Papers
1
Total Citations
2
H-Index
1
About
Haewon Park is a leading researcher in legged robotics and reinforcement learning, whose work is redefining how robots achieve versatile, adaptive locomotion. Her key contributions center on developing model-free frameworks that enable robots to seamlessly transition between diverse gaits—including quadrupedal, tripodal, and bipedal motion—without task-specific engineering. In her highly cited 2025 paper, "A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards," Park introduces an innovative motion-style reward grounded in a relaxed logarithmic barrier function. This soft-constraint approach biases learning toward natural, stable gaits while preserving the flexibility to tackle varied tasks. Though early in its citation trajectory, this work has already garnered attention for its potential to unify locomotion control under a single, scalable algorithm. Park’s research bridges the gap between theoretical reinforcement learning and practical robotic deployment, offering a pathway toward robots that can autonomously adapt their movement to complex, unstructured environments. Her achievements mark a significant step forward in creating truly versatile legged machines.
Research Focus
Key Achievements
Top Papers
- 1