Alexander Hermans
Papers
9
Total Citations
278
H-Index
5
About
Alexander Hermans is a robotics researcher whose work sits at the intersection of autonomous mobile systems, human detection, and multi-modal perception. He is perhaps best known for his contributions to the STRANDS Project, a landmark long-term autonomy initiative that demonstrated how service robots can operate reliably in real-world everyday environments — a milestone that has attracted nearly 200 citations and remains a touchstone in the field. Much of Hermans' subsequent research has focused on the challenging problem of person detection using 2D and 3D LiDAR range data, addressing critical limitations in sensor coverage, annotated training data, and cross-domain generalization for mobile robots navigating human-populated spaces. His pioneering DROW detector introduced deep learning to 2D range-based object detection, while later works explored self-supervised training pipelines and modality gap analysis to make detectors more robust and transferable. More recently, Hermans has expanded into 3D object detection with RGB-D fusion and anomaly detection for safe autonomous navigation, reflecting a broadening research vision. With publications spanning top robotics venues and a steadily growing citation record, his work makes meaningful contributions to building robots that perceive and operate safely alongside people in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1The STRANDS Project: Long-Term Autonomy in Everyday Environments196 citations · 2017
- 2Deep Person Detection in Two-Dimensional Range Data32 citations · 2018
- 32D vs. 3D LiDAR-based Person Detection on Mobile Robots17 citations · 2022
- 4Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera12 citations · 2021
- 5
- 6Deep Person Detection in 2D Range Data5 citations · 2018
- 7RGB-D Cube R-CNN: 3D Object Detection with Selective Modality Dropout4 citations · 2024
- 8OoDIS: Anomaly Instance Segmentation and Detection Benchmark2 citations · 2025
- 9