Description

This is a rich dataset derived from a vehicle driving around urban streets around the Australian Centre for Field Robotics in Sydney. The data were collected by a system fusing GPS and dead reckoning information from gyroscopes and odometry, at a resolution of 10 hertz.

This dataset has been used to examine prediction of vehicle collision likelihood under sensor uncertainty.

Publications

Publications using this dataset include:

  • J. Ward, G. Agamennoni, S. Worrall, and E. Nebot, “Vehicle collision probability calculation for general traffic scenarios under uncertainty,” in Intelligent Vehicles Symposium Proceedings, 2014 IEEE, 2014, pp. 986-992. doi:10.1109/IVS.2014.6856430
    [BibTeX] [Abstract]

    Vehicle-to-vehicle (V2V) communication systems allow vehicles to share state information with one another to improve safety and efficiency of transportation networks. One of the key applications of such a system is in the prediction and avoidance of collisions between vehicles. If a method to do this is to succeed it must be robust to measurement uncertainty. The method should also be general enough that it does not rely on constraints on vehicle motion for the accuracy of its predictions. It should work for all interactions between vehicles and not just a select subset. This paper presents a method for collision probability calculation that addresses these problems.

    @InProceedings{ward2014vehicle,
    Title = {Vehicle collision probability calculation for general traffic scenarios under uncertainty},
    Author = {Ward, J. and Agamennoni, G. and Worrall, S. and Nebot, E.},
    Booktitle = {Intelligent Vehicles Symposium Proceedings, 2014 IEEE},
    Year = {2014},
    Month = {June},
    Pages = {986-992},
    Abstract = {Vehicle-to-vehicle (V2V) communication systems allow vehicles to share state information with one another to improve safety and efficiency of transportation networks. One of the key applications of such a system is in the prediction and avoidance of collisions between vehicles. If a method to do this is to succeed it must be robust to measurement uncertainty. The method should also be general enough that it does not rely on constraints on vehicle motion for the accuracy of its predictions. It should work for all interactions between vehicles and not just a select subset. This paper presents a method for collision probability calculation that addresses these problems.},
    Doi = {10.1109/IVS.2014.6856430},
    Keywords = {mobile communication;road safety;road traffic;traffic engineering computing;V2V;general traffic scenarios;measurement uncertainty;transportation network efficiency;transportation network safety;vehicle collision probability calculation;vehicle-to-vehicle communication systems;Mathematical model;Safety;Support vector machines;Trajectory;Uncertainty;Vectors;Vehicles}
    }

 

Download