Changsuk Oh

Dr. Changsuk Oh

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 March 2021 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
YJYoungseok Jang
Youngseok Jang
Changsuk OhChangsuk Oh
Changsuk Oh
YLYunwoo Lee
Yunwoo Lee
HKH. Jin Kim
H. Jin Kim
Multirobot simultaneous localization and mapping (SLAM) requires technical ingredients such as systematic construction of multiple SLAM systems and collection of information from each robot. In particular, map fusion is an essential process of multirobot SLAM that combines multiple local maps estimated by team robots into a global map. Fusion of multiple local maps is usually based on interloop detection that recognizes the same scene visited by multiple robots, or robot rendezvous where a member(s) of a robot team is observed in another member's images. This article proposes a collaborative monocular SLAM including a map fusion algorithm that utilizes rendezvous, which can happen when multirobot team members operate in close proximity. Unlike existing rendezvous-based approaches that require additional sensors, the proposed system uses a monocular camera only. Our system can recognize robot rendezvous using nonstatic features (NSFs) without fiducial markers to identify team robots. NSFs, which are abandoned as outliers in typical SLAM systems for not supporting ego-motion, can include relative bearing measurements between robots in a rendezvous situation. The proposed pipeline consists of the following: first, a feature identification module that extracts the relative bearing measurements between robots from NSFs consisting of anonymous bearing vectors with false positives, and second, a map fusion module that integrates the map from the observer robot with the maps from the observed robots using identified relative measurements. The feature identification module can operate quickly using the proposed alternating minimization algorithm formulated by two subproblems with closed-form solutions. The experimental results confirm that our collaborative monocular SLAM system recognizes rendezvous rapidly and robustly, and fuses local maps of team robots into a global map accurately.

19 January 2022 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
HKHyoin Kim
Hyoin Kim
Changsuk OhChangsuk Oh
Changsuk Oh
IJInkyu Jang
Inkyu Jang
SPSungyong Park
Sungyong Park
HSHoseong Seo
Hoseong Seo
HKH. Jin Kim
H. Jin Kim
This paper presents an approach that generates the overall trajectory of mobile manipulators for a complex mission consisting of several sub-tasks. Parametric dynamic movement primitives (PDMPs) can quickly generalize the online motion of robot manipulation by learning multiple demonstrations in offline. However, regarding complex missions consisting of multiple sub-tasks, a large number of demonstrations are required for full generalization, which is impractical. In this paper, we propose a framework that reduces the number of demonstrations for a complex mission. In the proposed method, complex demonstrations are segmented into multiple unit motions representing sub-tasks, and one PDMP is formed per each segment, resulting in multiple PDMPs. The phase decision process determines which sub-task and associated PDMPs to be executed online, allowing multiple PDMPs to be autonomously configured within an integrated framework. In order to generalize the execution time and regional goal in each phase, the Gaussian process regression (GPR) is applied. Simulation results from two different scenarios confirm that the proposed framework not only effectively reduces the number of demonstrations but also improves generalization performance. The actual experiments also demonstrate that the mobile manipulators effectively perform complex missions through the proposed framework. Note to Practitioners—This paper presents an approach of learning from demonstration (LfD) to generalize complex movements of robots. Parametric dynamic movement primitives (PDMPs) compute styles of movements from multiple demonstrations. However, the complexity of the PDMP increases as the mission involves more sub-tasks. In this paper, we resolve this issue by segmenting the complex mission into multiple sub-tasks and configuring multiple PDMPs. This work effectively reduces the number of required demonstrations for PDMPs, moderates the complexity of the algorithm. Also, the proposed approach allows flexible sub-task sequencing. It enables the mission in an unlearned sequence or a new combination of sub-tasks. The proposed approach is validated in both simulation and experimental results. Our approach is applicable for complex missions whose sub-tasks are clearly identified

27 February 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JKJunha Kim
Junha Kim
HKHaram Kim
Haram Kim
Changsuk OhChangsuk Oh
Changsuk Oh
CKChanghyeon Kim
Changhyeon Kim
HKH. Jin Kim
H. Jin Kim
Deep learning methods have been applied to detect moving objects from 3D LiDAR data, but they require extra computing devices (GPUs) and often struggle to operate at real-time LiDAR frame rates. Additionally, retraining is necessary for new environments, which demands significant resources. Non-learning methods that operate online without prior maps and rely solely on a CPU often fail to achieve real-time performance. Furthermore, they are limited in applicability due to their dependence on specific pose estimation algorithms. To address these issues, we propose a novel occlusion accumulation framework in the range image domain for real-time 3D LiDAR moving object detection on a CPU. By incorporating compensation strategies that account for LiDAR artifacts and measurement sparsity, the proposed method reduces false positives and improves detection accuracy. Our approach is also flexible, integrating seamlessly with different pose estimation algorithms without performance degradation. Extensive experiments on KITTI, Apollo, and CARLA datasets demonstrate that the proposed method achieves competitive results compared to state-of-the-art (SOTA) learning-based methods on KITTI and outperforms them in cross-validation on Apollo and CARLA. Moreover, the proposed method operates four times faster than SOTA non-learning-based methods while offering higher detection accuracy, making it highly suitable for real-world applications in autonomous driving and robotic navigation. We provide all the source code and datasets used in this paper to the public at: https://github.com/JunhaAgu/Mapless_Moving.

22 May 2024 in IEEE Sensors Letters
Verified
Journal Article
Closed access
Changsuk OhChangsuk Oh
Changsuk Oh
DSDongseok Shim
Dongseok Shim
TLTaekbeom Lee
Taekbeom Lee
HKH. Jin Kim
H. Jin Kim
Object removal refers to the process of erasing designated objects from an image while preserving the overall appearance. The performance of an object remover is quantitatively evaluated by measuring the quality of object removal results. Current works reporting quantitative performance evaluations utilize original images as references. In this letter, we show that the evaluation methods used in the previous works are not suitable for evaluating object removal results. Additionally, we propose new evaluation methods tailored to gauge the performance of an object remover. The proposed methods evaluate the performance through class- wise object removal results and utilize images without the target class objects as a comparison set. We confirm that the proposed methods can make judgments consistent with human evaluators and those obtained using object removal ground truth on the COCO and self-acquired datasets, respectively.

30 September 2024 in IEEE Robotics & Automation Magazine
Verified
Journal Article
Closed access
IJInkyu Jang
Inkyu Jang
JKJunha Kim
Junha Kim
DLDongjae Lee
Dongjae Lee
CKChanghyeon Kim
Changhyeon Kim
Changsuk OhChangsuk Oh
Changsuk Oh
HKH. Jin Kim
H. Jin Kim
Autonomous excavator systems (AESs) can alleviate the issues caused by the shortage of skilled labor forces and increasing labor costs. For autonomous excavation, real-time landscape estimation, excavation path generation, control, and precise landscape inspection are all essential. In this article, we propose and experimentally validate an integrated AES that incorporates all these elements. Specifically, unlike previous research, we introduce a sensor arrangement capable of sufficiently covering the regions of interest (ROIs) regardless of the inclination of the target landscape, a motion planning method that satisfies geometric and physical constraints, and a precise postexcavation inspection module using onboard sensors only. The proposed methodology was experimentally validated using a real 30-ton hydraulic excavator. It successfully performed a cutting task on an upward slope with 45° inclination and achieved a centimeter-level accuracy through autonomous repetitive excavation; also, the proposed postexcavation inspection method demonstrated subcentimeter precision within seconds using onboard sensors only.

17 January 2024 in IEEE Access
Verified
Journal Article
Open access
Changsuk OhChangsuk Oh
Changsuk Oh
YJYoungseok Jang
Youngseok Jang
DSDongseok Shim
Dongseok Shim
CKChanghyeon Kim
Changhyeon Kim
JKJunha Kim
Junha Kim
HKH. Jin Kim
H. Jin Kim
Object detection in 3D is a key ingredient of various autonomous systems. Many 3D object detection methods rely on LiDAR, as it is robust to illumination conditions and provides accurate distance measurements. To apply LiDAR-based 3D object detection networks for new objects, we need new training datasets. However, because labeling target objects with 3D bounding boxes in LiDAR point clouds requires significant resources and open datasets contain annotations of only car-related classes, it is challenging to deploy LiDAR-based 3D object detectors for detecting objects not related to cars. We propose a system that automatically generates annotated pseudo-LiDAR (APL) data, which requires only stereo images to synthesize 3D bounding box annotations and pseudo-LiDAR points. Using the proposed method, we can dramatically reduce efforts and time for generating a LiDAR-based 3D object detection dataset. By utilizing classes in 2D image datasets, the proposed framework can annotate diverse objects beyond limited classes of existing LiDAR-based 3D object detection datasets. To verify the capability of the synthesized training data, we train 3D object detection networks with the APL data of new classes. The experiments show that the 3D object detection networks trained on the APL data can detect objects of the new classes in LiDAR point clouds, which demonstrates that the proposed method can help LiDAR-based 3D object detectors operate for various objects not covered in existing LiDAR-based 3D object detection datasets.