Max Robotics — Global Service Robot Directory + US Certification

About

Felix Spenrath’s research sits at the intersection of industrial robotics, machine learning, and manufacturing automation, with a focus on solving two critical challenges: robust random bin picking and intelligent welding process planning. His most significant contribution lies in addressing the problem of entangled workpieces in bin picking—a notoriously difficult issue where complex part geometries cause failed grasps. Spenrath pioneered machine learning approaches to detect and avoid these entanglements, with his 2020 paper “Increasing the Robustness of Random Bin Picking by Avoiding Grasps of Entangled Workpieces” accumulating 24 citations and establishing a new paradigm for reliable robotic grasping. He further advanced this work by applying deep neural networks to actively separate entangled parts, while also developing heuristic grasp planning methods that use neural networks to improve collision-free grip determination. In welding automation, Spenrath introduced an adaptive gap model for robotic MAG welding that dynamically adjusts parameters to compensate for part misalignment, enabling more precise and flexible manufacturing. His research, spanning from 2017 to 2021, has garnered over 50 citations and demonstrates a clear trajectory from statistical analysis to deep learning solutions, making him a notable contributor to the practical deployment of intelligent robotics in industrial settings.