Mobile Robotics Group

  • Robotcar (c) John Cairns
  • Robotcar interface
  • Wildcat on Begbroke approach
  • LEAFS & Wildcat parked
  • NABU montage
  • IW_D1_135 cropped
  • DSC02079 cropped
  • Beaumont Street
  • 21-Oct-2014 cropped b
  • IMG_1854 croped

How do you make a machine smart enough to navigate independently?

This question is at the heart of MRG’s research. Our goal is life-long infrastructure free navigation. We are developing future-proof mltechnology, which enables robots to navigate without modifying the environment and without depending on bespoke hardware, such as GPS.

Our core technology can be exploited in many different domains and many different conditions.

In 2014 a spin-out company called Oxbotica was launched to drive commercialisation and cross domain impact  of our work.

MRG Research Themes

Model-Free Tracking


Perception gives robots situational awareness. Our latest research Detection of Cars, Pedestrians and Bicyclists from
Read More


Much of our localisation, perception and mapping work uses multiple sensors. Sometimes we are talking
Read More
Bodleian Broad Street


The Mapping theme is all about building useful representations of workspaces. Sometimes these maps are used by our robots to localise ...
Read More


Localisation answers the all important: "Where am I?" This is a fundamental requirement of mobile robots. To be useful mobile ...
Read More



24th June 2015: UK-RAS Network Launch


The EPSRC EPSRC UK-Robotics and Autonomous Systems Network (UK-RAS Network) is dedicated to robotics innovation across the UK, with a mission to provide academic leadership in Robotics and Autonomous Systems (RAS), expand collaboration with industry, and integrate and coordinate activities at eight Engineering and Physical Sciences Research Council (EPSRC) funded RAS capital facilities and Centres for Doctoral Training (CDTs) across the country.

For more information please visit the UK-RAS Network website.

June 2015

 MRG is hiring! Please follow this link for more information.

May 2015

Congratulations to Chris, Winston and Paul for winning the Best Robotic Vision Paper Award! Awarded for the best paper relating to vision presented at the International Conference on Robotics and Automation (ICRA 2015). The basis for judging the paper titled Work Smart, Not Hard: Recalling Relevant Experiences for Vast-Scale but Time-Constrained Localisation were: technical merit, originality, potential impact on the field, clarity of the written paper, and quality of the oral or other presentation.





Department of Engineering Science, University of Oxford