The RoboBus dataset collected on a cross-border public transport route has been released for download on GitHub.
The dataset contains approximately 8 hours of driving data divided into 15 trips that have been recorded over 4 days. It includes about 1.7 million anonymized images captured by two road-facing cameras, GNSS traces, data from a 9-axis IMU, and information directly retrieved from the CAN interface of the vehicle including speed, steering angle and position of the accelerator/brake pedals. We use an end-to-end autonomous driving approach that relies on imitation learning as use case example for the dataset.
The paper describing the dataset has been presented at the PerVehicle Online Workshop in March.
This work has been financially supported by the EU INTERREG GR Terminal project. The authors would also like to thank Voyages Emile Weber Luxembourg for their support and for granting us access to their bus.