Driverless Car Challenges

Oxbotica is the nominated provider of the autonomous control system for two of the UK’s three Driverless Car Challenges taking place over the next few years in Milton Keynes, Coventry, Greenwich and Bristol.

In the GATEway project in Greenwich, London we are providing our Selenium autonomous control system to power 8 shuttle vehicles developed by Westfield Cars and Heathrow Airport, which will be used by members of the public in a 6 month demonstration starting early 2017.  We are also providing our Caesium shuttle management system – a cloud based service that will schedule and co-ordinate our small fleet of autonomous vehicles, enabling smartphone booking, route optimisation and data exchange between the vehicles without human intervention.

Selenium will also be used in the UK Autodrive project, which will see 40 self-driving pods carrying members of the public on routes around Milton Keynes city centre in 2017, linking in to key transportation hubs and car parks and travelling through pedestrianised areas.   Oxbotica is a pivotal contributor to UK Autodrive and will provide the entire autonomous control system and sensor sub-systems that enable real-world operation of driverless vehicles in urban and pedestrianised areas around Milton Keynes.

3D Mapping of Urban Environments

A foundation step for autonomy is the development of a map of the target environment using our patented integrated laser and vision based, GPS-free approach that produces 3D models of large-scale environments quickly, cheaply and robustly.  These highly accurate maps enable vehicle localisation, infrastructure-free navigation, scene perception and intelligent self-driving vehicles.

The same 3D maps are the foundation blocks for multiple applications ranging from Smart City planning, survey, infrastructure management, asset detection/management and low cost localisation for devices ranging from smartphones to cars, buses and trains.

 3D Object Detection

Oxbotica has developed technology for automatically detecting and removing 3D objects from point clouds. This video demonstrates how this might be used for the detection of cars in an outdoor scene with the ultimate aim of removing non-permanent features.