Martin Magnusson

Research Interests

My main research is concerned with 3D perception, and efficient and versatile 3D surface representations. I have investigated 3D scan registration and mobile-robot applications such as localisation, loop detection, and semantic analysis of 3D scenes. I have also been investigating methods for using 3D perception in autoloading of piled materials in construction and mining applications.

Since recently, my research also includes mapping methods that go beyond mere geometry, and methods for making use of maps with high uncertainty. I have a particular interest in quantitative quality measures of maps and the methods that are used when constructing them.

I support the international committee for robot arms control and the campaign to stop autonomous military robots.

Selected publications

  • T. P. Kucner, M. Magnusson, E. Schaffernicht, V. M. Hernandez Bennetts and A. Lilienthal. Enabling Flow Awareness for Mobile Robots in Partially Observable Environments. IEEE Robotics and Automation Letters 2017.BibTeX | DiVA  ]
  • Martin Magnusson, Narunas Vaskevicius, Todor Stoyanov, Kaustubh Pathak and Andreas Birk. Beyond points: Evaluating recent 3D scan-matching algorithms. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2015.BibTeX | DiVA Plot appendix ]

  • Martin Magnusson, Tom Duckett and Achim J. Lilienthal. Scan Registration for Autonomous Mining Vehicles Using 3D-NDT. Journal of Field Robotics 2007. [ BibTeX | DiVA  ]
  • Martin Magnusson, Tomasz Piotr Kucner and Achim J. Lilienthal. Quantitative Evaluation of Coarse-To-Fine Loading Strategies for Material Rehandling. Proceedings of the IEEE International Conference on Automation Science and Engineering (CASE) 2015. [ BibTeX | DiVA  ]


I teach Probabilistic Robotics, Computer Graphics, and Imperative Programming. I am also coordinating our Master’s Programme in Robotics and Intelligent Systems.

Brief CV

I currently work as lektor (asst. prof.) in the Mobile Robotics & Olfaction lab of AASS. I am mainly involved in the research projects ILIAD, SmokeBot, and AIR; where I’m working with methods for making use of rough and heterogeneous prior information in SLAM.

I am vice chair of the IEEE/RAS Working Group for the IEEE standard 1873-2015 for representing map data for robot navigation.

Previously I have also been active in the SPENCER project, working with safe and robust localisation and mapping in a crowded environment.

I was leading the ALLO project (with partners Volvo Construction Equipment and NCC) and was also heavily involved in its predecessor ALL-4-eHAM. The target application in both of these projects was autonomous wheel loaders, and the main outcome of the projects includes perception and planning methods for efficient auto-loading of piled materials. 

In 2009, I received a tekn. dr. (Ph. D.) degree from Örebro University. Between 2004 and 2009, I was an industrial graduate student at Örebro University in cooperation with Atlas Copco Rock Drills. The focus of my research as a PhD student was the 3D normal-distributions transform and its applications for scan registration, surface analysis, and loop detection.

I received my undergraduate education in computer science at Uppsala University, interleaved with periods of work and play. I wrote my Master’s thesis on the subject of hierarchical reinforcement learning for balancing a bipedal robot, and received my fil. mag. (M. Sc.) in computer science from Uppsala University in 2004.