Jihwan Kim

Completing Ph.D. at Robotics Laboratory in Seoul National University, under the supervision of Professor Frank C. Park, and currently working at the Robot Center of Samsung Research, Samsung Electronics.

Email: jihwankim@robotics.snu.ac.kr

CV / Google Scholar / Github / Youtube

Research Interests

My research interests lie at the intersection of robotics and machine learning, with a particular focus on motion planning for robot arm manipulation and collision avoidance systems. I am passionate about developing learning-based approaches for robotic systems, including representation learning and active learning methods that can enhance robot performance and safety in complex manipulation tasks.

Publications ( * denotes equal contribution.)

	[C3] EquiGraspFlow: SE(3)-Equivariant 6-dof Grasp Pose Generative Flows Byeongdo Lim, Jongmin Kim, Jihwan Kim, Yonghyeon Lee, Frank C. Park Conference on Robot Learning (CoRL) 2024 Project Page • Paper • Code • Bibtex
	[C2] Graph Geometry-Preserving Autoencoders Jungbin Lim, Jihwan Kim, Yonghyeon Lee, Cheongjae Jang, Frank C. Park International Conference on Machine Learning (ICML) 2024 Paper • Code • Bibtex
	[W1] Leveraging Equivariant Representations of 3D Point Clouds for SO(3)-Equivariant 6-DoF Grasp Pose Generation Byeongdo Lim, Jongmin Kim, Jihwan Kim, Yonghyeon Lee, Frank C. Park ICRA 2024 Workshop on 3D Visual Representations for Robot Manipulation Paper • Bibtex
	[J3] Active Learning of the Collision Distance Function for High-DOF Multi-arm Robot Systems Jihwan Kim, Frank C. Park Robotica 2024 Paper • Bibtex
	[C1] PairwiseNet: Pairwise Collision Distance Learning for High-dof Robot Systems Jihwan Kim, Frank C. Park Conference on Robot Learning (CoRL) 2023 Paper • Code • 3min Video • Bibtex
	[J2] DSQNet: A Deformable Model-Based Supervised Learning Algorithm for Grasping Unknown Occluded Objects Seungyeon Kim, Taegyun Ahn, Yonghyeon Lee, Jihwan Kim, Michael Y. Wang, Frank C. Park IEEE Transactions on Automation Science and Engineering (T-ASE) 2022 Project Page • Paper • Code • Bibtex
	[J1] Learning-Based Real-Time Detection of Robot Collisions Without Joint Torque Sensors Kyu Min Park, Jihwan Kim, Jinhyuk Park, Frank C. Park IEEE Robotics and Automation Letters (RA-L) 2021 Paper • Bibtex

Projects

	Non-prehensile Robot Manipulation for Automated Robot Recycling Systems Feb 2021 - Sep 2022 with IITP, Project Member Develop high-speed and reliable algorithms for non-prehensile robotic manipulation to automate recycling waste sortation through hitting, pushing, and throwing actions.
	Development of Machine Learning Models and Systems for Sales Forecasting Nov 2020 - Oct 2022 with Fresheasy, Project Member Develop a machine learning model and training system for sales forecasting to optimize food production management.
	Artificial Intelligence-based Automated Painting Robot System Oct 2020 - Sep 2021 with Doolim-Yaskawa, Project Member Develop an AI-driven automation system for optimizing robotic painting trajectories in automotive manufacturing facilities.
	Development of Learning-Based IT Operations System Monitoring Algorithm Mar 2020 - May 2020 with EXEM, Project Member Develop a machine learning algorithm for detecting anomalies in large-scale IT systems through analysis of sequential log message patterns and relationships.
	Kinematic and Dynamic Model Identification of Tendon-driven Robot Arm Systems Nov 2019 - Sep 2020 with Naver Labs, Project Member Develop an algorithm for identifying kinematic and dynamic parameters of robot arms with complex tendon-driven mechanisms, focusing on accurate system model identification.
	Learning-Based Collision Detection Algorithms for Collaborative Robot Arms Jun 2019 - Oct 2019 with Doosan Robotics, Project Member Develop a machine learning algorithm for detecting collisions in collaborative robot arms that can identify external torques without using expensive joint torque sensors [J1].

Education

Feb 2025. Ph.D. degree in Mechanical Engineering, Seoul National University

Advisor: Prof. Frank Chongwoo Park
Thesis: Collision Distance Estimation for High-dof Robot Systems: A Learning-Based Approach
PDF • Slides
Outstanding Doctoral Dissertation Award

Feb 2019. B.S. degree in Mechanical Engineering, Seoul National University

Cum Laude

Feb 2015. Gyeonggi Science High School for the Gifted

Teaching Experiences

Teaching Assistant, Geometric Methods for High-Dimensional Data Analysis (M3239.006800), SNU, 2023F

Teaching Assistant, Dynamics (446.204A), SNU, 2022F

Teaching Assistant, Introduction to Robotics (M2794.0027), SNU, 2019S

Template based on Jon Barron's website.