Jinwhan Kim
Korea Advanced Institute of Science and Technology · 工学
研究室紹介
Professor Jinwhan Kim's research lab specializes in autonomous maritime systems, focusing on sensor fusion, multi-target tracking, and real-time perception for unmanned surface vehicles (USVs) and underwater inspection platforms. The lab develops advanced estimation algorithms—such as Kalman filters, particle filters, and hybrid filtering techniques—for robust navigation and collision avoidance in complex maritime environments, particularly under non-Gaussian noise and nonlinear dynamics. Their work spans autonomous navigation, underwater visual inspection, and multimodal sensor data integration for safe and efficient operation in restricted and dynamic waterways.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15Abstract This study addresses the development of algorithms for multiple target detection and tracking in the framework of sensor fusion and its application to autonomous navigation and collision avoidance systems for the unmanned surface vehicle (USV) Aragon. To provide autonomous navigation capabilities, various perception sensors such as radar, lidar, and cameras have been mounted on the USV platform and automatic ship detection algorithms are applied to the sensor measurements. The relative
During the reentry to the atmosphere, certain ballistic missiles are known to undergo violent spiraling motions induced by aerodynamic resonance between roll and yaw/pitch modes. Successful interception of such spiraling targets is critically dependent on the performance of the target state estimator. Strong nonlinearities involved in the system dynamics and measurement equations together with sensor noise make this a challenging estimation task. The performance of an extended Kalman filter (EKF
Abstract Underwater visual inspection is an important task for checking the structural integrity and biofouling of the ship hull surface to improve the operational safety and efficiency of ships and floating vessels. This paper describes the development of an autonomous in‐water visual inspection system and its application to visual hull inspection of a full‐scale ship. The developed system includes a hardware vehicle platform and software algorithms for autonomous operation of the vehicle. The
This paper presents a multimodal maritime dataset and the data collection procedure used to gather it, which aims to facilitate autonomous navigation in restricted water environments. The dataset comprises measurements obtained using various perception and navigation sensors, including a stereo camera, an infrared camera, an omnidirectional camera, three LiDARs, a marine radar, a global positioning system, and an attitude heading reference system. The data were collected along a 7.5-km-long rout
The performance of ballistic target interception is critically dependent on the performance of the target state estimation. The estimation performance then strongly depends on the accuracy of the measurement model. The Gaussian uncertainty distribution has commonly been used for representing the statistical properties of sensor noise, due to its mathematical simplicity and effectiveness. However, seeker sensor measurements are often corrupted by glint noise which is highly non-Gaussian, and conv
This paper presents experimental validation results of autonomous collision avoidance algorithms using an unmanned surface vehicle (USV). For autonomous collision avoidance while following given waypoints, the existing line-of-sight (LOS) guidance and velocity obstacle (VO) algorithms are modifed and applied to this USV. The proposed collision avoidance algorithm considers the rule 13 to 17 in the international collision regulations (COLREGs) and provides a rule-compliant evasive path. The perfo