My research interest lies in the area of Reinforcement Learning, both practical applications and theoretical perspectives.
I focus on solving sequential decision-making problems for real-world autonomous learning systems!
These are the questions that I am digging these days.
1️⃣ How can an agent acquire skills with minimal (or without) human-engineered intervention?
2️⃣ How can an agent acquire general-purpose skills to efficiently solve practical, long-horizon tasks?
3️⃣ What are the key differences that distinguish AI agents from humans in the process of learning new skills? What aspects of human learning can AI systems leverage?
I am a research scientist at the Korea Institute of Science and Technology (KIST) under the supervision of a senior researcher, Yisoo Lee. Before that, I received my M.S. from Korea University under the supervision of Professor Myo-Taeg Lim, where I studied reinforcement learning and path planning for autonomous driving. I received my B.S. from the University of Seoul. I finished internship at Hyundai Motor Group, working on developing autonomous driving decision-making and control.
📖 Educations
- M.S. in Electrical and Computer Engineering, Mar. 2021 - Aug. 2023
- Major : Control, Robotics and Systems. Korea University (GPA: 4.39/4.5)
- Research Scholarship from Hyundai Motor Group, Mar. 2021 - Dec. 2022,
- B.S. in Electrical and Computer Engineering, Mar. 2017 - Feb. 2021
- University of Seoul. (GPA: 4.0/4.5)
- Research Scholarship from Hyundai Motor Group, Sep. 2019 - Dec. 2020
🔥 News
- Sep. 2023: 🎉🎉 Paper published at electronics journal
- Aug. 2023: 🎉🎉 Completed my M.S degree!!
- Jan. 2022: 🎉🎉 Started working at KIST.
👩🏼💻 ̆̈Projects
Autonomous Robot Manipulator Operation for Intricate Object Handling
- ON GOING PROJECT!
- Challenge to long-horizon manipulator operation using reinforcement learning.
- Develop skills for operating equipment (e.g., valve, switch, gear lever…) at industrial sites with a manipulator.
- Learn skills while minimizing human-engineered features.
- Learn skills without human intervention to enhance the autonomy of our robot manipulator.
- Implemented TQC.
Dual-Armed Mobile Manipulator Door Traversal
- ON GOING PROJECT!
- Address challenges of door traversal motion planning
- Unified framework for door traversal, from approaching, opening, passing through, and closing the door with dual-armed mobile manipulator
- Decision making for optimal contact point planning with RL.
Classified Experience Replay
- Challenge to skewed sub-goal distribution for goal-conditioned RL controller.
- Implemented TQC.
- Paper under review
Learning to drive in highway with guided RL controller.
- Addresses the challenge of reward shaping for continuous RL controllers by using MPC reference.
- Implemented DDPG.
- Paper published at ICEIC, 2022 (oral).
F1tenth Virtual Race competition
- Compete to race with RL controller.
- Participated in IROS, 2021 and ICRA, 2022
- Won 3rd prize
- Implemented PPO, DQN.
Pallet loading problem with robot manipulator
- Employed decision-making techniques using Reinforcement Learning (RL) to optimize box layout on pallets for varying box sizes.
- Implemented PPO.
- Executed pallet loading operations based on the optimized layout using the Doosan Robotics M1013 robot manipulator.
- Successfully applied this solution in a real-world scenario.
Lane change decision making on crowded highway environment
- Establishing robust statistical criteria for lane change decisions in driving, grounded in human data.
- Poster session at EMECS, 2023
Transformer model from scratch!
- Generate Korean-English translator.
Smart Mobility Project - Fail safe system development
- Development of a fail-safe system for self-driving cars.
- Utilization of V2V sensor data for operation during sensor failure.
- Presentation
📝 Publications
Classified Experience Replay: The Off-Policy Reinforcement Learning Method and Dynamic Trajectory Planning for Autonomous Driving
- Under Review
Yujin Kim, Sun-Ho Jang, Woo-Jin Ahn, Myo-Taeg Lim, Dong-Sung Pae
Reinforcement Learning for Autonomous Vehicle using MPC in Highway Situation
Yujin Kim, Dong-Sung Pae, Sun-Ho Jang, Seong-Woo Kang, Myo-Taeg Lim
Prediction of estimated lane change distance on highway: based on traffic information
Yujin Kim, Seok Youl Yang, Myo-Taeg Lim
Stable and Efficient Reinforcement Learning Method for Avoidance Driving of Unmanned Vehicles
Sun-Ho Jang, Woo-Jin Ahn, Yu-Jin Kim, Hyung-Gil Hong, Dong-Sung Pae, Myo-Taeg Lim
🎖 Honors and Awards
- Spring 2018, Scholarship for Excellent Achievement, University Of Seoul.
- Sep. 2018 - Dec. 2022, Full Scholarship for Selected Research Student, Hyundai Motor Company.
- May 2022, 10th F1TENTH Autonomous Racing Grand Prix, 3rd Place, ICRA 2022.
- Jul. 2018, 2018 Intelligent Model Car Competition, 3rd Place, Hanyang University.
- Jul. 2017, 14th Microrobot Competition, Special Award for Women Engineer, Dankook University.
💻 Work Experience
- Jan. 2023 - now, Korea Institute of Science and Technology, Republic of Korea.
- Jul. 2019, Hyundai Motor Group, Republic of Korea.