/Oxford Robotics Institute

About Oxford Robotics Institute

This author has not yet filled in any details.
So far Oxford Robotics Institute has created 65 blog entries.

Digital Railways project update

We have just completed the latest InnovateUK project review on our Digital Railways project, which sees our technology deployed on trains in order to provide robust and scalable detection and mapping of railway assets. This project brings together a large part of MRG technology from mapping and localisation at high speeds to calibration, active learning and object [...]

Self-driving pods win national innovation award

A ground-breaking research programme which will trial three self-driving vehicles on pedestrianised areas of Milton Keynes has won this year’s Society of Motor Manufacturers and Traders (SMMT) Automotive Award for Innovation. The LUTZ Pathfinder project saw off competition from four other shortlisted contenders to pick up the prestigious trophy at the 99th SMMT Annual Dinner. [...]

Best Paper Award – ICCV 2015

Congratulations to Geoff Pascoe, Will Maddern and Paul Newman on winning the Best Paper Award for their paper Direct visual location and calibration for road vehicles in changing city environments at 3rd Workshop on Computer Vision for Road Scene Understanding and Autonomous Driving, ICCV 2015.

EPSRC Press Release

The UK’s ability to develop and exploit the vast potential of Robotics and Autonomous Systems was given a major boost today with the formal launch of The EPSRC UK Robotics and Autonomous Systems Network (UK-RAS Network). The Network will bring together the UK’s core academic capabilities in robotics innovation under national coordination for the first time and encourage academic and industry collaborations [...]

Building, Curating, and Querying Large-scale Data Repositories for Field Robotics Applications

Abstract—Field robotics applications have some unique and unusual data requirements -- the curating, organisation and management of which are often overlooked. An emerging theme is the use of large corpora of spatiotemporally indexed sensor data which must be searched and leveraged both offline and online. Increasingly we build systems that must never stop learning. Every [...]

From Dusk till Dawn: Localisation at Night using Artificial Light Sources

Abstract—This paper is about localising at night in urban environments using vision. Despite it being dark exactly half of the time, surprisingly little attention has been given to this problem. A defining aspect of night-time urban scenes is the presence and effect of artificial lighting -- be that in the form of street or interior lighting through windows. By [...]

Work Smart, Not Hard: Recalling Relevant Experiences for Vast-Scale but Time-Constrained Localisation

This paper is about life-long vast-scale localisation in spite of changes in weather, lighting and scene structure. Building upon our previous work in Experience-based Navigation, we continually grow and curate a visual map of the world that explicitly supports multiple representations of the same place. We refer to these representations as experiences, where a single [...]

Jamie Frost

MRG Publications [bibtex author=Frost|Jamie group=year group_order=desc file=]

Gabe Sibley

MRG Publications [bibtex author=Sibley|Gabe group=year group_order=desc file=]

Liz Murphy

MRG Publications [bibtex author=Murphy|Liz group=year group_order=desc file=]