed unsupervised greedy layer-wise pre-training technique proved to perform the best across training, validation, and testing datasets in terms of reducing the mean absolute trajectory error (ATE).

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/147661