Duckyu Choi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Duckyu Choi has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Hyun Myung
School of Electrical Engineering, KAIST (Korea Advanced Institute of Science and Technology), Daejeon, Republic of Korea
11 shared publications - Sungwook Jung
Korea Electronics Technology Institute (KETI)
5 shared publications - Eungchang Mason Lee
School of Electrical Engineering, KAIST (Korea Advanced Institute of Science and Technology), Daejeon, Republic of Korea
4 shared publications Hyun Myung
School of Electrical Engineering, KI-R, KAIST,Daejeon,Korea,34141
4 shared publicationsJunho Choi
School of Electrical Engineering and KI-R, Korea Advanced Institute of Science and Technology(KAIST),Urban Robotics Laboratory,Daejeon,South Korea,34141
3 shared publications- Seungwon Song
Robotics Lab, Research and Development Division, Hyundai Motor Company, Uiwang, South Korea
3 shared publications
Latest Publications
- 15 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (9) , 7541-7548
CLOi-Mapper: Consistent, Lightweight, Robust, and Incremental Mapper With Embedded Systems for Commercial Robot Services
In commercial autonomous service robots with several form factors, simultaneous localization and mapping (SLAM) is an essential technology for providing proper services such as cleaning and guidance. Such robots require SLAM algorithms suitable for specific applications and environments. Hence, several SLAM frameworks have been proposed to address various requirements in the past decade. However, we have encountered challenges in implementing recent innovative frameworks when handling service robots with low-end processors and insufficient sensor data, such as low-resolution 2D LiDAR sensors. Specifically, regarding commercial robots, consistent performance in different hardware configurations and environments is more crucial than the performance dedicated to specific sensors or environments. Therefore, we propose a) a multi-stage approach for global pose estimation in embedded systems; b) a graph generation method with zero constraints for synchronized sensors; and c) a robust and memory-efficient method for long-term pose-graph optimization. As verified in in-home and large-scale indoor environments, the proposed method yields consistent global pose estimation for services in commercial fields. Furthermore, the proposed method exhibits potential commercial viability considering the consistent performance verified via mass production and long-term ( $>$ 5 years) operation.
- 15 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (9) , 7541-7548
CLOi-Mapper: Consistent, Lightweight, Robust, and Incremental Mapper With Embedded Systems for Commercial Robot Services
In commercial autonomous service robots with several form factors, simultaneous localization and mapping (SLAM) is an essential technology for providing proper services such as cleaning and guidance. Such robots require SLAM algorithms suitable for specific applications and environments. Hence, several SLAM frameworks have been proposed to address various requirements in the past decade. However, we have encountered challenges in implementing recent innovative frameworks when handling service robots with low-end processors and insufficient sensor data, such as low-resolution 2D LiDAR sensors. Specifically, regarding commercial robots, consistent performance in different hardware configurations and environments is more crucial than the performance dedicated to specific sensors or environments. Therefore, we propose a) a multi-stage approach for global pose estimation in embedded systems; b) a graph generation method with zero constraints for synchronized sensors; and c) a robust and memory-efficient method for long-term pose-graph optimization. As verified in in-home and large-scale indoor environments, the proposed method yields consistent global pose estimation for services in commercial fields. Furthermore, the proposed method exhibits potential commercial viability considering the consistent performance verified via mass production and long-term ( $>$ 5 years) operation.
- 17 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
AWP: Alpha Wrapping-Based Collision-Free Surface-Along Path Planner for UAV
This paper proposes a novel alpha wrapping-based collision-free surface-along path planner (AWP) designed specifically for unmanned aerial vehicles (UAVs) navigating along complex structural surfaces. The major objective is to facilitate collision-free movement of UAVs along such surfaces. The proposed methodology entails three key steps. Firstly, the alpha wrapping algorithm generates a free 3-dimensional curve, which smoothly carves and refines a mesh to approximate the desired structure. This process efficiently creates a free and smooth space for UAV maneuverability. Secondly, the axis-aligned bounding box (AABB) tree is constructed based on the mesh representation of the free space. The AABB tree identifies the points nearest to the UAV's start and target points within the free space. Lastly, a discrete geodesic problem solver determines the shortest path between the identified nearest points. The discrete geodesic problem solver considers the continuous characteristics of the surface represented by the mesh. The proposed AWP takes advantage of mesh-based path planning, thereby providing UAVs with collision-free surface-along paths. The experimental results demonstrate the proposed method's efficiency and robustness in generating collision-free paths for UAVs when traversing complex structures.
- 17 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
AWP: Alpha Wrapping-Based Collision-Free Surface-Along Path Planner for UAV
This paper proposes a novel alpha wrapping-based collision-free surface-along path planner (AWP) designed specifically for unmanned aerial vehicles (UAVs) navigating along complex structural surfaces. The major objective is to facilitate collision-free movement of UAVs along such surfaces. The proposed methodology entails three key steps. Firstly, the alpha wrapping algorithm generates a free 3-dimensional curve, which smoothly carves and refines a mesh to approximate the desired structure. This process efficiently creates a free and smooth space for UAV maneuverability. Secondly, the axis-aligned bounding box (AABB) tree is constructed based on the mesh representation of the free space. The AABB tree identifies the points nearest to the UAV's start and target points within the free space. Lastly, a discrete geodesic problem solver determines the shortest path between the identified nearest points. The discrete geodesic problem solver considers the continuous characteristics of the surface represented by the mesh. The proposed AWP takes advantage of mesh-based path planning, thereby providing UAVs with collision-free surface-along paths. The experimental results demonstrate the proposed method's efficiency and robustness in generating collision-free paths for UAVs when traversing complex structures.
- 25 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 566-570
NLOS-Avoiding and Obstacle-Adaptive Formation Control by Sharing Obstacle Information of a Leader UAV in Multi-UAV System
Formation control is crucial for multi-unmanned aerial vehicle (UAV) system. We presents a novel formation control method for a multi-UAV system. Non-Line-of-Sight (NLOS) situations are predicted and the formation is adjusted accordingly through the sharing of obstacle information obtained from the leader UAV that is equipped with a stereo camera. The minimum snap trajectory for control efficiency to compose the motion primitive is used. In addition, the relative position is estimated using range data between UAVs and the estimated results are used as the position values of the follower UAVs. Three formations are considered; linear formation for passage through a narrow area, pentagonal formation for environmental information acquisition, and rectangular formation for escorting the lead UAV. The proposed method is verified in the simulation environment.
- 25 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 566-570
NLOS-Avoiding and Obstacle-Adaptive Formation Control by Sharing Obstacle Information of a Leader UAV in Multi-UAV System
Formation control is crucial for multi-unmanned aerial vehicle (UAV) system. We presents a novel formation control method for a multi-UAV system. Non-Line-of-Sight (NLOS) situations are predicted and the formation is adjusted accordingly through the sharing of obstacle information obtained from the leader UAV that is equipped with a stereo camera. The minimum snap trajectory for control efficiency to compose the motion primitive is used. In addition, the relative position is estimated using range data between UAVs and the estimated results are used as the position values of the follower UAVs. Three formations are considered; linear formation for passage through a narrow area, pentagonal formation for environmental information acquisition, and rectangular formation for escorting the lead UAV. The proposed method is verified in the simulation environment.
- 1 March 2023
- Published by Springer Nature
- p. 27-36
CEO-MLCPP: Control-Efficient and Obstacle-Aware Multi-Layer Coverage Path Planner for 3D Reconstruction with UAVs
- 1 March 2023
- Published by Springer Nature
- p. 27-36
CEO-MLCPP: Control-Efficient and Obstacle-Aware Multi-Layer Coverage Path Planner for 3D Reconstruction with UAVs
- Open Access
- 23 December 2022
- Published by Elsevier in Journal of Infrastructure Intelligence and Resilience
- Vol. 2 (1)
Survey of robotics technologies for civil infrastructure inspection
- 23 December 2022
- Published by Elsevier in Journal of Infrastructure Intelligence and Resilience
- Vol. 2 (1)
Open AccessSurvey of robotics technologies for civil infrastructure inspection
- 27 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1984-1989
Range-only Relative Position Estimation for Multi-UAV
Although a UAV itself is adaptable to variety of tasks, its low payload and short flight time limit its usage. As a way to overcome the limitations of a UAV, a multi-UAV system is being researched. In order to utilize the Multi-UAV system, it is essential to estimate the relative position of each UAV. In this paper, a relative position estimation method is proposed that requires only range measurements from each pair of UAV combinations. The positions of UAVs are estimated by minimizing the difference between the range measurements and the distance values which are calculated from each pair of estimated positions of UAVs. The performance of the proposed method is verified by five UAVs flight simulation. The range data are generated from the ground-truth positions of five UAVs and Gaussian noise added range data are used for the experiments.
- 27 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1984-1989
Range-only Relative Position Estimation for Multi-UAV
Although a UAV itself is adaptable to variety of tasks, its low payload and short flight time limit its usage. As a way to overcome the limitations of a UAV, a multi-UAV system is being researched. In order to utilize the Multi-UAV system, it is essential to estimate the relative position of each UAV. In this paper, a relative position estimation method is proposed that requires only range measurements from each pair of UAV combinations. The positions of UAVs are estimated by minimizing the difference between the range measurements and the distance values which are calculated from each pair of estimated positions of UAVs. The performance of the proposed method is verified by five UAVs flight simulation. The range data are generated from the ground-truth positions of five UAVs and Gaussian noise added range data are used for the experiments.
- 4 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 103-108
M-BRIC: Design of Mass-driven Bi-Rotor with RL-based Intelligent Controller
Unmanned aerial vehicles (UAVs) have been widely used in complex applications, such as military, exploration, and rescue. Although there are many quadcopter applications, the bi-copter like a coaxial helicopter has apparent energy efficiency and scalability advantages. What makes the bi-copter challenging to use is difficulty in control because additional mechanical structures are essential for stable movement. This paper tackles this problem by proposing a novel bi-rotor design called M-BRIC with rotatable weight rods and reinforcement learning-based controller. Two weight rods that affect the model’s center of mass (CoM) allow higher maneuverability in horizontal directions. The controller of the model is trained to reach the random target point reliably using Proximal Policy Optimization (PPO). To train and test M-BRIC, NVIDIA Isaac Gym is adopted, which is a state-of-the-art physics simulation and supports superfast parallel training. Finally, four reward functions with different characteristics are designed, and the tracking performances of the controller trained with each reward function are compared in the simulation.
- 4 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 103-108
M-BRIC: Design of Mass-driven Bi-Rotor with RL-based Intelligent Controller
Unmanned aerial vehicles (UAVs) have been widely used in complex applications, such as military, exploration, and rescue. Although there are many quadcopter applications, the bi-copter like a coaxial helicopter has apparent energy efficiency and scalability advantages. What makes the bi-copter challenging to use is difficulty in control because additional mechanical structures are essential for stable movement. This paper tackles this problem by proposing a novel bi-rotor design called M-BRIC with rotatable weight rods and reinforcement learning-based controller. Two weight rods that affect the model’s center of mass (CoM) allow higher maneuverability in horizontal directions. The controller of the model is trained to reach the random target point reliably using Proximal Policy Optimization (PPO). To train and test M-BRIC, NVIDIA Isaac Gym is adopted, which is a state-of-the-art physics simulation and supports superfast parallel training. Finally, four reward functions with different characteristics are designed, and the tracking performances of the controller trained with each reward function are compared in the simulation.
- 1 September 2021
- Published by The Korea Robotics Society in Journal of Korea Robotics Society
- Vol. 16 (3) , 216-222
Autonomous Navigation System of an Unmanned Aerial Vehicle for Structural Inspection
- 1 September 2021
- Published by The Korea Robotics Society in Journal of Korea Robotics Society
- Vol. 16 (3) , 216-222
Autonomous Navigation System of an Unmanned Aerial Vehicle for Structural Inspection
- 5 August 2021
- Published by Springer Nature
- p. 136-146
Peacock Exploration: A Lightweight Exploration for UAV Using Control-Efficient Trajectory
- 5 August 2021
- Published by Springer Nature
- p. 136-146
Peacock Exploration: A Lightweight Exploration for UAV Using Control-Efficient Trajectory
- 12 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 392-396
Online 3D Coverage Path Planning Using Surface Vector
This paper presents an online coverage path planner for mapping the surface of three-dimensional structures. Recent works on mapping three-dimensional structural surface rely on random walks, volumetric cellular decomposition, and viewpoint optimization. Unfortunately, the approaches that utilize the volumetric cellular decomposition or the viewpoint optimization cannot perform their work online due to their heavy computational complexity, and online coverage path planners based on random walks show the inefficient spatial visiting, which leads to the failure of the coverage. In this paper, a novel non-randomized real-time coverage path planner that utilizes the newly updated surface is proposed to solve these problems. The proposed coverage planner detects the newly updated surface with an occupancy map and calculates the surface normal vector with k-nearest neighbors (K-NN) and principal component analysis (PCA). The ratio between the exploitation and map gathering can be balanced properly by planning the paths that consider the newly updated surface and surface normal vectors, which guarantees the increased pose estimation performance. By intensively simulating the proposed algorithm in challenging environments, the efficiency and the performance of the algorithm are validated in terms of coverage completeness.
- 12 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 392-396
Online 3D Coverage Path Planning Using Surface Vector
This paper presents an online coverage path planner for mapping the surface of three-dimensional structures. Recent works on mapping three-dimensional structural surface rely on random walks, volumetric cellular decomposition, and viewpoint optimization. Unfortunately, the approaches that utilize the volumetric cellular decomposition or the viewpoint optimization cannot perform their work online due to their heavy computational complexity, and online coverage path planners based on random walks show the inefficient spatial visiting, which leads to the failure of the coverage. In this paper, a novel non-randomized real-time coverage path planner that utilizes the newly updated surface is proposed to solve these problems. The proposed coverage planner detects the newly updated surface with an occupancy map and calculates the surface normal vector with k-nearest neighbors (K-NN) and principal component analysis (PCA). The ratio between the exploitation and map gathering can be balanced properly by planning the paths that consider the newly updated surface and surface normal vectors, which guarantees the increased pose estimation performance. By intensively simulating the proposed algorithm in challenging environments, the efficiency and the performance of the algorithm are validated in terms of coverage completeness.