Skip to main content

Team from Oxford Robotics Institute collects epic off-road driving data for the Sense-Assess-eXplain project

Building trust in autonomous vehicles in challenging real-world driving scenarios

JLR driving through water in scotland.

In March, a team from the Oxford Robotics Institute visited the Scottish Highlands and collected a week of epic off-road driving data, as part of the Sense-Assess-eXplain (SAX) project.

Understanding the decisions taken by an autonomous machine is key to building public trust in robotics and autonomous systems (RAS). This project will design, develop, and demonstrate fundamental AI technologies in real-world applications to address this issue of explainability and help build vehicles that can sense and fully understand their environment, assess their own capabilities and provide causal explanations for their own decisions.

The team collected data representing challenging off-road driving conditions and difficult weather in unlikely driving scenarios, during the day and at night, over several kilometres, to help develop techniques in motion estimation, localisation, terrain analysis, scene understanding and explainability.

The data collection will be released along with data from a range of driving conditions from motorways to dense urban driving.