Hyemin Park

About

Hyemin Park is a robotics researcher whose work sits at the intersection of deep reinforcement learning and anthropomorphic manipulation. Her primary research focus is on enabling robotic hands to perform human-like object grasping and relocation—a critical challenge in dexterous manipulation. In her most cited work, she introduced a novel framework that leverages natural hand pose priors within deep reinforcement learning, allowing an anthropomorphic robotic hand to learn more intuitive and efficient grasping strategies that closely mimic human motion. This contribution addresses a fundamental bottleneck in robotics: bridging the gap between rigid, pre-programmed grasps and the fluid, adaptive dexterity of the human hand. With 5 citations, her paper has provided a foundational approach for researchers working on human-robot interaction and autonomous manipulation. Park’s work is notable for its emphasis on biological plausibility in robotic control, offering a pathway toward more seamless and natural interactions between humans and machines in shared environments.

Research Focus

Key Achievements

Top Papers

1. 1
   Human-like Object Grasping and Relocation for an Anthropomorphic Robotic Hand with Natural Hand Pose Priors in Deep Reinforcement Learning

   5 citations · 2019

Key Collaborators

Contact & Links