Moshe Kimhi

Technion – Israel Institute of Technology

Papers

Total Citations

H-Index

About

Moshe Kimhi is a robotics researcher whose work focuses on the intersection of computer vision and robotic manipulation, particularly in unstructured, cluttered environments. His key contributions lie in developing data-efficient methods for robot perception, addressing the critical bottleneck of expensive manual annotation. His most-cited paper, "Robot Instance Segmentation with Few Annotations for Grasping" (2025), introduces a novel approach that enables robots to accurately segment and grasp objects using only a handful of labeled examples. This work directly tackles challenges in domains like traffic, navigation, and industrial grasping, where high object variability and clutter make traditional, data-hungry methods impractical. By reducing the reliance on vast labeled datasets, Kimhi’s research paves the way for more adaptable and cost-effective robotic systems. With 4 citations already for this recent publication, his work is gaining traction in the robotics community, promising significant impact on real-world applications from warehouse automation to autonomous driving.