Adaptive Deep Reinforcement Learning for Efficient 3D Navigation of Autonomous Underwater Vehicles

The exploration of the underwater environments has recently accelerated with the development of the Autonomous Underwater Vehicle (AUV). One of the key elements for enhancing the autonomy of AUVs navigation across various applications is efficient path planning. Reinforcement Learning (RL) methods h...

Full description

Saved in:
Bibliographic Details
Main Authors: Elena Politi, Artemis Stefanidou, Christos Chronis, George Dimitrakopoulos, and Iraklis Varlamis
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10770217/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850263631075213312
author Elena Politi
Artemis Stefanidou
Christos Chronis
George Dimitrakopoulos
and Iraklis Varlamis
author_facet Elena Politi
Artemis Stefanidou
Christos Chronis
George Dimitrakopoulos
and Iraklis Varlamis
author_sort Elena Politi
collection DOAJ
description The exploration of the underwater environments has recently accelerated with the development of the Autonomous Underwater Vehicle (AUV). One of the key elements for enhancing the autonomy of AUVs navigation across various applications is efficient path planning. Reinforcement Learning (RL) methods have been successfully introduced for path planning of AUVs, particularly in high-dimensional state spaces, where prior knowledge of the environment is unfeasible. In this work, we propose a Deep Reinforcement Learning (DRL) method for efficient AUV navigation in 3 Dimension (3D) environments, utilizing input from vision sensors to obtain information about the motion of the AUV and the surrounding space. We adopt a multi-tier approach in order to validate the performance of the proposed DRL approach in three different neural network architectures leveraging on adaptation and accuracy, with path length, execution time and success of operation being considered as the optimization objectives. Finally, a simulation platform is built to evaluate the performance of the proposed method, with experimental results showcasing enhanced decision-making capability for the AUV navigation, which translates to a higher level of autonomy for the vehicle in unknown environments.
format Article
id doaj-art-8b3faf26bebd436aa50dce081f33c335
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-8b3faf26bebd436aa50dce081f33c3352025-08-20T01:54:55ZengIEEEIEEE Access2169-35362024-01-011217820917822110.1109/ACCESS.2024.350803110770217Adaptive Deep Reinforcement Learning for Efficient 3D Navigation of Autonomous Underwater VehiclesElena Politi0https://orcid.org/0000-0001-8795-5560Artemis Stefanidou1https://orcid.org/0009-0008-2059-7429Christos Chronis2https://orcid.org/0000-0002-2768-7119George Dimitrakopoulos3https://orcid.org/0000-0002-7424-8557and Iraklis Varlamis4https://orcid.org/0000-0002-0876-8167Department of Informatics and Telematics, Harokopio University of Athens, Athens, GreeceDepartment of Informatics and Telematics, Harokopio University of Athens, Athens, GreeceDepartment of Informatics and Telematics, Harokopio University of Athens, Athens, GreeceDepartment of Informatics and Telematics, Harokopio University of Athens, Athens, GreeceDepartment of Informatics and Telematics, Harokopio University of Athens, Athens, GreeceThe exploration of the underwater environments has recently accelerated with the development of the Autonomous Underwater Vehicle (AUV). One of the key elements for enhancing the autonomy of AUVs navigation across various applications is efficient path planning. Reinforcement Learning (RL) methods have been successfully introduced for path planning of AUVs, particularly in high-dimensional state spaces, where prior knowledge of the environment is unfeasible. In this work, we propose a Deep Reinforcement Learning (DRL) method for efficient AUV navigation in 3 Dimension (3D) environments, utilizing input from vision sensors to obtain information about the motion of the AUV and the surrounding space. We adopt a multi-tier approach in order to validate the performance of the proposed DRL approach in three different neural network architectures leveraging on adaptation and accuracy, with path length, execution time and success of operation being considered as the optimization objectives. Finally, a simulation platform is built to evaluate the performance of the proposed method, with experimental results showcasing enhanced decision-making capability for the AUV navigation, which translates to a higher level of autonomy for the vehicle in unknown environments.https://ieeexplore.ieee.org/document/10770217/AUVunderwateractor-critic algorithmAUV navigationdynamic path planningproximal policy optimization
spellingShingle Elena Politi
Artemis Stefanidou
Christos Chronis
George Dimitrakopoulos
and Iraklis Varlamis
Adaptive Deep Reinforcement Learning for Efficient 3D Navigation of Autonomous Underwater Vehicles
IEEE Access
AUV
underwater
actor-critic algorithm
AUV navigation
dynamic path planning
proximal policy optimization
title Adaptive Deep Reinforcement Learning for Efficient 3D Navigation of Autonomous Underwater Vehicles
title_full Adaptive Deep Reinforcement Learning for Efficient 3D Navigation of Autonomous Underwater Vehicles
title_fullStr Adaptive Deep Reinforcement Learning for Efficient 3D Navigation of Autonomous Underwater Vehicles
title_full_unstemmed Adaptive Deep Reinforcement Learning for Efficient 3D Navigation of Autonomous Underwater Vehicles
title_short Adaptive Deep Reinforcement Learning for Efficient 3D Navigation of Autonomous Underwater Vehicles
title_sort adaptive deep reinforcement learning for efficient 3d navigation of autonomous underwater vehicles
topic AUV
underwater
actor-critic algorithm
AUV navigation
dynamic path planning
proximal policy optimization
url https://ieeexplore.ieee.org/document/10770217/
work_keys_str_mv AT elenapoliti adaptivedeepreinforcementlearningforefficient3dnavigationofautonomousunderwatervehicles
AT artemisstefanidou adaptivedeepreinforcementlearningforefficient3dnavigationofautonomousunderwatervehicles
AT christoschronis adaptivedeepreinforcementlearningforefficient3dnavigationofautonomousunderwatervehicles
AT georgedimitrakopoulos adaptivedeepreinforcementlearningforefficient3dnavigationofautonomousunderwatervehicles
AT andiraklisvarlamis adaptivedeepreinforcementlearningforefficient3dnavigationofautonomousunderwatervehicles