Hyun-Jae Jo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hyun-Jae Jo has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Jung-Hyeon Kim
Department of Marine Design Convergence Engineering, Pukyong National University, Busan 48513, Republic of Korea
5 shared publications - Su-Rim Kim
Maneuvering Control Research Team, Avikus, Seoul 06236, Republic of Korea
4 shared publications - Jong-Yong Park
Department of Marine Design Convergence Engineering, Pukyong National University, Busan 48513, Republic of Korea
3 shared publications Jong-Yong Park
2 shared publications- Jong-Yong Park
Department of Naval Architecture and Marine System Engineering Pukyong National University Busan Korea
2 shared publications Jung-Hyeon Kim
2 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Elsevier in International Journal of Naval Architecture and Ocean Engineering
- Vol. 18
3D LiDAR-based berthing state estimation: Quay wall detection considering fenders and field-of-view constraints
- 8 August 2026
- Published by Elsevier in International Journal of Naval Architecture and Ocean Engineering
- Vol. 18
Open Access3D LiDAR-based berthing state estimation: Quay wall detection considering fenders and field-of-view constraints
- Open Access
- 11 April 2026
- Published by Elsevier in SSRN Electronic Journal
Dynamic Berth Replanning from Unstructured VTS Communications via an LLM-Orchestrated BERT-MILP Architecture
Massive container vessels have intensified berth congestion, making dynamic berth replanning a tightly constrained problem. Urgent exceptions, like onshore power supply requests and mechanical degradations, are often conveyed through unstructured Vessel Traffic Services (VTS) dialogues rather than inputs ready for optimization. Conventional algorithms cannot process this unstructured text, leading to suboptimal plans. Directly relying on generative AI is also unsafe, as probabilistic outputs may violate physical constraints.To address this, we propose a safe architecture combining a Large Language Model, BERT, and Mixed Integer Linear Programming for communication aware berth replanning. The LLM interprets raw VTS dialogues to generate bounded coordination cues. A BERT layer structures and validates these cues into operational signals. Finally, the MILP solver computes the executable berth plan, ensuring compliance with hard constraints like changing tides, under keel clearance, weather limits, and spatial separation.Simulations using real operational and tidal data from Busan New Port demonstrate significant improvements. Integrating the BERT perception layer with the MILP model increased compliance from 74.7% to 89.5%. Adding LLM coordination improved compliance to 95.0% by safely resolving complex exceptions. This confirms unstructured VTS communications can be integrated into berth replanning while strictly preserving operational feasibility.
- 11 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessDynamic Berth Replanning from Unstructured VTS Communications via an LLM-Orchestrated BERT-MILP Architecture
Massive container vessels have intensified berth congestion, making dynamic berth replanning a tightly constrained problem. Urgent exceptions, like onshore power supply requests and mechanical degradations, are often conveyed through unstructured Vessel Traffic Services (VTS) dialogues rather than inputs ready for optimization. Conventional algorithms cannot process this unstructured text, leading to suboptimal plans. Directly relying on generative AI is also unsafe, as probabilistic outputs may violate physical constraints.To address this, we propose a safe architecture combining a Large Language Model, BERT, and Mixed Integer Linear Programming for communication aware berth replanning. The LLM interprets raw VTS dialogues to generate bounded coordination cues. A BERT layer structures and validates these cues into operational signals. Finally, the MILP solver computes the executable berth plan, ensuring compliance with hard constraints like changing tides, under keel clearance, weather limits, and spatial separation.Simulations using real operational and tidal data from Busan New Port demonstrate significant improvements. Integrating the BERT perception layer with the MILP model increased compliance from 74.7% to 89.5%. Adding LLM coordination improved compliance to 95.0% by safely resolving complex exceptions. This confirms unstructured VTS communications can be integrated into berth replanning while strictly preserving operational feasibility.
- Open Access
- 9 December 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (12) , 2255
Comparison of Collision Avoidance Algorithms for Unmanned Surface Vehicle Through Free-Running Test: Collision Risk Index, Artificial Potential Field, and Safety Zone
This paper details the development of a collision avoidance algorithm for unmanned surface vehicles (USVs) and its validation using free-running tests. The USV, designed as a catamaran, incorporates a variety of sensors for its guidance, navigation, and control system. It performs turning maneuvers using thrusters positioned on the port and starboard sides. The robot operating system is used to streamline communication, transmitting data such as position, orientation, and situational information from diverse sensors. Using the collision risk index (CRI) method, the algorithm calculates risk based on the distance to obstacles and the angle to the desired waypoint, directing the USV on a path with minimized risk. Noise within the data captured by the two-dimensional light detection and ranging system is filtered out using the k-dimensional tree and Euclidean distance methods, ensuring single obstacles are distinctly identified. To assess the efficacy of the CRI-based collision avoidance algorithm, it was benchmarked against other algorithms rooted in the artificial potential field and safety zone methods within an artificial tank setting. The results highlight the CRI method’s superior time efficiency and optimality in comparison to its counterparts.
- 9 December 2024
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 12 (12) , 2255
Open AccessComparison of Collision Avoidance Algorithms for Unmanned Surface Vehicle Through Free-Running Test: Collision Risk Index, Artificial Potential Field, and Safety Zone
This paper details the development of a collision avoidance algorithm for unmanned surface vehicles (USVs) and its validation using free-running tests. The USV, designed as a catamaran, incorporates a variety of sensors for its guidance, navigation, and control system. It performs turning maneuvers using thrusters positioned on the port and starboard sides. The robot operating system is used to streamline communication, transmitting data such as position, orientation, and situational information from diverse sensors. Using the collision risk index (CRI) method, the algorithm calculates risk based on the distance to obstacles and the angle to the desired waypoint, directing the USV on a path with minimized risk. Noise within the data captured by the two-dimensional light detection and ranging system is filtered out using the k-dimensional tree and Euclidean distance methods, ensuring single obstacles are distinctly identified. To assess the efficacy of the CRI-based collision avoidance algorithm, it was benchmarked against other algorithms rooted in the artificial potential field and safety zone methods within an artificial tank setting. The results highlight the CRI method’s superior time efficiency and optimality in comparison to its counterparts.
- Open Access
- 19 December 2022
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 10 (12) , 2036
Comparison of Velocity Obstacle and Artificial Potential Field Methods for Collision Avoidance in Swarm Operation of Unmanned Surface Vehicles
As the research concerning unmanned surface vehicles (USVs) intensifies, research on swarm operations is also being actively conducted. A swarm operation imitates the appearance of nature, such as ants, bees, and birds, in forming swarms, moving, and attacking in the search for food. However, several problems are encountered in the USV swarm operation. One of these is the problem of collisions between USVs. A conflict between agents in a swarm can lead to operational failure and property loss. This study attempted to solve this problem. In this study, a virtual matrix approach was applied as a swarm operation. Velocity obstacle (VO) and artificial potential field (APF) methods were used and compared as algorithms for collision avoidance for USVs in a swarm when the formation is changed. For effective collision avoidance, evasive maneuvers should be performed at an appropriate time and location. Therefore, a closest point of approach (CPA)-based method, which considers both temporal and spatial factors, was used. The swarm operation was verified through a large-scale simulation in which 30 USVs changed their formation seven times in 3400 s. When comparing the averages of the distance, error to waypoint, and battery usage, no significant differences were noticed between the VO and APF methods. However, when comparing the cumulative time using the minimum distance, VO was demonstrably safer than APF, and VO completed the formation faster. In conclusion, both the APF and VO methods can evidently perform swarm operations without collisions.
- 19 December 2022
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 10 (12) , 2036
Open AccessComparison of Velocity Obstacle and Artificial Potential Field Methods for Collision Avoidance in Swarm Operation of Unmanned Surface Vehicles
As the research concerning unmanned surface vehicles (USVs) intensifies, research on swarm operations is also being actively conducted. A swarm operation imitates the appearance of nature, such as ants, bees, and birds, in forming swarms, moving, and attacking in the search for food. However, several problems are encountered in the USV swarm operation. One of these is the problem of collisions between USVs. A conflict between agents in a swarm can lead to operational failure and property loss. This study attempted to solve this problem. In this study, a virtual matrix approach was applied as a swarm operation. Velocity obstacle (VO) and artificial potential field (APF) methods were used and compared as algorithms for collision avoidance for USVs in a swarm when the formation is changed. For effective collision avoidance, evasive maneuvers should be performed at an appropriate time and location. Therefore, a closest point of approach (CPA)-based method, which considers both temporal and spatial factors, was used. The swarm operation was verified through a large-scale simulation in which 30 USVs changed their formation seven times in 3400 s. When comparing the averages of the distance, error to waypoint, and battery usage, no significant differences were noticed between the VO and APF methods. However, when comparing the cumulative time using the minimum distance, VO was demonstrably safer than APF, and VO completed the formation faster. In conclusion, both the APF and VO methods can evidently perform swarm operations without collisions.
- 20 December 2021
- Published by The Society of Naval Architects of Korea in Journal of the Society of Naval Architects of Korea
- Vol. 58 (6) , 358-365
A Study on Development of Sway Velocity Reference Model During Auto-berthing/Unberthing Through Analysis of Ship’s Berthing/Unberthing Data
Crabbing motion is a pure sway motion with only sway velocity. The ship’s crabbing motion is essential for an ideal berthing/unberthing process. The unberthing situation proceeds in sequential order such as crabbing motion section, pivoting section, and outer port section. For the berthing situation, the sequence has a reverse order: the inner port section, pivoting section, and crabbing motion section. In this paper, the berthing/unberthing data of the reference ship, Pukyong National University research ship“NARA”, was analyzed to develop a sway velocity reference model. Several constraints were defined to derive the crabbing motion section during berthing/unberthing. The sway velocity reference model for the auto-berthing/unberthing was developed using the estimated sway velocity. A reproduction simulation of the ship was performed to compare the designed reference model and the reference ship data.
- 20 December 2021
- Published by The Society of Naval Architects of Korea in Journal of the Society of Naval Architects of Korea
- Vol. 58 (6) , 358-365
A Study on Development of Sway Velocity Reference Model During Auto-berthing/Unberthing Through Analysis of Ship’s Berthing/Unberthing Data
Crabbing motion is a pure sway motion with only sway velocity. The ship’s crabbing motion is essential for an ideal berthing/unberthing process. The unberthing situation proceeds in sequential order such as crabbing motion section, pivoting section, and outer port section. For the berthing situation, the sequence has a reverse order: the inner port section, pivoting section, and crabbing motion section. In this paper, the berthing/unberthing data of the reference ship, Pukyong National University research ship“NARA”, was analyzed to develop a sway velocity reference model. Several constraints were defined to derive the crabbing motion section during berthing/unberthing. The sway velocity reference model for the auto-berthing/unberthing was developed using the estimated sway velocity. A reproduction simulation of the ship was performed to compare the designed reference model and the reference ship data.
- Open Access
Formation Control of Swarming Vessels Using a Virtual Matrix Approach and ISOT Guidance Algorithm
The formation control for the effective operation of multiple vessels is discussed. First, a virtual matrix approach is proposed to improve the formation robustness and transform performance during swarm operations, which is created based on the virtual leader vessel location, and agents composing the formation follow cells in the matrix to maintain formation. This approach is affected by the virtual leader vessel location. The virtual leader vessel location is defined by two cases: matrix center and geometric center; furthermore, robustness and efficiency comparison simulations are performed. The simulation results show that in most formations, the geometric center is better in terms of efficiency and robustness. Second, the isosceles triangle guidance algorithm is proposed to improve the “go-back behavior” of certain agents during excessive maneuvering. Through a waypoint-following simulation, the algorithm is confirmed to be superior to the line-of-sight guidance algorithm. The swarm simulation on the virtual map verifies the performance of the proposed formation control and guidance algorithm.
Open AccessFormation Control of Swarming Vessels Using a Virtual Matrix Approach and ISOT Guidance Algorithm
The formation control for the effective operation of multiple vessels is discussed. First, a virtual matrix approach is proposed to improve the formation robustness and transform performance during swarm operations, which is created based on the virtual leader vessel location, and agents composing the formation follow cells in the matrix to maintain formation. This approach is affected by the virtual leader vessel location. The virtual leader vessel location is defined by two cases: matrix center and geometric center; furthermore, robustness and efficiency comparison simulations are performed. The simulation results show that in most formations, the geometric center is better in terms of efficiency and robustness. Second, the isosceles triangle guidance algorithm is proposed to improve the “go-back behavior” of certain agents during excessive maneuvering. Through a waypoint-following simulation, the algorithm is confirmed to be superior to the line-of-sight guidance algorithm. The swarm simulation on the virtual map verifies the performance of the proposed formation control and guidance algorithm.
- 20 April 2021
- Published by The Society of Naval Architects of Korea in Journal of the Society of Naval Architects of Korea
- Vol. 58 (2) , 121-128
Development of Autonomous Algorithm for Boat Using Robot Operating System
According to the increasing interest and demand for the Autonomous Surface Vessels (ASV), the autonomous navigation system is being developed such as obstacle detection, avoidance, and path planning. In general, autonomous navigation algorithm controls the ship by detecting the obstacles with various sensors and planning path for collision avoidance. This study aims to construct and prove autonomous algorithm with integrated various sensor using the Robot Operating System (ROS). In this study, the safety zone technique was used to avoid obstacles. The safety zone was selected by an algorithm to determine an obstacle-free area using 2D LiDAR. Then, drift angle of the ship was controlled by the propulsion difference of the port and starboard side that based on PID control. The algorithm performance was verified by participating in the 2020 Korea Autonomous BOAT (KABOAT).
- 20 April 2021
- Published by The Society of Naval Architects of Korea in Journal of the Society of Naval Architects of Korea
- Vol. 58 (2) , 121-128
Development of Autonomous Algorithm for Boat Using Robot Operating System
According to the increasing interest and demand for the Autonomous Surface Vessels (ASV), the autonomous navigation system is being developed such as obstacle detection, avoidance, and path planning. In general, autonomous navigation algorithm controls the ship by detecting the obstacles with various sensors and planning path for collision avoidance. This study aims to construct and prove autonomous algorithm with integrated various sensor using the Robot Operating System (ROS). In this study, the safety zone technique was used to avoid obstacles. The safety zone was selected by an algorithm to determine an obstacle-free area using 2D LiDAR. Then, drift angle of the ship was controlled by the propulsion difference of the port and starboard side that based on PID control. The algorithm performance was verified by participating in the 2020 Korea Autonomous BOAT (KABOAT).