Obin Kwon
I'm a postdoc in KIMLAB (Kinetic Intelligent Machine LAB), University of Illinois Urbana-Champaign. I recently got Ph.D. in ECE, Seoul National University, Korea. I was in Robot Learning Labatory (RLLAB) and was supervised by Songhwai Oh . Before the PhD course, I received a B.S. degree in Electrical and Computer Engineering from SNU in 2018.
Previously I was in internship at Naver LABS in Jan.-June 2023. I also worked as a robotics researcher in Sequor Robotics, Inc. from Oct 2023 to Jun 2024.
Research Keywords : Embodied AI, Robot Learning 🤖 with Computer Vision 👀, Machine Learning🧠
My research interests are lie in translating sensory information into effective robot action policies . Previously, I focused on developing novel scene representations from vision signals and creating robot policies that effectively use these representations to perform high-level tasks. Looking forward, I am enthusiastic about exploring a wide spectrum of new frontiers in robotics, encompassing multi-modal perception, human-robot interaction, and advanced decision-making processes.
News
Aug 01, 2024 | 🎓 I received the Distinguished Ph.D. Dissertation Award from ECE, Seoul National University! 🎓 |
---|---|
Jul 08, 2024 | I started my role as a postdoctoral research associate in KIMLAB@UIUC, working with Joohyung Kim. |
Jun 30, 2024 | Our paper “RNR-Nav: A Real-World Visual Navigation System Using Renderable Neural Radiance Maps” is accepted to IROS 2024, as oral presentation. |
Jun 26, 2024 | I successfully defended my Ph.D Thesis! |
May 13, 2024 | I attended ICRA 2024, presenting my paper “WayIL:Image-based Indoor Localization with Wayfinding Maps” |
Publications
- Spatially-Conditional 3D Furniture Generation Model for Indoor Scene GenerationIn 2024 24th International Conference on Control, Automation and Systems (ICCAS), Oct 2024Scene RepresentationScene Generation
-
- WayIL:Image-based Indoor Localization with Wayfinding MapsIn 2024 International Conference on Robotics and Automation (ICRA), May 2024Scene RepresentationVisual Localization
- Renderable Neural Radiance Map for Visual NavigationIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2023 (Highlight)Scene RepresentationVisual NavigationNeRF
- Attention-Based Randomized Ensemble Multi-Agent Q-LearningIn 2023 23rd International Conference on Control, Automation and Systems (ICCAS), Jun 2023Multi-AgentReinforcement Learning
- Topological Semantic Graph Memory for Image-Goal NavigationIn Proceedings of The 6th Conference on Robot Learning, 14–18 dec 2022 (Oral Presentation)Scene RepresentationVisual NavigationMemory BuildingImitation LearningReinforcement Learning
- Visually Grounding Language Instruction for History-Dependent ManipulationIn 2022 International Conference on Robotics and Automation (ICRA), 14–18 dec 2022ManipulationMemory BuildingLanguage Instruction
- Image-goal navigation algorithm using viewpoint estimationIn International Conference on Control, Automation and Systems (ICCAS), 14–18 dec 2021Visual NavigationReinforcement Learning
- Geometric Understanding of Reward Function in Multi-Agent Visual ExplorationOct 2021Multi-AgentReinforcement LearningVisual Navigation
- Visual Graph Memory With Unsupervised Representation for Visual NavigationIn Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2021Visual NavigationScene RepresentationMemory BuildingImitation LearningReinforcement Learning
- Image-Goal Navigation Algorithm using Viewpoint EstimationIn 2021 21st International Conference on Control, Automation and Systems (ICCAS), Oct 2021Visual NavigationMemory BuildingReinforcement Learning