Papers
1
Total Citations
6
H-Index
1
About
Evelyn Fu is a pioneering roboticist whose research sits at the intersection of computer vision, physics simulation, and autonomous manipulation. Her most notable contribution is the development of fully automated Real2Sim pipelines—systems that bridge the gap between real-world perception and high-fidelity digital twins. In her landmark 2025 paper, "Scalable Real2Sim: Physics-Aware Asset Generation Via Robotic Pick-and-Place Setups," Fu introduced a method that eliminates the labor-intensive manual measurements traditionally required to create simulation-ready assets. By leveraging robotic pick-and-place interactions, her approach automatically infers physical properties like mass, friction, and center of mass from real-world observations, generating accurate digital twins with zero human intervention. This work has already garnered 6 citations and is reshaping how researchers approach robotic manipulation, enabling more robust sim-to-real transfer. Fu’s research directly addresses a critical bottleneck in robotics: the scalability of physics-aware asset generation. Her contributions are foundational for advancing autonomous systems that can learn and adapt in unstructured environments, making her a rising leader in the field of robotic simulation and digital twin technology.
Research Focus
Key Achievements
Top Papers
- 1