Papers
5
Total Citations
199
H-Index
4
About
Suyoung Choi is redefining the boundaries of legged robotics, with a focus on enabling quadrupedal robots to operate robustly in complex, real-world environments. His primary research areas span reinforcement learning for locomotion, whole-body manipulation, and state estimation. Choi’s major contributions include pioneering simulation-based reinforcement learning approaches that allow quadrupeds to traverse soft and deformable terrain at high speed—a critical challenge for field robotics. He also developed a hierarchical control system for whole-body manipulation, enabling robots to move large, heavy objects using their entire body, not just a gripper. His work on learning vehicle dynamics from cropped image patches further advances autonomous navigation in unpaved outdoor terrains. Choi’s impact is evidenced by his highly cited 2023 paper on deformable terrain locomotion (147 citations) and his 2023 work on whole-body manipulation (40 citations). Notably, he led the RAIBO2 project, which achieved a world-first: a quadruped robot completing a full marathon on a single battery charge, demonstrating unprecedented energy efficiency. Through his integration of model-based filters with neural networks for state estimation, Choi continues to push legged robots toward true autonomy in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1Learning quadrupedal locomotion on deformable terrain147 citations · 2023
- 2Learning Whole-Body Manipulation for Quadrupedal Robot40 citations · 2023
- 3
- 4
- 5