John (Chung Hee) Kim

I am a PhD student in the Robotics Institute at Carnegie Mellon University. I am currently a graduate student researcher at the Kantor Lab advised by Dr. George Kantor.

I received my B.Eng. in Mechanical Engineering and M.Phil. in Electronic and Computer Engineering from the Hong Kong University of Science and Technology, where I worked as a research assistant in the Robot Manipulation Lab advised by Dr. Jungwon Seo.

           

profile photo
Research

My research interest lies in the intersection of robotic manipulation, perception, and machine learning. I enjoy solving real world problems by working with robots to develop practical systems and solutions.

Autonomous Robotic Pepper Harvesting: Imitation Learning in Unstructured Agricultural Environments
Chung Hee Kim, Abhisesh Silwal, George Kantor
Under Review
[Project Page] [arXiv]

Autonomous robotic pepper harvesting in the wild!

Towards Robotic Tree Manipulation: Leveraging Graph Representations
Chung Hee Kim, Moonyoung Lee, Oliver Kroemer, George Kantor
ICRA 2024
[Project Page] [Video] [Poster] [arXiv]

We present a framework for learning robotic contact manipulation of tree-like crops by leveraging graph representations.

Occlusion Reasoning for Skeleton Extraction of Self-Occluded Tree Canopies
Chung Hee Kim, George Kantor
ICRA 2023   (ICRA 2023 Outstanding Sensors and Perception Paper Award Winner, Outstanding Student Paper Award Finalist)
[Video] [Presentation] [Poster] [arXiv]

We develop a computer vision method to extract skeleton representation of trees from images featuring large amounts of foliage and self-occlusion.

3D Reconstruction-Based Seed Counting of Sorghum Panicles for Agricultural Inspection
Harry Freeman, Eric Schneider, Chung Hee Kim, Moonyoung Lee, George Kantor
ICRA 2023
[Video] [arXiv]

We develop a method for creating 3D models of sorghum panicles and a non-destructive approach to estimate seed count and weight. This is acheived using seeds as semantic landmarks in both 2D and 3D and a novel density-based clustering approach. Additionally, we present a new metric to evaluate reconstruction quality in the abscense of ground-truth.

Planning for Dexterous Ungrasping: Secure Ungrasping Through Dexterous Manipulation
Chung Hee Kim, Ka Hei Mak, Jungwon Seo
IEEE RA-L / ICRA 2022
[Project Page] [Video] [Presentation] [arXiv]

This enables human-level dexterity in the tasks of ungrasping, e.g., the placement of Go stones that AlphaGo is unable to perform.

Robust Ungrasping of High Aspect Ratio Objects Through Dexterous Manipulation
Ka Hei Mak, Chung Hee Kim, Jungwon Seo
IEEE RA-L / ICRA 2022
[Project Page] [Video]

There's more to our Dexterous Ungrasping -- robustness.

Dig-Grasping via Direct Quasistatic Interaction Using Asymmetric Fingers: An Approach to Effective Bin Picking
Zhekai Tong, Yu Hin Ng, Chung Hee Kim, Tierui He, Jungwon Seo
IEEE RA-L / ICRA 2021
[Project Page] [Video]

Effective bin picking using an asymmetric gripper with different finger lengths.

Picking Thin Objects by Tilt-and-Pivot Manipulation and Its Application to Bin Picking
Zhekai Tong, Tierui He, Chung Hee Kim, Yu Hin Ng, Qianyi Xu, Jungwon Seo
ICRA 2020
[Video]

We present an effective manipulation technique for picking thin objects from a flat surface.

Shallow-Depth Insertion: Peg in Shallow Hole through Robotic In-Hand Manipulation
Chung Hee Kim, Jungwon Seo
IEEE RA-L / ICRA 2019   (ICRA 2019 Best Paper Award in Robot Manipulation)
[Project Page] [Video] [Poster]

We address how to insert a thin object (such as the phone battery) into a shallow-depth hole through dexterous manipulation.


Patents and Copyrights
System and Methods for Robotic Precision Placement and Insertion
Chung Hee Kim, Jungwon Seo
U.S. Patent No. 11,628,561. 18 April, 2023.
[Project Page]

A system and method for accurately placing or inserting objects using robotic manipulation is disclosed.

Selected Projects
Coming Soon

Stolen from source code. Last updated Nov 14, 2024.