I am currently working as a researcher at Samsung Advanced Institute of Technology (SAIT). I received my Ph.D. from Seoul National University, where I was advised by Professor Songhwai Oh. My research focuses on the visual navigation of embodied agents and interactive 3D perceptions of embodied agents. Prior to my Ph.D. studies, I earned a B.S. degree with great honors from Korea University in the Department of Electrical Engineering in 2016. I also had the opportunity to study abroad for a semester at the Australian National University.


[Mar 2023] Start working @ SAIT autonomous car team.
[Feb 2023] Invited talk @ KAIST.
[Dec 2022] Successfully finished Ph.D. Thesis Defense.
[Dec 2022] Oral presentation at CoRL 2022.
[Nov 2022] Poster presentation of TSGM at AIIS Retreat @ Seoul National Univ.
[Sep 2022] TSGM accepted to CoRL 2022 as an oral presentation.
[Jun 2022] Invited talk @ Intelligent Robotics Course of Korea Univ.
[Jul 2021] VGM accepted to ICCV 2021.

Publications (representative papers are highlighted)


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-22)
Oral presentation (acceptance rate: 6.5%)

Semantic Descriptors into Representation for Robust Indoor Visual Place Recognition

Nuri Kim, Minjae Kang, and Songhwai Oh.
International Conference on Control, Automation and Systems (ICCAS-21)


Visual Graph Memory with Unsupervised Representation for Visual Navigation

Obin Kwon, Nuri Kim, Yunho Choi, Hwiyeon Yoo, Jeongho Park, and Songhwai Oh.
International Conference on Computer Vision (ICCV-21)
webpage | pdf | video | code


Learning Instance-Aware Object Detection Using Determinantal Point Processes

Nuri Kim, Donghoon Lee, and Songhwai Oh.
Computer Vision and Image Understanding (CVIU-20)
pdf | code

Interactive Text2Pickup Networks for Natural Language-Based Human-Robot Collaboration

Hyemin Ahn, Sungjoon Choi, Nuri Kim, Geonho Cha, and Songhwai Oh.
IEEE Robotics and Automation Letters (RAL-18) and IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS-18)
pdf | video


Semantic Visual Navigation for Embodied Agents: A Graph-Based Approach

Seminar, KAIST, Feb 2023

CoRL 2022 Review

Lab Seminar, Seoul National University, Jan 2023

Oral Presentation of TSGM

Conference on Robot Learning, Auckland, New Zealand, Dec 2022
Video, Slides

Topological Semantic Graph Memory

AIIS Retreat, Seoul National University, Nov 2022

Introduction to Visual Navigation

Intelligent Robotics Course, Korea University, June 2022

Honors and Awards

  • Brain Korea 21 Plus Scholarship, Seoul National University, 2019-2021
  • Great Paper Award, Korean Institute of Information Scientists and Engineers, 2017
  • Lecture & Research Scholarship, Seoul National University, 2016
  • Graduate with Great Honor, Korea University, 2016
  • Creative Challenger Scholarship, Korea University, 2015
  • National Scholarship For Science and Engineering, Korea Student Aid Foundation (KOSAF), 2014-2015

  • Teaching Experience

  • Graduation Project, Seoul National University, 2018F
  • Introduction to Intelligent Systems, Seoul National University, 2016F

  • Projects

  • [Navi AI] Development of AI Technology for Guidance of a Mobile Robot to its Goal with Uncertain Maps in Indoor/Outdoor Environments, 2019-2022
    1. - Developed an indoor environment navigation robot that works even in unknown environments by leveraging semantic understanding when maps are unavailable.
  • [SW Star Lab] Robot Learning: Efficient, Safe, and Socially-Acceptable Machine Learning, 2019-2021
    1. - Developed a robot navigation technology capable of predicting crowd trajectories and performing social actions in various crowd cluster scenarios.
  • [Brain AI] Brain-Inspired AI with Human-Like Intelligence, 2019-2021
    1. - Developed a reliable object detector in occluded environments.
  • [Giga 4D] Real-time 4D reconstruction of dynamic objects for ultra-realistic service, 2017-2020
    1. - Collected 3D point cloud data for dynamic object registration and alignment.

    Personal Projects

  • [Quant] Quantitative Trading, 2020-Present
    1. - Development of algorithms for finding an optimal portfolio ratio.