Design and Implementation of Unmanned Surface Vehicle JEROS for Jellyfish Removal

Donghoon Kim, Jae-Uk Shin, Hyongjin Kim, Hanguen Kim, Donghwa Lee, Seung‐Mok Lee, Hyun MyungThe Journal of Korea Robotics Society 2013 · DOI

Abstract

Recently, the number of jellyfish has been rapidly grown because of the global warming, the increase of marine structures, pollution, and etc. The increased jellyfish is a threat to the marine ecosystem and induces a huge damage to fishery industries, seaside power plants, and beach industries. To overcome this problem, a manual jellyfish dissecting device and pump system for jellyfish removal have been developed by researchers. However, the systems need too many human operators and their benefit to cost is not so good. Thus, in this paper, the design, implementation, and experiments of autonomous jellyfish removal robot system, named JEROS, have been presented. The JEROS consists of an unmanned surface vehicle (USV), a device for jellyfish removal, an electrical control system, an autonomous navigation system, and a vision-based jellyfish detection system. The USV was designed as a twin hull-type ship, and a jellyfish removal device consists of a net for gathering jellyfish and a blades-equipped propeller for dissecting jellyfish. The autonomous navigation system starts by generating an efficient path for jellyfish removal when the location of jellyfish is received from a remote server or recognized by a vision system. The location of JEROS is estimated by IMU (Inertial Measurement Unit) and GPS, and jellyfish is eliminated while tracking the path. The performance of the vision-based jellyfish recognition, navigation, and jellyfish removal was demonstrated through field tests in the Masan and Jindong harbors in the southern coast of Korea.

Introduction

Jellyfish blooms have become a global menace, fueled by climate change, overfishing of natural predators, and marine pollution. These massive swarms cause significant economic damage by clogging cooling water intakes of seaside power plants and destroying commercial fishing nets. While manual removal systems exist, they are labor-intensive and expensive. The Jellyfish Elimination RObot System (JEROS) provides an autonomous, efficient, and low-cost solution capable of patrolling coastal waters and eliminating jellyfish blooms without constant human intervention.

System Hardware and Removal Mechanism

The JEROS platform utilizes a twin-hull (catamaran) design for superior lateral stability against wind and waves. This stability is essential for maintaining the performance of both the onboard vision system and the mechanical shredding mechanism in choppy coastal waters.

Physical components of the JEROS USV, including the hull, camera, and shredding mechanism.

The removal mechanism features a specialized net assembly that funnels jellyfish toward a propeller equipped with blades designed to "dissect" or shred the jellyfish as the vehicle moves forward. By shredding the jellyfish on-site rather than collecting them, the robot avoids the weight and storage limitations that would otherwise necessitate frequent trips back to shore.

System Architecture and Navigation

The Guidance, Navigation, and Control (GNC) system is managed by a Single Board Computer (SBC) that integrates data from GPS and an Inertial Measurement Unit (IMU) for precise localization.

System architecture of JEROS, illustrating the flow from sensors to the thruster control.

JEROS supports dual-mode operation: it can receive target coordinates from a remote server (e.g., from aerial drones) or autonomously search for jellyfish using its onboard camera. For dense blooms, the system employs "Coverage Path Planning," executing a zigzag pattern to ensure the entire area is cleared. Line-of-Sight (LoS) guidance is used to transition smoothly between waypoints.

Vision-Based Detection

Detecting translucent jellyfish against a reflective, moving water surface is a significant challenge. JEROS employs a multi-stage image processing pipeline to filter noise and identify targets:

  1. Mean-shift filtering for noise reduction.
  2. Morphological gradient operations to find jellyfish boundaries.
  3. Dark area extraction to filter out reflections and wave artifacts.
  4. Blob detection and classification based on shape (circularity) and size to distinguish jellyfish from debris.

Experimental Results

Field tests conducted in Masan and Jindong harbors, as well as controlled tests at KAIST, validated the system's performance:

  • Detection Accuracy: In field-captured video tests (789 frames), the vision system achieved a True Positive Rate (TPR) of 99% with a 0% False Positive Rate (FPR).
  • Removal Efficiency: Operating at a speed of 0.5 m/s, the system is estimated to remove approximately 150kg of jellyfish per hour, assuming an average jellyfish weight of 0.1kg.
  • Navigation: The USV successfully demonstrated autonomous path-following and zigzag coverage patterns in open harbor waters.

Conclusion and Future Work

JEROS demonstrates the feasibility of autonomous maritime pest control. Future iterations will focus on integrating robust obstacle avoidance sensors to navigate around other vessels and debris. Additionally, the authors propose the use of "swarms" of JEROS units working in formation to clear massive blooms more rapidly across larger areas.

Reference: Kim, D., et al. (2013). Design and Implementation of Unmanned Surface Vehicle JEROS for Jellyfish Removal. Journal of Korea Robotics Society.

Summary updated

Abstract

Recently, the number of jellyfish has been rapidly grown because of the global warming, the increase of marine structures, pollution, and etc. The increased jellyfish is a threat to the marine ecosystem and induces a huge damage to fishery industries, seaside power plants, and beach industries. To overcome this problem, a manual jellyfish dissecting device and pump system for jellyfish removal have been developed by researchers. However, the systems need too many human operators and their benefit to cost is not so good. Thus, in this paper, the design, implementation, and experiments of autonomous jellyfish removal robot system, named JEROS, have been presented. The JEROS consists of an unmanned surface vehicle (USV), a device for jellyfish removal, an electrical control system, an autonomous navigation system, and a vision-based jellyfish detection system. The USV was designed as a twin hull-type ship, and a jellyfish removal device consists of a net for gathering jellyfish and a blades-equipped propeller for dissecting jellyfish. The autonomous navigation system starts by generating an efficient path for jellyfish removal when the location of jellyfish is received from a remote server or recognized by a vision system. The location of JEROS is estimated by IMU (Inertial Measurement Unit) and GPS, and jellyfish is eliminated while tracking the path. The performance of the vision-based jellyfish recognition, navigation, and jellyfish removal was demonstrated through field tests in the Masan and Jindong harbors in the southern coast of Korea.
BibTeX
@article{kim2013design,
  author = {Donghoon Kim and Jae-Uk Shin and Hyongjin Kim and Hanguen Kim and Donghwa Lee and Seung‐Mok Lee and Hyun Myung},
  title = {{Design and Implementation of Unmanned Surface Vehicle JEROS for Jellyfish Removal}},
  journal = {The Journal of Korea Robotics Society},
  year = {2013},
  doi = {10.7746/jkros.2013.8.1.051},
}
Figure