Sungjae Park

I am a Research Intern at Cognitive Learning for Vision and Robotics Lab(CLVR) in Korea Advanced Institute of Science and Technology(KAIST), where I work on robot learning. Also, I am currently a senior undergraduate student in Mechanical Engineering and Mathematics at Seoul National University(SNU).

Email  /  CV  /  Twitter  /  Github

profile photo
Research

My research interest lies on developing a learning robot that can accomplish complex, long-horizon manipulation tasks. Ultimately, I aim to develop a general-purpose robot system. To achieve my ultimate goal, specific topics I am interested in are: learning an agent with physical understanding & reasoning ability, efficient reinforcement learning from prior data, and contact-rich dexterous manipulation.

critical Accelerating Reinforcement Learning with Critical States from Prior Data
Sungjae Park, Ayush Jain, Youngwoon Lee, Joseph J. Lim
To be submitted

We use task oriented critical states to boost reinforcment learning.

Projects
pgm Online Active Gaussian Process Motion Planning in Unknown Environments
Sungjae Park, Hyelim Choi, Taekyun Kim
Graduate Course Project (Probabilistic Graphical Models, Spring 2022)

We combine gaussian process motion planning with entropy-based information factor to perform online active motion planning in unknown environments.

Teaching
modern_robotics Introduction to Robotics
Student Instructor, Spring 2022

College Physics 1, 2
Undergraduate Tutoring, Spring 2018, Fall 2018, Spring 2021, Fall 2021

Linear Algebra
Undergraduate Tutoring, Spring 2021



Website template from Jon Barron.