Papers
1
Total Citations
1
H-Index
1
About
Jemin Lee is a researcher at the intersection of robotics, computer vision, and human-robot interaction, with a particular focus on enabling robots to understand and adapt to human preferences during physical tasks. Their most-cited work, "Visual Preference Inference: An Image Sequence-Based Preference Reasoning in Tabletop Object Manipulation" (2024), addresses a critical challenge in assistive robotics: how machines can infer a human’s unspoken visual preferences—such as favoring a specific color or shape—from sequences of object manipulation. By leveraging image sequences rather than explicit commands, Lee’s approach allows robots to reason about user intent more naturally, reducing the need for direct programming or verbal instructions. While early in its citation trajectory, this contribution is foundational for developing more intuitive, human-aligned robotic systems in domestic and industrial settings. Lee’s research bridges cognitive science and machine learning, offering a pathway toward robots that learn from observation rather than instruction. Their work holds promise for applications in personalized assistance, rehabilitation, and collaborative manufacturing, where understanding subtle human cues is essential for seamless cooperation.
Research Focus
Key Achievements
Top Papers
- 1