In the developement of safe intelligent vehicles, intentions of other road users need to be estimated in order to plan a safe and convenient trajectory. The present work tries to approach the answer to the question of how a prediction could be assessed holistically using the example of pedestrian prediction. Recently used metrics are compared on a state of the art (SOTA) prediction method. A good prediction does not only have to verify itself on a limited data set, so machine versus human pedestrian prediction are compared. A study with test persons points out the similarity of human predictions compared to SOTA prediction. However, further research is required since we cannot propose a holistic metric that answers the question in the title, yet.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    What Does a Good Prediction Look Like?


    Contributors:


    Publication date :

    2019-10-01


    Size :

    1486733 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A typical Adelaide drive: what does it look like?

    Zito, R. / Australasian Transport Research Forum | British Library Conference Proceedings | 2004


    COMPLETE DESIGN PANEL WHAT DOES THE 1955 TRANSPORT LOOK LIKE?

    JOHNSON, CLARENCE L. | SAE Technical Papers | 1948


    A System Investigation: What Does Your ``Electrical DNA'' Look Like?

    American Public Transportation Association | British Library Conference Proceedings | 2007



    What Will Sunsats Look Like?

    Ph.D. Flournoy, Don M. | Springer Verlag | 2012