Patrick Pfreundschuh

ETH Zurich, École Polytechnique Fédérale de Lausanne

Papers

7

Total Citations

126

H-Index

6

About

Patrick Pfreundschuh is a leading roboticist whose research centers on perception, localization, and autonomy in complex, dynamic environments. He is best known for his pivotal role on Team CERBERUS, which won the prestigious DARPA Subterranean Challenge in 2021—a landmark achievement in multi-robot underground exploration. His major contributions include Dynablox (67 citations), a real-time mapping-based system for detecting diverse dynamic objects, and TULIP (18 citations), a transformer-based method for upsampling sparse LiDAR point clouds. Pfreundschuh has also advanced robust state estimation, developing a baro-radar-inertial odometry M-estimator for multicopter navigation in challenging urban and forest settings, and has analyzed degeneracy-aware point cloud registration for reliable SLAM in the wild. His work on dynamic-object-aware LiDAR SLAM, which automatically generates training data, further underscores his commitment to deploying robots in real-world, unstructured scenarios. With over 120 total citations and a string of recent high-impact publications, Pfreundschuh is shaping the future of autonomous navigation in environments where robots must perceive and react to a constantly changing world.

Research Focus

Key Achievements

6
H-Index
7
Papers
126
Total Citations
18
Avg Citations/Paper
🏆 Most Cited Paper
Dynablox: Real-Time Detection of Diverse Dynamic Objects in Complex Environments
67 citations · 2023
📈 Most Prolific Year: 2024 (3 Papers)
🤝 Key Collaborators: 51
🏛 Institutions: ETH Zurich, École Polytechnique Fédérale de Lausanne

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6
  7. 7

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago