SOLAQUA: SINTEF Ocean Large Aquaculture Robotics Dataset

TL;DR

SOLAQUA introduces a large-scale, multi-modal underwater dataset collected from an operational sea-based fish farm to support autonomous navigation and inspection in net pens. It uses a BlueROV2 platform to record synchronized streams from DVLs (A50, Nucleus 1000), USBL, Sonoptix multibeam sonar, mono and stereo cameras, and vehicle sensors, under both manual and net-following autonomy. The paper documents sensor placements, camera calibration (intrinsic/extrinsic for mono/stereo rigs) and ground-truth via AprilTag markers, with data logged as ROS bag files and made available under CC BY-SA. The dataset aims to facilitate robust localization, mapping, and vision-based navigation in dynamic aquaculture environments, enabling safer and more efficient IMR operations at industrial scales.

Abstract

This paper presents a dataset gathered with an underwater robot in a sea-based aquaculture setting. Data was gathered from an operational fish farm and includes data from sensors such as the Waterlinked A50 DVL, the Nortek Nucleus 1000 DVL, Sonardyne Micro Ranger 2 USBL, Sonoptix Mulitbeam Sonar, mono and stereo cameras, and vehicle sensor data such as power usage, IMU, pressure, temperature, and more. Data acquisition is performed during both manual and autonomous traversal of the net pen structure. The collected vision data is of undamaged nets with some fish and marine growth presence, and it is expected that both the research community and the aquaculture industry will benefit greatly from the utilization of the proposed SOLAQUA dataset.

Figures (11)

• Figure 1: ROV with two different sensor configurations.
• Figure 2: The net-relative sway speed measured by the Water Linked A50 and the Nortek Nucleus 1000 DVL.
• Figure 3: ROV distance to net (blue) and desired distance (red).
• Figure 4: ROV heading relative to net (blue) and desired net relative heading (red).
• Figure 5: ROV net relative sway speed (blue) and desired speed (red).