High-Fidelity Simulation Platform for Autonomous Fish Net-Pen Visual Inspection With Unmanned Underwater Vehicles in Offshore Aquaculture

Abstract

Abstract The importance of high-fidelity simulation in the deployment of Unmanned Underwater Vehicles (UUVs) in offshore aquaculture is evident, driven by a range of crucial factors such as safe deployment in challenging working environments. Such simulations enable thorough testing and refinement of UUV behavior, thereby mitigating safety concerns associated with human workforce exposure to risk. Additionally, the intricate preparations for real-world field trials involving multiple stakeholders require thorough planning. High-fidelity simulations serve a pivotal role as an informed decision-making tool in a cost-efficient way in aligning these diverse stakeholders and in pre-validating the advantages and challenges associated with UUV deployment in uncertain and demanding offshore aquaculture environments. In this paper, a number of existing simulation platforms are reported and using one of them which is built on the Robot Operating System (ROS) in Python, namely UUV simulator, an autonomous fish net-pen visual inspection with the BlueROV2 Heavy Configuration for the Blue Endeavour project (an upcoming first offshore aquaculture firm in New Zealand) of the New Zealand King Salmon company was demonstrated as a use-case study.