Tim Pfeifer
Papers
3
Total Citations
79
H-Index
3
About
Tim Pfeifer is a leading researcher in robust state estimation and sensor fusion for autonomous robotics. His work directly tackles the critical challenge of making robotic perception reliable in unpredictable, real-world environments. Pfeifer’s major contribution is the development of parameter-free, self-tuning algorithms that automatically adapt to sensor failures and measurement outliers. His seminal paper, "Robust Sensor Fusion with Self-Tuning Mixture Models" (2018, 38 citations), introduces a novel approach that eliminates the need for extensive manual tuning of error models, a persistent bottleneck in the field. This is complemented by his work on "Dynamic Covariance Estimation" (2017, 35 citations), which provides a mathematically elegant solution to prevent divergence in simultaneous localization and mapping (SLAM) systems. Beyond theory, Pfeifer has proven his methods in practice, notably as part of the team that competed in the DLR SpaceBot Cup 2015, where two autonomous robots successfully explored and mapped a challenging lunar-like terrain within a strict 60-minute window. His research is essential reading for anyone building robust, field-deployable robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Robust Sensor Fusion with Self-Tuning Mixture Models38 citations · 2018
- 2
- 3