본문 바로가기 대메뉴 바로가기

KAIST

NEWS

홈페이지 통합검색

-
KOREAN

%4c%69%65%63%68%74%65%6e%73%74%65%69%6e

Professor Hyun Myung's Team Wins First Place in a Challenge at ICRA by IEEE < Photo 1. (From left) Daebeom Kim (Team Leader, Ph.D. student), Seungjae Lee (Ph.D. student), Seoyeon Jang (Ph.D. student), Jei Kong (Master's student), Professor Hyun Myung > A team of the Urban Robotics Lab, led by Professor Hyun Myung from the KAIST School of Electrical Engineering, achieved a remarkable first-place overall victory in the Nothing Stands Still Challenge (NSS Challenge) 2025, held at the 2025 IEEE International Conference on Robotics and Automation (ICRA), the world's most prestigious robotics conference, from May 19 to 23 in Atlanta, USA. The NSS Challenge was co-hosted by HILTI, a global construction company based in Liechtenstein, and Stanford University's Gradient Spaces Group. It is an expanded version of the HILTI SLAM (Simultaneous Localization and Mapping)* Challenge, which has been held since 2021, and is considered one of the most prominent challenges at 2025 IEEE ICRA.*SLAM: Refers to Simultaneous Localization and Mapping, a technology where robots, drones, autonomous vehicles, etc., determine their own position and simultaneously create a map of their surroundings. < Photo 2. A scene from the oral presentation on the winning team's technology (Speakers: Seungjae Lee and Seoyeon Jang, Ph.D. candidates of KAIST School of Electrical Engineering) > This challenge primarily evaluates how accurately and robustly LiDAR scan data, collected at various times, can be registered in situations with frequent structural changes, such as construction and industrial environments. In particular, it is regarded as a highly technical competition because it deals with multi-session localization and mapping (Multi-session SLAM) technology that responds to structural changes occurring over multiple timeframes, rather than just single-point registration accuracy. The Urban Robotics Lab team secured first place overall, surpassing National Taiwan University (3rd place) and Northwestern Polytechnical University of China (2nd place) by a significant margin, with their unique localization and mapping technology that solves the problem of registering LiDAR data collected across multiple times and spaces. The winning team will be awarded a prize of $4,000. < Figure 1. Example of Multiway-Registration for Registering Multiple Scans > The Urban Robotics Lab team independently developed a multiway-registration framework that can robustly register multiple scans even without prior connection information. This framework consists of an algorithm for summarizing feature points within scans and finding correspondences (CubicFeat), an algorithm for performing global registration based on the found correspondences (Quatro), and an algorithm for refining results based on change detection (Chamelion). This combination of technologies ensures stable registration performance based on fixed structures, even in highly dynamic industrial environments. < Figure 2. Example of Change Detection Using the Chamelion Algorithm> LiDAR scan registration technology is a core component of SLAM (Simultaneous Localization And Mapping) in various autonomous systems such as autonomous vehicles, autonomous robots, autonomous walking systems, and autonomous flying vehicles. Professor Hyun Myung of the School of Electrical Engineering stated, "This award-winning technology is evaluated as a case that simultaneously proves both academic value and industrial applicability by maximizing the performance of precisely estimating the relative positions between different scans even in complex environments. I am grateful to the students who challenged themselves and never gave up, even when many teams abandoned due to the high difficulty." < Figure 3. Competition Result Board, Lower RMSE (Root Mean Squared Error) Indicates Higher Score (Unit: meters)> The Urban Robotics Lab team first participated in the SLAM Challenge in 2022, winning second place among academic teams, and in 2023, they secured first place overall in the LiDAR category and first place among academic teams in the vision category.
2025.05.30 View 11337