Wim Dewulf

About

Wim Dewulf is a leading researcher at the intersection of industrial robotics, manufacturing, and non-destructive testing. His work primarily focuses on enhancing the efficiency and precision of robotic systems, with key contributions in energy-optimized robot path planning and advanced X-ray computed tomography (CT). Dewulf’s most cited paper (108 citations) introduces a systematic methodology for identifying and planning energy-efficient trajectories for industrial ABB robots, using non-invasive on-site measurements to reduce energy consumption without compromising performance. In the realm of robotic CT, he has pioneered methods for flexible scan trajectories, including a reference-free approach for estimating imaging geometry (8 citations) and investigations into robot properties affecting twin Robot-CT systems (8 citations). His recent work leverages deep learning for simultaneous mass estimation and class classification of scrap metals (38 citations), demonstrating the application of AI in material recycling. Dewulf’s research is notable for its practical impact on sustainable manufacturing and high-precision inspection, bridging the gap between theoretical robotics and real-world industrial challenges.

Research Focus

Key Achievements

Top Papers

1. 1
   Energy Efficient Trajectories for an Industrial ABB Robot

   108 citations · 2014
2. 2
   Simultaneous mass estimation and class classification of scrap metals using deep learning

   38 citations · 2022
3. 3
   Reference free method for robot CT imaging geometry estimation

   8 citations · 2022
4. 4
   Investigation of the impact of various robot properties on a twin Robot-CT system

   8 citations · 2020
5. 5
   Geometric qualification for robot CT with flexible trajectories

   7 citations · 2022

Key Collaborators

Contact & Links