Veselin Georgiev

Papers

Total Citations

H-Index

About

Veselin Georgiev is a roboticist whose research focuses on dexterous manipulation and machine learning for physical interaction. His most-cited work, "Learning to slide a magnetic card through a card reader" (2012, 14 citations), tackles a deceptively complex challenge: programming an upper-torso humanoid robot to perform a precise, occluded manipulation task. The paper demonstrates how robots can learn to handle flexible, partially visible objects—a significant departure from rigid, fully observable parts. Georgiev’s key contribution lies in bridging the gap between high-level planning and low-level sensorimotor control, showing that a robot can acquire a fine motor skill through trial-and-error learning rather than explicit programming. While his citation count is modest, the work is notable for its practical, real-world focus on a task humans perform effortlessly but robots find extremely difficult. This research has implications for automating everyday interactions, from swiping cards to handling flexible packaging. Georgiev’s approach—combining reinforcement learning with careful experimental design—offers valuable lessons for students and researchers working on manipulation in partially observable environments.