SLSeung-Mok Lee

Seung-Mok Lee

*This is an algorithmically generated author record based on publicly available information.

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


Seung-Mok Lee has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Model Predictive Trajectory Optimization and Control for UAV Replacement in Close Formation Flight With Local Minima Avoidance

    by Seung-Mok Lee, Soojung Son

    This paper proposes a model predictive trajectory optimization and control method for unmanned aerial vehicle (UAV) replacement in close formation flight. When a UAV in close formation fails and needs to be replaced, the replacement UAV must compute a collision-free trajectory to reach the specific relative position previously occupied by the failed UAV. In close formation flight, the replacement UAV must navigate in a densely packed environment, which increases the risk of collision. To reduce this risk, trajectory optimization is performed with constraints that enforce a minimum safe distance between UAVs. However, due to the confined space, the replacement UAV may become trapped in a local minimum during optimization, preventing it from converging to the desired relative position. To address this issue, this paper presents a model predictive trajectory optimization and control method that incorporates a potential field to generate 3D collision-free trajectories that are close to the global optimum for UAV replacement. In addition, a simplified collision avoidance constraint and convergence conditions for UAV replacement are derived. Theoretical analysis demonstrates that the proposed method ensures trajectory convergence while maintaining stability throughout the replacement process. To validate the performance of the proposed method, a hardware-in-the-loop (HITL) test environment was developed based on 3D robot simulator Gazebo and multiple single-board computers to closely replicate real-world hardware tests. The results of the HITL tests show that the proposed method effectively enables UAV replacement in close formation flight in various scenarios.


  • Open Access

    Global-Initialization-Based Model Predictive Control for Mobile Robots Navigating Nonconvex Obstacle Environments

    by Seung-Mok Lee

    This paper proposes a nonlinear model predictive control (MPC) framework initialized using an initial-guess particle swarm optimization (IG-PSO) algorithm for mobile robots navigating in environments with nonconvex obstacles. The proposed method is designed to address the local minimum problem inherent in conventional optimization-based MPC by incorporating a PSO-based global search method to generate effective initial guesses. In addition, a grid-based representation of the nonconvex obstacles is implemented to systematically define the collision avoidance constraints within the MPC formulation. The proposed method was validated in real-time simulations using the Robot Operating System (ROS) and the Gazebo physics simulator. The results demonstrate that the proposed MPC initialized by IG-PSO generates collision-free trajectories that avoid local minima and track the desired reference trajectory in environments with nonconvex obstacles. Compared with conventional IPOPT-based MPC, the proposed method exhibited improved performance in the tested scenario. The proposed method also maintains real-time control capabilities by selectively activating the IG-PSO algorithm only as required. The findings of this study demonstrate the potential of the proposed framework for robust and efficient trajectory planning in complex, nonconvex obstacle environments.


  • Open Access

    Multi-Robot Formation Planning in Maze-Like Environments Consisting of Narrow Passages Using Graph Search

    by Seung-Mok Lee, Jeong-Uk Lee

    This paper presents a formation planning method for a group of mobile robots navigating complex maze-like environments with walls and narrow passages. For a group of robots to move in complex maze-like environments, the robots need to move in a formation that maintains a proper relative position to each other. In addition, the robots need to adapt their formation to safely traverse narrow passages. Our proposed formation planning method, based on a 2D grid map, determines an optimal formation sequence along a given global path to traverse narrow passages while avoiding collisions with walls. Through simulations, we demonstrate that the proposed formation planning method effectively plans an optimal formation sequence in complex environments consisting of multiple narrow passages. To verify that the proposed method can be effectively applied in the real-world, we also conduct experiments in a virtual experimental environment built almost identical to the real-world environment.


  • Formation Reconfiguration Control With Collision Avoidance of Nonholonomic Mobile Robots

    by Seongchang Park, Seung-Mok Lee

    This letter proposes a global optimization-based formation reconfiguration control method for multiple nonholonomic mobile robots. To reconfigure their formation, multiple mobile robots need to move from their initial poses to specific relative poses. However, during the formation reconfiguration process, there is a high risk of collision between robots. Moreover, each robot might fall into a local optimum and fail to converge to the desired formation. To address these problems, we propose a global optimization-based model predictive formation control method that can guarantee collision avoidance. The proposed global optimization-based formation control method effectively avoids local optima, and finds solutions close to the global optimal solution in real-time, ensuring that the desired formation is achieved. To verify the performance of the proposed method, we built hardware-in-the-loop (HIL) simulation using physics simulation and multiple embedded computers to establish an experimental environment that is closely similar to that of real physical multiple mobile robots. Furthermore, we conduct experimental verification using actual physical multiple mobile robots. The proposed method demonstrates the effectiveness of formation reconfiguration for nonholonomic mobile robots.


  • Marine Object Segmentation and Tracking by Learning Marine Radar Images for Autonomous Surface Vehicles

    by Hanguen Kim, Donghoon Kim, Seung-Mok Lee

    This paper proposes a radar image segmentation and tracking method by learning radar images for autonomous surface vehicles. To identify marine objects from radar images, we propose a deep neural network named the dual path squeeze and excitation network (DPSE-Net). By learning the radar images, the proposed DPSE-Net is designed to segment every pixel of the radar images into four classes: marine objects, land, noise, and background. The proposed DPSE-Net shows the best performance in radar image segmentation while operating in real-time, compared to state-of-the-art real-time image segmentation network models. In addition, we design a real-time moving object tracking algorithm for estimating the position and velocity of marine objects based on deep simple online real-time tracking with a deep association metric (DeepSORT), a widely used tracking algorithm. The existing DeepSORT algorithm uses the intersection over union (IoU) metric and a deep appearance descriptor for data association, but since they are not suitable for radar images, successive tracking is difficult. To solve this problem, a new data association metric suitable for radar images is proposed. The field tests in ocean environments confirm that the proposed method performs better in marine object segmentation and tracking.


  • Open Access

    Ultrawideband (UWB)-based precise short-range localization for wireless power transfer to electric vehicles in parking environments

    by Seung-Mok Lee

    As the necessity of wireless charging to support the popularization of electric vehicles (EVs) emerges, the development of a wireless power transfer (WPT) system for EV wireless charging is rapidly progressing. The WPT system requires alignment between the transmitter coils installed on the parking lot floor and the receiver coils in the vehicle. To automatically align the two sets of coils, the WPT system needs a localization technology that can precisely estimate the vehicle’s pose in real time. This paper proposes a novel short-range precise localization method based on ultrawideband (UWB) modules for application to WPT systems. The UWB module is widely used as a localization sensor because it has a high accuracy while using low power. In this paper, the minimum number of UWB modules consisting of two UWB anchors and two UWB tags that can determine the vehicle’s pose is derived through mathematical analysis. The proposed localization algorithm determines the vehicle’s initial pose by globally optimizing the collected UWB distance measurements and estimates the vehicle’s pose by fusing the vehicle’s wheel odometry data and the UWB distance measurements. To verify the performance of the proposed UWB-based localization method, we perform various simulations and real vehicle-based experiments.


  • Open Access

    Artificial Intelligence Vision-Based Monitoring System for Ship Berthing

    by Hanguen Kim, Donghoon Kim, Byeolteo Park, Seung-Mok Lee

    This paper proposes a novel artificial intelligence vision-based monitoring system (AVMS) for ship berthing. To dock a ship, it is necessary to accurately estimate the relative distance between the quay wall and the ship. However, maneuvering large ships near a port is a complicated and difficult procedure. Thus, tugboats push the ship and dock it at the berth under the supervision of a pilot, who receives distance information from a berthing aid system (BAS). The conventional BAS based on laser distance sensors, which is the most widely used approach, is high-priced and limited by the size of the ship. Additionally, if there is an obstacle between the ship and the berth, the distance cannot be measured, since it obscures the laser signal. To address this problem, we develop an AVMS sensor module composed of a low-priced camera, a differential global positioning system (DGPS) receiver, and an inertial measurement unit (IMU) with an algorithm to estimate the distance between ship and berth. To evaluate the performance of the proposed AVMS, field tests are performed at Ulsan port in Korea, and the results are compared with a conventional BAS. From the field test results, the AVMS provides highly accurate estimates and shows robust performance in poor weather conditions compared to the conventional BAS. The AVMS can measure the distance between ship and berth regardless of the size of the ship, since it has a wide field of view. In addition, it provides the pilot with real-time image information of the ship approaching the berth to obtain safe ship berthing.