Papers
2
Total Citations
33
H-Index
2
About
Marius Moosmann is a robotics researcher specializing in intelligent manipulation and industrial automation, with a core focus on random bin picking—a notoriously difficult challenge in manufacturing. His work addresses the critical problem of workpiece entanglement, where geometrically complex parts become interlocked, causing robotic grippers to fail. Moosmann’s key contributions lie in applying machine learning and deep neural networks to detect and avoid these entanglements, significantly improving the robustness and reliability of automated picking systems. His most cited paper, "Increasing the Robustness of Random Bin Picking by Avoiding Grasps of Entangled Workpieces" (2020, 24 citations), introduces a novel approach that predicts entanglement-prone configurations before a grasp is attempted. Building on this, his 2021 work, "Using Deep Neural Networks to Separate Entangled Workpieces in Random Bin Picking" (9 citations), advances the field by enabling robots to actively disentangle parts. Though early in his career, Moosmann’s research directly addresses a practical bottleneck in Industry 4.0, offering scalable solutions that reduce downtime and waste in high-volume manufacturing. His work is essential reading for engineers and researchers seeking to bridge the gap between deep learning and real-world robotic dexterity.
Research Focus
Key Achievements
Top Papers
- 1
- 2