Naturalistic Intersection Driving Dataset

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 data has been used to estimate the future intention of drivers through the intersection by building probabilistic models of the intersection.

Publications

 

Publications using this dataset include:

  • A. Bender, J. R. Ward, S. Worrall, and E. M. Nebot, “Predicting Driver Intent from Models of Naturalistic Driving,” in Intelligent Transportation Systems (ITSC), 2015 IEEE 18th International Conference on, 2015, pp. 1609-1615. doi:10.1109/ITSC.2015.262
    [BibTeX]
    @InProceedings{Bender2015b,
    Title = {Predicting Driver Intent from Models of Naturalistic Driving},
    Author = {Bender, Asher and Ward, James R. and Worrall, Stewart and Nebot, Eduardo M.},
    Booktitle = {Intelligent Transportation Systems (ITSC), 2015 IEEE 18th International Conference on},
    Year = {2015},
    Month = {Sept},
    Pages = {1609-1615},
    Doi = {10.1109/ITSC.2015.262},
    Keywords = {Computational modeling;Data models;Hidden Markov models;Roads;Training;Trajectory;Vehicles}
    }

 

Download