Oxford RobotCar Dataset

Real-time Kinematic Ground Truth

2020-02-20T00:00:00+00:00

We are pleased to release the ground truth reference data towards a planned challenging long-term localisation and mapping Oxford RobotCar Long-Term Autonomy Benchmark.

The Oxford Radar RobotCar Dataset

2019-09-02T00:00:00+01:00

We are pleased to announce the release of the Oxford Radar RobotCar Dataset, a radar extension to the Oxford RobotCar Dataset.

This dataset provides Millimetre-Wave radar data, dual velodyne lidars, and optimised ground truth odometry for 280 km of driving around Oxford, UK (in addition to all sensors in the original Oxford RobotCar Dataset). We intend that this dataset will help accelerate research with this interesting sensor which is robust to challenging conditions that may trouble other modalities.

For more information and to sign up to use the dataset, please visit Oxford Radar RobotCar Dataset. Please also take a look at the paper which provides full documentation for this dataset: The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset.

RobotCar Long-Term Autonomy Benchmark

2017-06-02T00:00:00+01:00

The initial release of the RobotCar Dataset consisted purely of raw data, giving researchers a large collection of data with a wide range of variation in illumination, weather, dynamic objects, seasonal changes, roadworks and building construction.

Building on that release, today at the ICRA Workshop on Robotics and Vehicular Technologies for Self-driving cars, we announced that we will soon be releasing a localisation benchmarking service, based on RTK-corrected GPS/INS trajectories.

We plan to offer a subset of the corrected RTK solutions for a small number of traversals, and withhold the remaining ground truth in order to provide an online benchmarking service.

By providing a benchmark where researchers can quantitatively evaluate and compare localisation and mapping approaches on a challenging large-scale dataset, we hope to accelerate development of long-term autonomy for future autonomous vehicles.

Please enter your email address below if you wish to be notified when the benchmark becomes available.

Python tools added to SDK

2017-02-01T00:00:00+00:00

We have added some Python tools to the SDK. These tools will enable researchers using Python to get started on using the dataset more quickly.

The Python tools mirror those provided for MATLAB, including functions for:

loading, rectifying, and displaying images;
building pointclouds from LIDAR scans; and
projecting LIDAR points into images.

To download the tools, please visit the Github repository.

Missing Mono Images

2016-12-09T00:00:00+00:00

It has come to our attention that some archives of mono images were empty. We have now regenerated these archives. If you have downloaded a dataset that has missing monocular images, please download them again now.

2015/11/13

2015-11-13T00:00:00+00:00

2015/11/12

2015-11-12T00:00:00+00:00

2015/11/12

2015-11-12T00:00:00+00:00

2015/11/11

2015-11-11T00:00:00+00:00

2015/11/11

2015-11-11T00:00:00+00:00