COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning
Path Following and Collision Avoidance, be it for unmanned surface vessels or other autonomous vehicles, are two fundamental guidance problems in robotics. For many decades, they have been subject to academic study, leading to a vast number of proposed approaches. However, they have mostly been trea...
Main Authors: | , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2020
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2006.09540 https://arxiv.org/abs/2006.09540 |
id |
ftdatacite:10.48550/arxiv.2006.09540 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2006.09540 2023-05-15T17:47:06+02:00 COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning Meyer, Eivind Heiberg, Amalie Rasheed, Adil San, Omer 2020 https://dx.doi.org/10.48550/arxiv.2006.09540 https://arxiv.org/abs/2006.09540 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Robotics cs.RO Artificial Intelligence cs.AI Machine Learning cs.LG FOS Computer and information sciences Article CreativeWork article Preprint 2020 ftdatacite https://doi.org/10.48550/arxiv.2006.09540 2022-03-10T15:29:18Z Path Following and Collision Avoidance, be it for unmanned surface vessels or other autonomous vehicles, are two fundamental guidance problems in robotics. For many decades, they have been subject to academic study, leading to a vast number of proposed approaches. However, they have mostly been treated as separate problems, and have typically relied on non-linear first-principles models with parameters that can only be determined experimentally. The rise of Deep Reinforcement Learning (DRL) in recent years suggests an alternative approach: end-to-end learning of the optimal guidance policy from scratch by means of a trial-and-error based approach. In this article, we explore the potential of Proximal Policy Optimization (PPO), a DRL algorithm with demonstrated state-of-the-art performance on Continuous Control tasks, when applied to the dual-objective problem of controlling an underactuated Autonomous Surface Vehicle in a COLREGs compliant manner such that it follows an a priori known desired path while avoiding collisions with other vessels along the way. Based on high-fidelity elevation and AIS tracking data from the Trondheim Fjord, an inlet of the Norwegian sea, we evaluate the trained agent's performance in challenging, dynamic real-world scenarios where the ultimate success of the agent rests upon its ability to navigate non-uniform marine terrain while handling challenging, but realistic vessel encounters. Article in Journal/Newspaper Norwegian Sea DataCite Metadata Store (German National Library of Science and Technology) Norwegian Sea |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Robotics cs.RO Artificial Intelligence cs.AI Machine Learning cs.LG FOS Computer and information sciences |
spellingShingle |
Robotics cs.RO Artificial Intelligence cs.AI Machine Learning cs.LG FOS Computer and information sciences Meyer, Eivind Heiberg, Amalie Rasheed, Adil San, Omer COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning |
topic_facet |
Robotics cs.RO Artificial Intelligence cs.AI Machine Learning cs.LG FOS Computer and information sciences |
description |
Path Following and Collision Avoidance, be it for unmanned surface vessels or other autonomous vehicles, are two fundamental guidance problems in robotics. For many decades, they have been subject to academic study, leading to a vast number of proposed approaches. However, they have mostly been treated as separate problems, and have typically relied on non-linear first-principles models with parameters that can only be determined experimentally. The rise of Deep Reinforcement Learning (DRL) in recent years suggests an alternative approach: end-to-end learning of the optimal guidance policy from scratch by means of a trial-and-error based approach. In this article, we explore the potential of Proximal Policy Optimization (PPO), a DRL algorithm with demonstrated state-of-the-art performance on Continuous Control tasks, when applied to the dual-objective problem of controlling an underactuated Autonomous Surface Vehicle in a COLREGs compliant manner such that it follows an a priori known desired path while avoiding collisions with other vessels along the way. Based on high-fidelity elevation and AIS tracking data from the Trondheim Fjord, an inlet of the Norwegian sea, we evaluate the trained agent's performance in challenging, dynamic real-world scenarios where the ultimate success of the agent rests upon its ability to navigate non-uniform marine terrain while handling challenging, but realistic vessel encounters. |
format |
Article in Journal/Newspaper |
author |
Meyer, Eivind Heiberg, Amalie Rasheed, Adil San, Omer |
author_facet |
Meyer, Eivind Heiberg, Amalie Rasheed, Adil San, Omer |
author_sort |
Meyer, Eivind |
title |
COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning |
title_short |
COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning |
title_full |
COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning |
title_fullStr |
COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning |
title_full_unstemmed |
COLREG-Compliant Collision Avoidance for Unmanned Surface Vehicle using Deep Reinforcement Learning |
title_sort |
colreg-compliant collision avoidance for unmanned surface vehicle using deep reinforcement learning |
publisher |
arXiv |
publishDate |
2020 |
url |
https://dx.doi.org/10.48550/arxiv.2006.09540 https://arxiv.org/abs/2006.09540 |
geographic |
Norwegian Sea |
geographic_facet |
Norwegian Sea |
genre |
Norwegian Sea |
genre_facet |
Norwegian Sea |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2006.09540 |
_version_ |
1766151413977579520 |