Seungchan Kim

email: seungch2@andrew.cmu.edu

I am a fourth-year PhD student in the Robotics Institute at Carnegie Mellon University, advised by Sebastian Scherer. My research interests are robot exploration & navigation, active robotic perception, and spatial AI.

Previously, I received B.S. in Applied Mathematics & Computer Science and M.S. in Computer Science from Brown University. During my time at Brown, I was advised by George Konidaris and Michael Littman, working on research in deep reinforcement learning.

CV  /  GitHub  /  Google Scholar  /  Twitter

profile photo
News

  • 03/2023: Organizing Tartan Planning Series Spring 2023!
  • 07/2022: 2 papers on few-shot object detection were accepted at ECCV and IROS
  • 11/2021: 1 paper on unsupervised online learning for robotics accepted at T-RO
  • 09/2020: Started PhD in Robotics at Carnegie Mellon University!

Publications
Multi-Robot Multi-Room Exploration with Geometric Cue Extraction and Spherical Decomposition
Seungchan Kim, Micah Corah, John Keller, Graeme Best, Sebastian Scherer
arXiv preprint arXiv:2307.15202. Under Review
AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration
Bowen Li, Chen Wang, Pranay Reddy, Seungchan Kim, Sebastian Scherer
European Conference on Computer Vision (ECCV) 2022
project page | code
Robotic Interestingness via Human-Informed Few-Shot Object Detection
Seungchan Kim, Chen Wang, Bowen Li, Sebastian Scherer
IEEE/RSJ International Conference on Robotics and Systems (IROS) 2022
Unsupervised Online Learning for Robotic Interestingness with Visual Memory
Chen Wang, Yuheng Qiu, Wenshan Wang, Yafei Hu, Seungchan Kim, Sebastian Scherer
IEEE Transactions on Robotics (T-RO) 2022
Using Computational Analysis of Behavior to Discover Developmental Change in Memory-Guided Attention Mechanisms in Childhood
Dima Amso, Lakshmi Govindarajan, Pankaj Gupta, Diego Placido, Heidi Baumgartner, Andrew Lynn, Kelley Gunther, Tarun Sharma, Vijay Veerabadran, Kalpit Thakkar, Seungchan Kim, Thomas Serre
PsyArXiv. doi:10.31234/osf.io/gq4rt
Combating the Compounding-Error Problem with a Multi-step Model
Kavosh Asadi, Dipendra Misra, Seungchan Kim, Michael Littman
arXiv preprint arXiv:1905.13320 (2019).
DeepMellow: Removing the Need for a Target Network in Deep Q-Learning
Seungchan Kim, Kavosh Asadi, Michael Littman, George Konidaris
International Joint Conference on Artificial Intelligence (IJCAI) 2019
Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2019
project page | code
Removing the Target Network from Deep Q-Networks with the Mellowmax Operator
Seungchan Kim, Kavosh Asadi, Michael Littman, George Konidaris
International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2019
Teaching
16-711 Kinematics, Dynamics, Control , Carnegie Mellon University Robotics Institute
Teaching Assistant, Spring 2023

16-833 Robot Localization and Mapping, Carnegie Mellon University Robotics Institute
Teaching Assistant, Spring 2022
CSCI1430 Computer Vision, Brown University
Teaching Assistant, Spring 2019

CSCI0040 Intro to Scientific Computing and Problem Solving, Brown University
Teaching Assistant, Spring 2015
Service
Organizer: Tartan Planning Series Spring 2023

Reviewer: ICML, AAAI, ICLR, NeurIPS, ICRA, IEEE RA-L, IJRR

Website Template from Jon Barron.