Autonomous port navigation with ranging sensors using model-based reinforcement learning
Abstract: Autonomous shipping has recently gained much interest in the research community. However, little research focuses on inland - and port navigation, even though this is identified by countries such as Belgium and the Netherlands as an essential step towards a sustainable future. These enviro...
Published in: | Volume 5: Ocean Engineering |
---|---|
Main Authors: | , , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10067/2009940151162165141 |
id |
ftunivantwerpen:c:irua:200994 |
---|---|
record_format |
openpolar |
spelling |
ftunivantwerpen:c:irua:200994 2023-12-24T10:12:00+01:00 Autonomous port navigation with ranging sensors using model-based reinforcement learning Herremans, Siemen Anwar, Ali Troch, Arne Ravijts, Ian Vangeneugden, Maarten Mercelis, Siegfried Hellinckx, Peter 2023 https://hdl.handle.net/10067/2009940151162165141 eng eng info:eu-repo/semantics/altIdentifier/doi/10.1115/OMAE2023-104455 info:eu-repo/semantics/closedAccess 42nd International Conference on Ocean, Offshore & Arctic Engineering, 11-16 June, 2023, Melbourne, Australia 978-0-7918-8687-8 Engineering sciences. Technology info:eu-repo/semantics/conferenceObject 2023 ftunivantwerpen https://doi.org/10.1115/OMAE2023-104455 2023-11-29T23:24:23Z Abstract: Autonomous shipping has recently gained much interest in the research community. However, little research focuses on inland - and port navigation, even though this is identified by countries such as Belgium and the Netherlands as an essential step towards a sustainable future. These environments pose unique challenges, since they can contain dynamic obstacles that do not broadcast their location, such as small vessels, kayaks or buoys. Therefore, this research proposes a navigational algorithm which can navigate an inland vessel in a wide variety of complex port scenarios using ranging sensors to observe the environment. The proposed methodology is based on a machine learning approach that has recently set benchmark results in various domains: model-based reinforcement learning. By randomizing the port environments during training, the trained model can navigate in scenarios that it never encountered during training. Furthermore, results show that our approach outperforms the commonly used dynamic window approach and a benchmark model-free reinforcement learning algorithm. This work is therefore a significant step towards vessels that can navigate autonomously in complex port scenarios. Conference Object Arctic IRUA - Institutional Repository van de Universiteit Antwerpen Volume 5: Ocean Engineering |
institution |
Open Polar |
collection |
IRUA - Institutional Repository van de Universiteit Antwerpen |
op_collection_id |
ftunivantwerpen |
language |
English |
topic |
Engineering sciences. Technology |
spellingShingle |
Engineering sciences. Technology Herremans, Siemen Anwar, Ali Troch, Arne Ravijts, Ian Vangeneugden, Maarten Mercelis, Siegfried Hellinckx, Peter Autonomous port navigation with ranging sensors using model-based reinforcement learning |
topic_facet |
Engineering sciences. Technology |
description |
Abstract: Autonomous shipping has recently gained much interest in the research community. However, little research focuses on inland - and port navigation, even though this is identified by countries such as Belgium and the Netherlands as an essential step towards a sustainable future. These environments pose unique challenges, since they can contain dynamic obstacles that do not broadcast their location, such as small vessels, kayaks or buoys. Therefore, this research proposes a navigational algorithm which can navigate an inland vessel in a wide variety of complex port scenarios using ranging sensors to observe the environment. The proposed methodology is based on a machine learning approach that has recently set benchmark results in various domains: model-based reinforcement learning. By randomizing the port environments during training, the trained model can navigate in scenarios that it never encountered during training. Furthermore, results show that our approach outperforms the commonly used dynamic window approach and a benchmark model-free reinforcement learning algorithm. This work is therefore a significant step towards vessels that can navigate autonomously in complex port scenarios. |
format |
Conference Object |
author |
Herremans, Siemen Anwar, Ali Troch, Arne Ravijts, Ian Vangeneugden, Maarten Mercelis, Siegfried Hellinckx, Peter |
author_facet |
Herremans, Siemen Anwar, Ali Troch, Arne Ravijts, Ian Vangeneugden, Maarten Mercelis, Siegfried Hellinckx, Peter |
author_sort |
Herremans, Siemen |
title |
Autonomous port navigation with ranging sensors using model-based reinforcement learning |
title_short |
Autonomous port navigation with ranging sensors using model-based reinforcement learning |
title_full |
Autonomous port navigation with ranging sensors using model-based reinforcement learning |
title_fullStr |
Autonomous port navigation with ranging sensors using model-based reinforcement learning |
title_full_unstemmed |
Autonomous port navigation with ranging sensors using model-based reinforcement learning |
title_sort |
autonomous port navigation with ranging sensors using model-based reinforcement learning |
publishDate |
2023 |
url |
https://hdl.handle.net/10067/2009940151162165141 |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
42nd International Conference on Ocean, Offshore & Arctic Engineering, 11-16 June, 2023, Melbourne, Australia 978-0-7918-8687-8 |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1115/OMAE2023-104455 |
op_rights |
info:eu-repo/semantics/closedAccess |
op_doi |
https://doi.org/10.1115/OMAE2023-104455 |
container_title |
Volume 5: Ocean Engineering |
_version_ |
1786172107366858752 |