Dylan Danno

Papers

Total Citations

H-Index

About

Dylan Danno is a researcher at the forefront of robotic manipulation and human-robot interaction, with a focused interest in applying computer vision to enable robots to learn from natural human demonstrations. His primary contribution lies in the development of a novel framework for robotic cooking that extracts human poses from unscripted cooking actions using OpenPose, a real-time multi-person keypoint detection system. By capturing and translating the nuanced, sequential movements of a human chef—such as chopping, stirring, and pouring—into actionable robotic commands, Danno’s work bridges the gap between unstructured human activity and precise robotic execution. His most-cited paper, "Robotic Cooking Through Pose Extraction from Human Natural Cooking Using OpenPose" (2022), has garnered 9 citations, reflecting its significance in advancing imitation learning for domestic robotics. This research not only demonstrates a practical pathway for robots to acquire complex culinary skills without explicit programming but also opens avenues for broader applications in assistive and service robotics. Danno’s work is a key step toward making robots more intuitive and capable in everyday environments.