David Then

Papers

Total Citations

151

H-Index

About

David Then is a leading researcher in intelligent robotic manufacturing, specializing in adaptive control and deep learning for automated surface finishing processes. His work bridges the gap between traditional industrial robotics and advanced artificial intelligence, enabling machines to perceive and respond to complex, variable tasks in real time. Then’s most influential contribution is the development of an in-process virtual verification system for weld seam removal during robotic abrasive belt grinding, which uses deep learning to monitor and validate material removal without halting production—a breakthrough that has garnered 97 citations. He further advanced the field with an adaptive framework for robotic polishing based on impedance control, cited 54 times, which allows robots to adjust force and motion dynamically for consistent, high-quality finishes on irregular surfaces. These innovations have significant implications for automotive, aerospace, and heavy manufacturing industries, where precision and efficiency are critical. Then’s work is notable for its practical integration of AI into real-world robotic applications, making him a key figure in the evolution of smart manufacturing and a valuable resource for students and researchers exploring the intersection of robotics, machine learning, and process automation.