Michael Fiegert
Papers
4
Total Citations
30
H-Index
3
About
Michael Fiegert’s research lies at the intersection of robotic perception, scene analysis, and automated system configuration, with a focus on making service and industrial robots more capable and easier to deploy. His most cited work introduces a probabilistic rule set joint state update, an efficient approximation for high-dimensional state estimation in multi-object scene analysis—a critical capability for service robots tasked with identifying and localizing objects in cluttered environments. This work, with 12 citations, addresses the computational challenge of tracking multiple objects simultaneously. Fiegert also made significant contributions to industrial automation through his work on virtual training and commissioning of bin picking systems (9 citations), where he developed methods using synthetic sensor data and simulation to reduce the costly setup and tuning efforts typically required for handling unsorted parts. His research further extends to the automatic configuration of perception pipelines (3 citations), tackling the complex engineering problem of optimizing pipeline structure and parameterization. Through these contributions, Fiegert has advanced both the theoretical foundations and practical deployment of robotic perception systems, enabling more robust and adaptable automation solutions.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Scene Analysis for Service Robots6 citations · 2012
- 4