Aquaculture America 2024

February 18 - 21, 2024

San Antonio, Texas

AQUACULTURE ROBOTICS RESEARCH AT SINTEF OCEAN – AUTONOMY, NAVIGATION, AND MOTION PLANNING DEDICATED TO IMPROVE EFFICIENCY, SAFETY AND FISH WELFARE

Sveinung Johan Ohrem*, Eleni Kelasidi, Herman Biørn Amundsen, Linn Danielsen Evjemo, Bent Haugaløkken, Oscar Nissen, Aya Saad, Martin Skaldebø , Marios Xanthidis

Department of Aquaculture

SINTEF Ocean AS

Brattørakaia 17C

7010 Trondheim, Norway

Sveinung.ohrem@sintef.no

 



Research on aquaculture robotics at SINTEF Ocean targets the development of dedicated solutions for the aquaculture industry and aims to address the industry’s challenges related to navigating and manoeuvring in dynamically changing environments, performing  intervention  and inspection operations, and increasing the level of autonomy .  With  an  interdisciplinary  focus, we are linking the fields of technology and biology and perform fundamental and applied research on the modelling of UUVs, aquaculture structures, fish behaviour and environmental disturbances, and on advanced control strategies for the autonomous navigation of unmanned underwater and surface vehicles operating in dynamically changing environments.

 Through variety of projects, we  have  developed methods and robotic solutions for autonomous operations in fish farms (to name few of them: CHANGE, ResiFarm , NetClean 24/7, RACE-Fish Machine Interaction, CageReporter and Artifex). Some of our developments include autonomous net following, framework for navigation inside net pens, robust low-level control methods and motion planning systems including obstacle avoidance. We own and use a variety of robotic systems including aerial, surface, and underwater vehicles. In addition we contribute  to the development of new, dedicated robotic systems suitable for operating in both traditional sea-based fish farms and new production technologies . SINTEF Ocean owns four research licenses for farmed Atlantic salmon ( Salmo salar ) and we can therefore test and demonstrate our developed methods in realistic environments (Figs. 1 and 2).