|
Radar-lidar sensor fusion for seamless target tracking with an unmanned surface vehicle |
|
Jungwook Han, Jinwhan Kim(KAIST, Korea) |
| This paper addresses the problem of automatic target tracking of multiple surface vessels for unmanned surface vehicles (USVs). For safe USV operation, the detection of vessels in the surrounding environment is an important capability, and marine radars have been used to detect and estimate their motion. However, vessel detection at short-range using radars is challenging due to their inherent blind zone. Therefore, we proposes a vessel tracking approach fusing a pulse radar and a 3D lidar, which enables persistent tracking of multiple surface vessels. |
|
|
Efficient Quantification of Terrain Information for Terrain-Referenced Underwater Navigation |
|
Taeyun Kim, Jinwhan Kim(KAIST, Korea) |
| The performance of terrain-referenced navigation varies significantly depending on how informative a given terrain is, however it is not straightforward to quantify the amount of information that can be provided by the terrain and predict the navigation performance. This study proposes a new terrain information measure by analyzing and quantifying the amount of information in terms of terrain roughness and uniqueness. The expected information is evaluated in the spatial frequency domain via Fourier transforms to maximize the computational efficiency of the quantification. |
|
|
Development of Simulator for Autonomous Underwater Vehicles utilizing Underwater Acoustic and Optical Sensing Emulators |
|
Jason Kim, Minsung Sung, Son-Cheol Yu(Pohang University of Science and Technology, Korea) |
| This paper addresses an autonomous underwater vehicle (AUV) simulator with underwater image sonar and optical vision emulation. Development of the simulator that emulates underwater image sonar and optical vision can support intelligent underwater missions by visualizing and simulating virtual scenarios and reproducing real missions. When an underwater virtual scenario of terrain, target objects, and AUVs with sensors is plotted using standard 3-D modeling programs, the simulator configures the scenario and displays sonar and optical images. |
|
|
A Sea Creatures Classification Method using Convolutional Neural Networks |
|
Jonghyun Ahn, Yuya Nishida, Kazuo Ishii, Tamaki Ura(Kyushu Institute of Technology, Japan) |
| In this research, we propose an automatic classification method for the sea creatures using convolutional neural networks to provide the requested information, such as crab images, to researcher. The proposed method is comprised image enhancement process, segmentation process and classification process. The total candidate detection rate was 64%, and the total recognition accuracy was 67% by the evaluation. |
|
|
Underwater Agent Vehicle for Manipulation and Object Recovery Using Winch System |
|
Juhwan Kim, Meungsuk Lee, Hyeonwoo Cho, Son-Cheol Yu(Pohang University of Science and Technology (POSTECH), Korea) |
| We developed a new concept of underwater agent vehicle and conducted a preliminary test of recovering a heavy object. We fabricated the small agent vehicle that was designed for manipulation. The vehicle includes a gripper, sensors, and a winch system that increases the lift force of the agent low thrust. The agent can autonomously navigate specific areas, has object detection abilities and is intended for deployment to areas where large underwater vehicles cannot access. In fact, we successfully conducted manipulation within a water tank. The agent vehicle was deployed on the water surface an |
|
|
Design and Implementation of Backstepping Controller for Tilting Thruster Underwater Robot |
|
Santhakumar Mohan(Indian Institute of Technology, India), Jagadeesh Kadiyam(IIT Indore, India), Devendra Deshmukh(Indian Institute of Technology, India), TaeWon Seo(Hanyang University, Korea) |
| A new motion control approach for an underwater robot with four tilting thrusters is proposed and investigated in
this paper. The tilting thruster arrangement results in overactuated system which carries out six degree of freedom (DOF) motion with four rotatable thrusters. |
|