우리 연구실 졸업생 안인규 박사가 2025년 2월 국민대학교 소프트웨어융합학과에 조교수로 임용되었습니다.
안인규 박사는 3차원 공간에서 음원의 위치를 정밀하게 추적하는 기술 개발의 연구를 진행하였으며, 특히 음파의 회절과 반사 특성을 고려한 음원 위치 추적 기술 등을 개발하고, 이를 인정받아 권위 있는 학술지에 논문을 발표하였습니다.
윤성의 교수님께서는 “안 박사는 로봇 청각 분야에서 탁월한 연구 역량을 보여왔다”며 “국민대에서 그의 연구가 더욱 발전해 로봇 기술의 새로운 전기를 마련할 것으로 기대한다”고 밝혔으며, 안 박사님께서는 안 박사는 “로봇의 청각 및 인식 능력을 강화해 인간과 자연스럽게 상호작용하도록 하겠다”고 포부를 밝혔습니다.
https://cs.kaist.ac.kr/board/view?bbs_id=news&bbs_sn=11394&menu=8
윤성의 교수님께서 DGIST 로봇학과에 방문하여 연구 소개 세미나를 진행하였습니다.
DGIST 캠퍼스 벚꽃이 대전 보다 좀 더 빨리 피는 것 같네요
Our lab members Woobin, Heechan, Guoyuan, Mincheul, Xu, graduated for phd degree, Yaxin, Juhyung, Woojung, Taegeun, Youngju, Jeil graduated for master degree. Congratuations!
Professor Yoon and his Ph.D. students, Sebin Lee, Minsung Yoon, and Taegeun Yang, conducted a tutorial session at the KRoC 2024 conference. The topic of this tutorial was “Advancements in Robot Motion Generation Techniques: From Sampling-Based to Reinforcement Learning and Applications (로봇 모션 생성 기법의 발전: 샘플링 기반에서 강화 학습 및 응용까지).”
Sebin introduced sensor technologies for enhancing robotic environmental perception. Minsung discussed reinforcement learning methods and their applications to robotic arms and quadruped robots. Taegeun explained hierarchical reinforcement learning and its applications in robotic motion planning.
The session provided a valuable opportunity to share knowledge on robot motion generation techniques, fostering meaningful discussions and idea exchange among participants.
Jiwoo Hwang presented a paper at the KRoC 2025 Conference, held from February 12 to 15, 2025. His presentation focused on the research topic, “Whole Body Controller for Mobile Manipulator via Reinforcement Learning and Differentiable Inverse Kinematics.” This study proposes a method for controlling a robotic arm by determining the movements of the mobile base and end effector using reinforcement learning and utilizing differentiable inverse kinematics for precise manipulation.
Professor Yoon, along with some of his Ph.D. and M.S. students, attended the KRoC 2025 conference in Pyeongchang from February 12th to 13th, 2025. They participated in paper presentations and tutorials at the conference. Additionally, they enjoyed shared meals and spent time together engaging in activities like skiing and snowboarding.
Our lab members, Heechan, Xu Yin, Guoyuan and Mincheul, successfully defended their theses in December 2024.
Heechan presented his research, “Adaptive Locomotion and Manipulation through Gravitational Moment Minimization based on Centroid of Locomotion Feet for Quadruped Robot“
Xu Yin introduced his work, “Data-efficient Scene Understanding and Adaptive Decision-making toward Open-World Scenarios”
Guoyuan explained his study, “Developing a Self-Adaptive Visual Search and QA System with Spatial, Topology, and Semantic Consistency”
Mincheul shared his research, “Social Robot Navigation Integrating Human Behavior in Crowded Environments“
Congratulations to all on this achievement! Their hard work and dedication paid of, well done!
Our lab members, Youngju, Taegeun, and Jeil, successfully defended their theses in December 2024.
Youngju presented his research, “Generalizable 3D Surface Reconstruction from Arbitrary and Unfavorable Data Sets.”
Taegeun introduced his work, “Hierarchical Reinforcement Learning for Efficient Navigation Among Movable Obstacles Using a Mobile Manipulator.”
Jeil explained his study, “Depth Image-Based Navigation for Quadrupedal Robots in Unstructured Environments Using Hierarchical Reinforcement Learning.”
Congratulations to all on their achievements! Everyone worked incredibly hard, well done!
Professor Yoon and some of his students participated in the Hanwha Aerospace presentation on December 20th and completed it smoothly. Great job, everyone!
Our Ph.D. student Yoonki Cho presented his work titled “Generalizable Person Re-identification via Balancing Alignment and Uniformity” at NeurIPS 2024 held from December 10th to December 15th, 2024. This study introduces the Balancing Alignment and Uniformity (BAU) framework to enhance domain generalization in person re-identification by maintaining a balance between alignment and uniformity, thereby improving robustness against distributional shifts. The proposed approach effectively leverages data augmentation to achieve state-of-the-art performance without requiring complex training procedures.
Professor Yoon, his Ph.D. student Yoonki Cho, and MS student Youngju Na attended the NeurIPS2024 conference held at the Vancouver Convention Center in Canada from December 10th to December 15th, 2024. There, we had the valuable opportunity to meet our doctoral student Chungsu Jang and alumnus Inyoung Cho, allowing us to engage in meaningful exchanges. Additionally, by participating in the conference, we were able to understand recent research topics and gain a broader research perspective, making it a precious opportunity.
Professor Yoon and his Ph.D. students, Jaeyoon Kim and Kyubeom Han, attended the SIGGRAPH ASIA 2024 conference held at the Tokyo International Forum in Japan from December 3rd to December 6th, 2024. The conference provided a great opportunity for the team to connect, participate in various programs, exchange ideas, and stay updated on the latest trends. Additionally, we were able to meet our alumnus, YuChi, and have catch-up conversations, offering mutual support.
On November 4th, our lab visited the Chrysanthemum Festival at Yurim Park. We strolled among the fully bloomed chrysanthemums, enjoying relaxed conversations and a refreshing break. Afterward, we shared lunch together, strengthening our team bonds. It was a meaningful outing, made even more special by the chance to connect and enjoy time with everyone in the lab.
Our PhD student SeongJoo Moon presented his work titled “LiDAR-camera Online Calibration by Representing Local Feature and Global Spatial Context” at IROS2024. This research proposes a Transformer-based framework for LiDAR-camera online calibration, addressing degradation in calibration accuracy caused by physical vibrations and environmental changes. By learning feature correspondences and integrating global spatial context, the method achieves superior calibration performance compared to existing benchmarks, enhancing perception systems for autonomous driving applications.
Our PhD student Mincheul Kim presented his work titled “CCTV-Informed Human-Aware Robot Navigation in Crowded Indoor Environments” at IROS 2024. This study, which has also been accepted for publication in RAL 2024, proposes a novel navigation framework that integrates CCTV data with deep reinforcement learning to overcome the limitations of onboard sensors, enabling robots to navigate crowded indoor spaces safely and efficiently. By leveraging external CCTV insights on human movements, the framework anticipates interactions, minimizes collisions, and generates socially acceptable paths, significantly improving navigation compared to methods reliant solely on local sensing.
Our PhD student Minsung Yoon presented his work titled “Learning-based Adaptive Control of Quadruped Robots for Active Stabilization on Moving Platforms” at IROS2024. This research introduces Learning-based Active Stabilization on Moving Platforms (LAS-MP), a novel system that enables quadruped robots to balance effectively on six-DOF moving platforms by leveraging adaptive posture adjustment policies and state estimators trained on proprioceptive sensor data. The framework systematically addresses challenges caused by platform-induced inertia forces and showcases superior performance over baselines through trajectory generation, ablation studies, and detailed evaluations of its components.
