Nabil Ettehadi

Papers

Total Citations

H-Index

About

Nabil Ettehadi is a roboticist whose research lies at the intersection of manipulation, perception, and learning, with a focus on enabling robots to interact with novel objects in unstructured environments. His most influential work, "Edge-Based Recognition of Novel Objects for Robotic Grasping" (2018, 9 citations), introduces a framework that combines object geometry, reachability, and force closure analysis to localize contact regions for grasping unknown items—a critical step toward autonomous operation in real-world settings. Complementing this, his 2017 paper on "Learning from Demonstration" (4 citations) presents a motion segmentation algorithm that identifies locally distinct trajectory segments, allowing for adaptive scaling and rotation of learned skills. This work bridges the gap between demonstration and generalization, making robot programming more intuitive. Ettehadi’s contributions are particularly notable for their practical focus on perception-driven manipulation, offering scalable solutions for robotic grasping without prior object models. His research continues to influence the fields of dexterous manipulation and learning from demonstration, providing foundational tools for robots that must adapt to dynamic, cluttered environments.