Ruomeng Fan

About

Ruomeng Fan is a rising researcher in computer vision and robotics, whose work centers on enabling intelligent systems to intuitively interact with the physical world. Her primary research areas include affordance learning, robotic manipulation, and one-shot imitation learning. Fan’s most notable contribution is the development of One-Shot Affordance Learning (OSAL), a groundbreaking pipeline that allows robots to learn how to manipulate articulated objects—such as doors, drawers, or cabinets—by observing a single human demonstration. This approach redefines affordance by encoding it as an open-loop trajectory tied to a specific object region, dramatically reducing the need for large-scale training data. While her 2023 paper has garnered early citations, its conceptual novelty positions it as a foundational step toward more efficient, human-like robot learning. Fan’s work bridges the gap between perception and action, offering a scalable solution for robots to generalize manipulation skills across unseen objects. Her achievements highlight a promising trajectory in making robotic systems more adaptable and accessible, with potential applications in assistive technology, manufacturing, and household automation.

Research Focus

Key Achievements

Top Papers

1. 1
   One-Shot Affordance Learning (OSAL): Learning to Manipulate Articulated Objects by Observing Once

   2 citations · 2023

Key Collaborators

Contact & Links