Scholar
Andrew Davison
Google Scholar ID: A0ae1agAAAAJ
Professor of Robot Vision, Department of Computing, Imperial College London
Citations & Impact
Citations
28,990
H-index
61
i10-index
124
Publications
20
Co-authors
154
list available
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Developed the breakthrough MonoSLAM algorithm in 2003, enabling real-time monocular SLAM and influencing robotics, VR, and AR tracking
- Authored influential discussion papers: 'FutureMapping: The Computational Structure of Spatial AI Systems' (2018) and 'FutureMapping 2: Gaussian Belief Propagation for Spatial AI' (2019)
- Supervised numerous PhD students, including:
- – 2010: Dr. Margarita Chli, 'Applying Information Theory to Efficient SLAM', now at University of Cyprus
- – 2012: Dr. Steven Lovegrove, 'Parametric Dense Visual SLAM', now at Meta Reality Labs, USA
- – 2012: Dr. Gerardo Carrera, 'Robot SLAM and Navigation with Multi-Camera Computer Vision', now at Grupo Financiero Banorte, Mexico
- – 2012: Dr. Hauke Strasdat, 'Local Accuracy and Global Consistency for Efficient Visual SLAM', now at Meta Reality Labs, USA
- – 2013: Dr. Ankur Handa (incomplete information)
Background
- Professor of Robot Vision at the Department of Computing, Imperial College London
- Leads the Dyson Robotics Laboratory at Imperial College, focusing on vision and AI for next-generation home robotics
- Leads the Robot Vision Research Group
- Primary research area: vision-based SLAM (Simultaneous Localisation and Mapping)
- Pioneered vision-based SLAM since the mid-1990s; introduced the MonoSLAM algorithm in 2003—the first real-time, drift-free, long-term SLAM from a single camera
- Current research focuses on improving dynamics, scale, detail, efficiency, and semantic understanding in real-time 3D vision
- Proposes the concept of 'Spatial AI', viewing SLAM as evolving into a broader computational framework
