Dennis Ludl

Papers

Total Citations

H-Index

About

Dennis Ludl is a researcher specializing in computer vision and robotics, with a focus on enabling autonomous, data-driven perception for industrial manipulators. His key research areas include 2D pose estimation of industrial robots, dataset acquisition for real-world robotic systems, and the development of smart sensory systems for dynamic, human-robot collaborative workspaces. Ludl’s major contribution is the RoPose framework, which leverages convolutional neural networks (CNNs) to accurately estimate the 2D pose of industrial robot arms in cluttered, non-stationary environments. This work addresses a critical need for reliable environmental monitoring as production workspaces become more mobile and flexible. By building on this foundation with the RoPose-Real dataset, he provided a benchmark for real-world data acquisition, enabling more robust and generalizable pose estimation models. His research directly supports the safe and autonomous operation of robots mounted on mobile platforms alongside human workers. With his most-cited paper, “RoPose: CNN-based 2D Pose Estimation of Industrial Robots” (2018), accumulating 15 citations, Ludl’s work has laid important groundwork for integrating deep learning into industrial robotics. His achievements highlight a practical, data-driven approach to overcoming the challenges of dynamic manufacturing environments, making his research highly relevant for students and engineers working at the intersection of computer vision, robotics, and Industry 4.0.