A Navigation System for ROV's inspection on Fish Net Cage

2025-03-01

AI Summary

To address the low efficiency and high operational risk associated with manual inspection of fishing net enclosures, this paper proposes a navigation system for autonomous underwater vehicle (AUV)-based inspection. Built upon the BlueROV2 platform and the Robot Operating System (ROS), the system integrates TagSLAM to achieve GPS-denied, high-precision underwater visual localization (centimeter-level accuracy) in localized environments. A robust trajectory-tracking strategy is designed using a nominal feedback controller (NFC), complemented by low-level PID motion control and Ultra-Wideband (UWB)-aided pose calibration. The approach overcomes key challenges in complex aquaculture environments—including structural occlusions and texture-poor surfaces—that typically degrade localization and tracking performance. End-to-end validation was conducted in a controlled laboratory water tank, demonstrating stable and accurate autonomous path execution. The system significantly enhances inspection automation and operational reliability in underwater net monitoring tasks.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Vision for Robotics & Autonomous Driving

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Autonomous Remotely Operated Vehicles (ROVs) offer a promising solution for automating fishnet inspection, reducing labor dependency, and improving operational efficiency. In this paper, we modify an off-the-shelf ROV, the BlueROV2, into a ROS-based framework and develop a localization module, a path planning system, and a control framework. For real-time, local localization, we employ the open-source TagSLAM library. Additionally, we propose a control strategy based on a Nominal Feedback Controller (NFC) to achieve precise trajectory tracking. The proposed system has been implemented and validated through experiments in a controlled laboratory environment, demonstrating its effectiveness for real-world applications.

Problem

• Automating fishnet inspection using ROVs to reduce labor dependency.
• Developing a ROS-based framework for ROV navigation and control.
• Implementing real-time localization and precise trajectory tracking systems.

Innovation

• Modified BlueROV2 with ROS-based framework
• Used TagSLAM for real-time localization
• Implemented NFC for precise trajectory tracking