Hordur Johannsson

About

Hordur Johannsson is a robotics researcher whose work sits at the intersection of simultaneous localization and mapping (SLAM), visual odometry, and autonomous navigation. Based primarily at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), Johannsson has made significant contributions to real-time dense RGB-D mapping and robust camera tracking, most notably through extensions to the Kintinuous algorithm that enabled spatially extended, GPU-accelerated 3D reconstruction — work that has garnered over 321 citations. His research on autonomous underwater vehicles for ship hull inspection (251 citations) demonstrated sophisticated integration of perception, planning, and navigation in one of robotics' most demanding environments. Johannsson has also advanced long-term mapping in dynamic environments through pose graph SLAM techniques (151 citations), addressing the critical challenge of maintaining accurate maps as the world changes over time. His contributions to sensor fusion for building-scale indoor mapping and Monte Carlo localization using RGB-D cameras further reflect his breadth across mobile robotics. The MIT Stata Center dataset, which he helped create, has become a valuable benchmark resource for the research community. Collectively, his work addresses foundational challenges in building robots that navigate and perceive the world robustly over extended durations.

Research Focus

Key Achievements

Top Papers

1. 1
   Robust real-time visual odometry for dense RGB-D mapping

   321 citations · 2013
2. 2
   Advanced perception, navigation and planning for autonomous in-water ship hull inspection

   251 citations · 2012
3. 3
   Dynamic pose graph SLAM: Long-term mapping in low dynamic environments

   151 citations · 2012
4. 4
   Efficient scene simulation for robust monte carlo localization using an RGB-D camera

   78 citations · 2012
5. 5
   The MIT Stata Center dataset

   58 citations · 2013
6. 6
   Sensor fusion for flexible human-portable building-scale mapping

   57 citations · 2012
7. 7
   Robust Tracking for Real-Time Dense RGB-D Mapping with Kintinuous

   47 citations · 2012
8. 8
   Robust Tracking for Real-Time Dense RGB-D Mapping with Kintinuous : Computer Science and Artificial Intelligence LaboratoryTechnical Report MIT-CSAIL-TR-2012-031

   9 citations · 2012
9. 9
   Mapping the MIT Stata Center: Large-scale Integrated Visual and RGB-D SLAM

   5 citations · 2012
10. 10
    Toward lifelong visual localization and mapping

    5 citations · 2013

Key Collaborators

Contact & Links