Yewon Kim

Papers

Total Citations

H-Index

About

Yewon Kim is a rising researcher in the field of cooperative robotics and reinforcement learning, with a focused interest in enabling robots to master dynamic, real-world manipulation tasks. Her work centers on the challenge of table-balancing, a complex problem requiring precise coordination and adaptive control. Kim’s major contributions lie in advancing multi-robot learning systems, moving beyond traditional single-agent reinforcement learning. Her most cited work, "Cooperative Robot for Table Balancing Using Q-learning" (2020, 8 citations), established a foundational framework for this task. She then significantly expanded this approach in her 2023 paper on deep reinforcement learning (6 citations), which demonstrated how robots can autonomously learn to judge and operate in cooperative scenarios. Her latest 2024 research introduces a novel "interactive robot-robot reinforcement learning" technique, designed to minimize the high labor costs of human intervention in robot training. By proposing a system where robots learn from each other, Kim is pioneering more scalable and autonomous methods for deploying service and guiding robots, making her a notable voice in the future of human-robot collaboration.