Sökning: "autonomous driving scenario representation"

Hittade 3 uppsatser innehållade orden autonomous driving scenario representation.

  1. 1. Scenario Generation For Vehicles Using Deep Learning

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Jay Patel; [2022]
    Nyckelord :Scenario generation; Mixture Density Network; Gaussian Mixture Model; Autonomous driving; Semantic Graph Network; Scenariogenerering; Mixture Density Network; Gaussian Mixture Model; Autonom körning; Semantic Graph Network;

    Sammanfattning : In autonomous driving, scenario generation can play a critical role when it comes to the verification of the autonomous driving software. Since uncertainty is a major component in driving, there cannot be just one right answer to a prediction for the trajectory or the behaviour, and it becomes important to account for and model that uncertainty. LÄS MER

  2. 2. Development of Swarm Traffic Algorithms : Road detection within an ellipse

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Massimiliano Dal Mas; [2021]
    Nyckelord :OpenSCENARIO; autonomous driving scenario representation; simulation infrastructure; automated driving systems; self-driving car project;

    Sammanfattning : The latest trends in autonomous vehicles research gave rise to the needs for specific tools to validate and test such systems. The estimations state that to consider an autonomous vehicle statistically safe, it should drive for thousands of kilometres using traditional validation methods. This process would take a long time. LÄS MER

  3. 3. Building verification database and extracting critical scenarios for self-driving car testing on virtual platform

    Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)

    Författare :Kaige Tan; [2019]
    Nyckelord :;

    Sammanfattning : This degree project, conducted at Volvo Cars, investigates a method about how to build a test database for an Autonomous Driving (AD) function on a virtual platform and how to extract critical scenarios from the test database to finish test cases reduction through optimization. The virtual platform under study is the model-in-the-loop (MIL) based Simulation Platform Active Safety (SPAS) environment and the optimization tool being used is modeFrontier. LÄS MER