Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Biology and Technology Interaction: Study identifying the impact of robotic systems on fish behaviour change in industrial scale fish farms

Linn Danielsen Evjemo, Qin Zhang, Hanne-Grete Alvheim, Herman Biørn Amundsen, Martin Føre, Eleni Kelasidi

TL;DR

The study tackles the problem of quantifying how industrial-scale robotic operations influence the behaviour of farmed Atlantic salmon in sea-based cages. It adopts field-scale experiments at a Norwegian research facility using an Argus Mini ROV equipped with Ping360 sonars and a stereo camera, and analyzes responses with a DL sonar segmentation approach, a stereo-vision tracking pipeline, and qualitative video scoring. The findings indicate that thruster activity, sudden forwards movement, and active upwards movement elicit the most pronounced fish responses, with cross-method agreement in strong cases but variability in subtler movements. These insights can guide the design of fish-friendly robotic operations and inform sensor and algorithmic strategies to monitor welfare in aquaculture robotics.

Abstract

The significant growth in the aquaculture industry over the last few decades encourages new technological and robotic solutions to help improve the efficiency and safety of production. In sea-based farming of Atlantic salmon in Norway, Unmanned Underwater Vehicles (UUVs) are already being used for inspection tasks. While new methods, systems and concepts for sub-sea operations are continuously being developed, these systems generally does not take into account how their presence might impact the fish. This abstract presents an experimental study on how underwater robotic operations at fish farms in Norway can affect farmed Atlantic salmon, and how the fish behaviour changes when exposed to the robot. The abstract provides an overview of the case study, the methods of analysis, and some preliminary results.

Biology and Technology Interaction: Study identifying the impact of robotic systems on fish behaviour change in industrial scale fish farms

TL;DR

The study tackles the problem of quantifying how industrial-scale robotic operations influence the behaviour of farmed Atlantic salmon in sea-based cages. It adopts field-scale experiments at a Norwegian research facility using an Argus Mini ROV equipped with Ping360 sonars and a stereo camera, and analyzes responses with a DL sonar segmentation approach, a stereo-vision tracking pipeline, and qualitative video scoring. The findings indicate that thruster activity, sudden forwards movement, and active upwards movement elicit the most pronounced fish responses, with cross-method agreement in strong cases but variability in subtler movements. These insights can guide the design of fish-friendly robotic operations and inform sensor and algorithmic strategies to monitor welfare in aquaculture robotics.

Abstract

The significant growth in the aquaculture industry over the last few decades encourages new technological and robotic solutions to help improve the efficiency and safety of production. In sea-based farming of Atlantic salmon in Norway, Unmanned Underwater Vehicles (UUVs) are already being used for inspection tasks. While new methods, systems and concepts for sub-sea operations are continuously being developed, these systems generally does not take into account how their presence might impact the fish. This abstract presents an experimental study on how underwater robotic operations at fish farms in Norway can affect farmed Atlantic salmon, and how the fish behaviour changes when exposed to the robot. The abstract provides an overview of the case study, the methods of analysis, and some preliminary results.
Paper Structure (18 sections, 3 figures, 1 table)

This paper contains 18 sections, 3 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. Experimental setup and data acquisition
  3. Experimental Case Studies
  4. Thruster effects
  5. Forwards motion effects
  6. Turning effects
  7. Upwards motion effects
  8. Data Acquisition
  9. Methods
  10. Sonar data analysis
  11. Stereo Vision Method
  12. Qualitative Results from video data
  13. Preliminary results
  14. Thrusters off - on low - on high
  15. Forwards movement
  16. ...and 3 more sections

Figures (3)

  • Figure 1: Illustrations of experimental case studies. (a) integrated sensors on ROV; (b) Argus Mini ROV with integrated sensors during deployment at ACE facilities;(c) Stationary position with A: Active thrusters, B: No thruster activity; (d) A: Forwards movement, B: Stationary; (e) A: Turning, B: Stationary; (f) A1: Upwards passive movement, A2: Upwards active movement, B: Stationary
  • Figure 2: Thruster effects on fish behaviour
  • Figure 3: Results from the blind analysis: Collective Forward, Turning, Upwards Active and Upwards Passive.