Benjamin Suger
Papers
7
Total Citations
189
H-Index
7
About
Benjamin Suger’s research lies at the intersection of autonomous navigation, mobile robotics, and environmental perception, with a focus on enabling safe, long-term operation in complex outdoor settings. His most influential work introduces a semi-supervised learning approach for traversability analysis using 3D-LiDAR data, a method that has garnered over 100 citations for its ability to reliably distinguish obstacles from traversable ground—a critical prerequisite for truly autonomous systems. Suger has also advanced global navigation by leveraging OpenStreetMap for outer-urban routes, addressing map inaccuracies and positional uncertainty. In the realm of localization, he has made notable contributions to vision-based Markov localization, enabling robust performance across substantial perceptual changes such as seasonal variation, and has developed terrain-adaptive obstacle detection for real-time, resource-constrained platforms. His work on sparse scan-based map representations further tackles memory efficiency in robot localization. With a publication record spanning top venues and a clear focus on practical, deployable solutions, Suger’s research has shaped how mobile robots perceive, navigate, and adapt to challenging real-world environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2Global outer-urban navigation with OpenStreetMap29 citations · 2017
- 3Vision-based Markov localization for long-term autonomy16 citations · 2016
- 4Vision-based Markov localization across large perceptual changes13 citations · 2015
- 5Terrain-adaptive obstacle detection13 citations · 2016
- 6Robot localization with sparse scan-based maps9 citations · 2017
- 7