ePrints

SWiMM DEEPeR: A Simulated Underwater Environment for Tracking Marine Mammals Using Deep Reinforcement Learning and BlueROV2

Lookup NU author(s): Sam Appleby, Kirsten Crane, Dr Giacomo BergamiORCiD, Dr Stephen McGough

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

This paper offers a feasibility study on using simulated environments for training autonomous underwater vehicles (AUVs). With the goal of monitoring marine megafauna, we propose a Unity-hosted simulation of a realistic open ocean environment, with a focus on simulating Blue Robotics’ BlueROV2. The result is SWiMM DEEPeR ¹ , coupling the former simulation with a reinforcement learning (RL) pipeline. Animated marine mammal models emulate the target objects of the real-world deployment scenario, offering a solution in a new application space (conservation) as well as a new problem space (visual active tracking). We provide experiments with respect to each stage of the proposed pipeline: i) image similarity experiments provide evidence for decisions around image rendering and data transfer, ii) autoencoder training demonstrates the feasibility of mapping raw images to low-dimensional feature representations, iii) agent training demonstrates successful self-learnt vehicle control.

Publication metadata

Author(s): Appleby S, Crane K, Bergami G, McGough AS

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: IEEE Conference on Games

Year of Conference: 2023

Pages: 1-8

Online publication date: 04/12/2023

Acceptance date: 09/05/2023

ISSN: 9798350322774

Publisher: IEEE

URL: https://doi.org/10.1109/CoG57401.2023.10333168

DOI: 10.1109/CoG57401.2023.10333168

Share