“Testing Self Driving Cars with Game Development Tools” by Kaviratna

  • ©Neal Kaviratna



Entry Number: 54


    Testing Self Driving Cars with Game Development Tools



    The Uber Advanced Technologies Group (ATG) aims to bring safe, reliable self-driving transportation to everyone, everywhere; In order to facilitate this mission, a suite of simulation technologies for exercising the self driving vehicle (SDV) needs to be created. These simulations must be scale-able, believable, and human interpretable in order to provide consistent value.

    Here we will cover how ATG leveraged a game engine to meet these demands. Topics covered include: evaluating self driving performance, authoring self driving tests, simulating robot-realistic worlds, and critical lessons learned while building these tools.


    2020 Unreal Engine | The most powerful real-time 3D creation platform. https: //www.unrealengine.com/en-US/. Accessed: 2020-03-22.
    Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. 2017. CARLA: An Open Urban Driving Simulator. In Proceedings of the 1st Annual Conference on Robot Learning. 1–16.



    Thanks to everyone involved in the ATG Simulation effort, both within the simulation org and without. This has been and will continue to be a large multi-team initiative.

    Special thanks to Samuel Gundry, Allison Liemhetcharat, Jessica Smith, Peter Melick, and Michael Knight.

ACM Digital Library Publication:

Overview Page: