Dabae Kim
Papers
2
Total Citations
18
H-Index
2
About
Dabae Kim is a roboticist whose research lies at the intersection of manipulation, perception, and geometric methods. Her key contributions include pioneering a novel caging-based grasping technique for deformable objects, which enables robots to securely grasp soft or irregular items using only geometric constraints and position control—eliminating the need for complex force sensing. This work, published in 2019, has garnered 13 citations and represents a significant step toward more robust, geometry-driven robotic manipulation. Kim has also advanced spherical camera rotation estimation with her work on E-CNN, a method that uniformizes distorted optical flow fields to enable accurate rotation regression using convolutional neural networks. This approach, cited 5 times, addresses a critical challenge in applying CNNs to non-planar imagery for robotic applications. Through these contributions, Kim demonstrates a commitment to developing elegant, principled solutions that expand the capabilities of robotic systems in real-world environments, particularly in handling deformable objects and leveraging novel sensing modalities.
Research Focus
Key Achievements
Top Papers
- 1
- 2