Machine learning-based local collision avoidance for maritime navigation

This report investigates the application of Deep Reinforcement Learning (DRL) in collision avoidance in maritime navigation. In this study, the transfer of DRL methods from land to sea environment was studied, with a focus on the ability of this extensive range of techniques to generalize. Our thoro...

Full description

Saved in:
Bibliographic Details
Main Author: Zou, Yixuan
Other Authors: Jiang Xudong
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/177278
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-177278
record_format dspace
spelling sg-ntu-dr.10356-1772782024-05-31T15:44:16Z Machine learning-based local collision avoidance for maritime navigation Zou, Yixuan Jiang Xudong School of Electrical and Electronic Engineering EXDJiang@ntu.edu.sg Engineering Maritime navigation Machine learning Collision avoidance This report investigates the application of Deep Reinforcement Learning (DRL) in collision avoidance in maritime navigation. In this study, the transfer of DRL methods from land to sea environment was studied, with a focus on the ability of this extensive range of techniques to generalize. Our thorough analysis classifies significant DRL studies according to important variables such as evaluating potential dangers, selecting algorithms, adhering to International Regulations for Preventing Collisions at Sea (COLREGs), and utilizing Automatic Identification System (AIS) data. In this study, we also examine the differences between DRL approaches that are implemented on-policy and off-policy and evaluate their appropriateness for various navigation scenarios. As a former study for the model training in sea environment, agent was trained in various ground environment using TD3 algorithm during the research. By capitalizing on the sophisticated dynamics of the simulation environment and utilizing the strengths of DRL, this integrated approach guarantees a solid foundation for further research of autonomous vessel navigation. Bachelor's degree 2024-05-27T07:48:23Z 2024-05-27T07:48:23Z 2024 Final Year Project (FYP) Zou, Y. (2024). Machine learning-based local collision avoidance for maritime navigation. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/177278 https://hdl.handle.net/10356/177278 en J3333-232 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering
Maritime navigation
Machine learning
Collision avoidance
spellingShingle Engineering
Maritime navigation
Machine learning
Collision avoidance
Zou, Yixuan
Machine learning-based local collision avoidance for maritime navigation
description This report investigates the application of Deep Reinforcement Learning (DRL) in collision avoidance in maritime navigation. In this study, the transfer of DRL methods from land to sea environment was studied, with a focus on the ability of this extensive range of techniques to generalize. Our thorough analysis classifies significant DRL studies according to important variables such as evaluating potential dangers, selecting algorithms, adhering to International Regulations for Preventing Collisions at Sea (COLREGs), and utilizing Automatic Identification System (AIS) data. In this study, we also examine the differences between DRL approaches that are implemented on-policy and off-policy and evaluate their appropriateness for various navigation scenarios. As a former study for the model training in sea environment, agent was trained in various ground environment using TD3 algorithm during the research. By capitalizing on the sophisticated dynamics of the simulation environment and utilizing the strengths of DRL, this integrated approach guarantees a solid foundation for further research of autonomous vessel navigation.
author2 Jiang Xudong
author_facet Jiang Xudong
Zou, Yixuan
format Final Year Project
author Zou, Yixuan
author_sort Zou, Yixuan
title Machine learning-based local collision avoidance for maritime navigation
title_short Machine learning-based local collision avoidance for maritime navigation
title_full Machine learning-based local collision avoidance for maritime navigation
title_fullStr Machine learning-based local collision avoidance for maritime navigation
title_full_unstemmed Machine learning-based local collision avoidance for maritime navigation
title_sort machine learning-based local collision avoidance for maritime navigation
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/177278
_version_ 1814047282542149632