Nahyeon Park

About

Nahyeon Park is a robotics researcher whose work sits at the intersection of deep reinforcement learning and anthropomorphic manipulation. Her primary research focuses on enabling robotic hands to grasp and manipulate objects with human-like dexterity and naturalness—a longstanding challenge in robotics. In her most-cited work, "Natural object manipulation using anthropomorphic robotic hand through deep reinforcement learning and deep grasping probability network" (2020, 19 citations), Park developed a framework that combines deep reinforcement learning with a grasping probability network to achieve more intuitive and effective object manipulation. Her earlier study (2019, 5 citations) introduced natural hand pose priors into the learning process, significantly improving the human-likeness of robotic grasping and relocation tasks. By incorporating biomechanically plausible hand configurations as priors, Park’s approach reduces the gap between robotic and human manipulation, offering a pathway toward more seamless human-robot interaction. Her contributions are particularly valuable for applications in assistive robotics, prosthetics, and automated manufacturing. With a focused trajectory on learning-based control for dexterous hands, Park is helping to shape the future of embodied AI and robotic dexterity.

Research Focus

Key Achievements

Top Papers

1. 1
   Natural object manipulation using anthropomorphic robotic hand through deep reinforcement learning and deep grasping probability network

   19 citations · 2020
2. 2
   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