Obin Kwon

I am a PhD student at Robot Learning Labatory (RLLAB) , Seoul National University, Korea. I am 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 work as a researcher in Sequor Robotics, Inc. from Oct 2023.

Research Keywords : Embodied AI, Robot Learning 🤖 with Computer Vision 👀, Machine Learning🧠

Email / CV / Google Scholar / Twitter / Github / Linkedin

Research

My research interests are lie in translating visual information into effective robot action policies . Previously, I expanded my expertise by investigating building advanced scene representations and devising novel training strategies to enhance robotic perception and decision-making. Looking forward, I am enthusiastic about exploring a wide spectrum of new frontiers in robotics, encompassing vision-based control, human-robot interaction, and advanced decision-making processes.

Representative papers are highlighted.

	[NEW] WayIL:Image-based Indoor Localization with Wayfinding Maps Obin Kwon, Dongki Jung, Youngji Kim, Soohyun Ryu, Suyong Yeon, Songhwai Oh, Donghwan Lee IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2024. (Accepted)
	Attention-Based Randomized Ensemble Multi-Agent Q-Learning Jeongho Park, Obin Kwon, Songhwai Oh. International Conference on Control, Automation and Systems (ICCAS). IEEE, 2023. paper
	Renderable Neural Radiance Map for Visual Navigation Obin Kwon, Jeongho Park, Songhwai Oh. IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023. Highlighted paper project page / arXiv / code
	Topological Semantic Graph Memory for Image-Goal Navigation Nuri Kim, Obin Kwon, Hwiyeon Yoo, Yunho Choi, Jeongho Park, and Songhwai Oh. Conference on Robot Learning (CoRL). PMLR, 2022. Oral presentation project page / arXiv / code / video / talk
	Visually Grounding Language Instruction for History-Dependent Manipulation Hyemin Ahn, Obin Kwon*, Kyungdo Kim, Jaeyeon Jeong, Howoong Jun, Hongjung Lee, Dongheui Lee, and Songhwai Oh. ( equal contribution) International Conference on Robotics and Automation (ICRA). IEEE, 2022. project page / arXiv / code+data
	Visual Graph Memory with Unsupervised Representation for Visual Navigation Obin Kwon, Nuri Kim, Yunho Choi, Hwiyeon Yoo, Jeongho Park, Songhwai Oh. (* equal contribution) IEEE/CVF International Conference on Computer Vision (ICCV), 2021. project page / paper / code
	Geometric Understanding of Reward Function in Multi-Agent Visual Exploration Minyoung Hwang, Obin Kwon, Songhwai Oh. International Conference on Control, Automation and Systems (ICCAS) , 2021. paper / video
	Image-goal navigation algorithm using viewpoint estimation Obin Kwon, Songhwai Oh. International Conference on Control, Automation and Systems (ICCAS) , 2021. paper
	Learning to use topological memory for visual navigation Obin Kwon, Songhwai Oh. International Conference on Control, Automation and Systems (ICCAS) , 2020. paper
	... and more ! Will be updated soon :)

Project

Visual Navigation in Real World
Seoul National University, Winter 2021, Summer 2022.

Teaching

	Deep Reinforcement LEarning (Topics in Control and Automation) TA, Seoul National University, Spring 2021.
	Theory and Lab of IoT, AI, and Big Data TA, Seoul National University, Fall 2019.
	Introduction to Intelligent Systems TA, Seoul National University, Fall 2018.

Scholarship

	BrainKorea 21 Plus Fall 2020 - Spring 2022, Fall 2023.
	Kim Jeong-sik Special Scholarship, Kwanak Corporation, Electrical and Compucter Scholarship Foundation Spring 2015 - Fall 2017. (Full tuition + )
	Merit-based Admission Scholarship, Yongin City Scholarship Foundation Spring 2014.

Last Updated: 24.03.23

This webpage template is from Jon Barron's.