Thomas Friedel

About

Thomas Friedel is a researcher at the forefront of industrial robotics and computer vision, with a particular focus on enabling precise and reliable object localization for collaborative assembly. His work bridges the gap between deep learning and classical machine vision, a synthesis best exemplified by his highly cited 2021 paper, "A Hybrid Approach for Object Localization Combining Mask R-CNN and Halcon in an Assembly Scenario." In this work, Friedel demonstrates how to leverage the semantic understanding of a neural network alongside the sub-pixel accuracy of traditional algorithms, achieving the speed and robustness necessary for real-world robotic grasping. This hybrid methodology is his key contribution, offering a practical pathway for deploying AI in manufacturing. While his citation count is still growing, his research is directly shaping how robots perceive and interact with their environment in Industry 4.0 settings. By focusing on the critical intersection of accuracy and speed, Friedel is helping to make truly collaborative, human-robot workspaces a tangible reality.

Research Focus

Key Achievements

Top Papers

1. 1
   A Hybrid Approach for Object Localization Combining Mask R-CNN and Halcon in an Assembly Scenario

   2 citations · 2021

Key Collaborators

Contact & Links