Yizhak Ben-Shabat

Technion – Israel Institute of Technology, Australian National University

Papers

Total Citations

258

H-Index

About

Yizhak Ben-Shabat is a researcher specializing in 3D computer vision, deep learning, and robotics, with a particular focus on point cloud analysis and human-robot collaboration. His work bridges the gap between raw sensor data and intelligent machine perception, making significant contributions to how autonomous systems understand and interact with three-dimensional environments. Ben-Shabat's most notable contribution is his 2018 paper introducing 3DmFV (Three-Dimensional Modified Fisher Vectors), a pioneering approach for real-time 3D point cloud classification using convolutional neural networks. This work, which has accumulated an impressive 243 citations, addressed a critical challenge in robotics — enabling systems equipped with LiDAR sensors to efficiently process and classify their surroundings for applications such as obstacle avoidance and environmental mapping. By proposing a novel representation that bridges classical statistical methods with modern deep learning, his approach demonstrated both computational efficiency and strong classification performance. More recently, Ben-Shabat has extended his research into human-robot collaborative systems, exemplified by GoferBot (2022), a visually guided assembly system designed to support smart manufacturing workflows. This work reflects a broader research vision connecting 3D perception with practical robotic applications, positioning Ben-Shabat as a versatile contributor to the evolving field of intelligent, perception-driven robotics.