Elke Smet

About

Elke Smet is a researcher at the forefront of robotics and computer vision, with a focus on integrating deep learning into robotic control systems. Her primary research areas include visual servoing, convolutional neural networks (CNNs), and collaborative robotics, particularly applied to industrial cobots. Her most-cited work, "Comparison of Deep Learning Models in Position Based Visual Servoing" (2022, 6 citations), introduces a novel PBVS algorithm that repurposes and fine-tunes a pre-trained CNN offline, enabling a UR10 cobot to perform precise positioning tasks without real-time retraining. This contribution bridges the gap between deep learning and practical robotic manipulation, offering a scalable solution for industrial automation. Smet’s work demonstrates how transfer learning can reduce computational overhead while maintaining accuracy, a key challenge in real-world robotics. Her research has implications for manufacturing, where cobots must adapt to dynamic environments. With a growing citation footprint, Smet is establishing herself as a rising voice in applied AI and robotics, pushing the boundaries of how neural networks can enhance robotic perception and control in collaborative settings.

Research Focus

Key Achievements

Top Papers

1. 1
   Comparison of Deep Learning Models in Position Based Visual Servoing

   6 citations · 2022

Key Collaborators

Contact & Links