Davide Scaramuzza

About

Davide Scaramuzza is a pioneering researcher in robotics and computer vision, whose work spans autonomous navigation, simultaneous localization and mapping (SLAM), visual odometry, and autonomous aerial vehicles. Based at the University of Zurich, he has fundamentally shaped how robots perceive and navigate their environments, particularly in GPS-denied and unstructured settings. His highly influential tutorial series on visual odometry (2011–2012, over 2,000 combined citations) established foundational understanding of ego-motion estimation from camera input, becoming essential reading for robotics students worldwide. His comprehensive survey on SLAM (2016, 3,158 citations) stands as one of the field's most referenced works, charting three decades of progress and future challenges in robust robot perception. Scaramuzza has also driven the frontier of autonomous drone research, demonstrating deep reinforcement learning systems capable of champion-level drone racing (2023, 562 citations) and pioneering urban drone navigation through his DroNet framework. His contributions to event-based vision sensing and micro aerial vehicle navigation further reflect his commitment to pushing beyond conventional sensing paradigms. Collectively, his research portfolio has accumulated thousands of citations, reflecting extraordinary influence on robotics, autonomous systems, and machine learning communities globally.

Research Focus

Key Achievements

Top Papers

1. 1
   Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age

   3,158 citations · 2016
2. 2
   Visual Odometry [Tutorial]

   1,485 citations · 2011
3. 3
   A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots

   694 citations · 2015
4. 4
   Event-Based Vision: A Survey

   633 citations · 2020
5. 5
   Visual Odometry : Part II: Matching, Robustness, Optimization, and Applications

   606 citations · 2012
6. 6
   Champion-level drone racing using deep reinforcement learning

   562 citations · 2023
7. 7
   DroNet: Learning to Fly by Driving

   502 citations · 2018
8. 8
   A Benchmark Comparison of Monocular Visual-Inertial Odometry Algorithms for Flying Robots

   395 citations · 2018
9. 9
   The current state and future outlook of rescue robotics

   361 citations · 2019
10. 10
    Vision-Controlled Micro Flying Robots: From System Design to Autonomous Navigation and Mapping in GPS-Denied Environments

    297 citations · 2014

Key Collaborators

Contact & Links