Aquaculture Robotics: Adaptive Path Planning through Real-Time Estimation of the Shape of Flexible Net Pens
Herman Biørn Amundsen, Eirini Katsidoniotaki, Martin Føre, Eleni Kelasidi
AI summary
Problem
Flexible aquaculture net pens constantly deform due to ocean currents and waves, making autonomous robot navigation difficult and collision-prone. Existing estimation methods either require costly net instrumentation, lack real-time global shape data, or depend on unavailable current measurements.
Approach
The method fuses sparse distance measurements from a forward-looking DVL on the ROV with a numerical net pen model to continuously estimate the pen's full shape in real-time. This estimated shape is then used to plan and update safe, net-relative waypoints for closed-loop autonomous navigation.
Key results
- Real-time full net pen shape estimation without external instrumentation or current data
- 0.5 m root mean square error for global net structure estimation in simulations
- Centimeter-level accuracy in estimating ROV-to-net distance
- Successful autonomous ROV navigation and inspection in full-scale industrial trials
Why it matters
Enables safer, cost-effective autonomous inspection and maintenance of offshore aquaculture facilities by eliminating the need for costly net instrumentation and reducing reliance on human pilots.
Abstract
Aquaculture is a marine industry experiencing significant growth and an important seafood provider. Underwater vehicles such as remotely operated vehicles (ROVs) are commonly used for inspection and maintenance of the net pens where the fish are grown. These net pens are flexible structures whose position and shape change with ocean currents and waves. Any autonomous robotic operation in aquaculture is therefore challenging as the net pen position and shape cannot be predetermined and since it is imperative that the robot does not collide with and damage the net. This article addresses this issue by proposing a novel method to estimate the full shape of aquaculture net pens in real time using an underwater vehicle equipped with a forward-looking Doppler velocity log. The method introduces a new concept for how sparse measurement data on the net pen can be fused with numerical models of the full net pen that contrasts other models in literature by not requiring instrumentation on the net pen nor knowledge of ocean current conditions. The estimator output is then used in closed-loop vehicle control by planning and following paths relative to the estimated pen shape. The method is tested in simulations, which show an root mean square error (RMSE) of 0.5 m for estimate of the entire net pen structure and centimeter-level estimation error of the distance between the vehicle and net, and in full-scale trials in an industrial fish farm where an ROV autonomously navigated a net pen.