Clustering traffic scenarios and detecting novel scenario types are required for scenario-based testing of autonomous vehicles. These tasks benefit from either good similarity measures or good representations for the traffic scenarios. In this work, an expert-knowledge aided representation learning for traffic scenarios is presented. The latent space so formed is used for successful clustering and novel scenario type detection. Expert-knowledge is used to define objectives that the latent representations of traffic scenarios shall fulfill. It is presented, how the network architecture and loss is designed from these objectives, thereby incorporating expert-knowledge. An automatic mining strategy for traffic scenarios is presented, such that no manual labeling is required. Results show the performance advantage compared to baseline methods. Additionally, extensive analysis of the latent space is performed.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Expert-LaSTS: Expert-Knowledge Guided Latent Space for Traffic Scenarios


    Contributors:


    Publication date :

    2022-06-05


    Size :

    1725790 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    ExAgt: Expert-guided Augmentation for Representation Learning of Traffic Scenarios

    Balasubramanian, Lakshman / Wurst, Jonas / Egolf, Robin et al. | IEEE | 2022


    Expert Knowledge-Guided Travel Demand Estimation: Neuro-Fuzzy Approach

    Seyedabrishami, Seyedehsan / Shafahi, Yousef | Taylor & Francis Verlag | 2011


    Knowledge Engineering For An Air Traffic Expert System

    Galotti, V. P. / Kornecki, A. J. / Air Traffic Control Association | British Library Conference Proceedings | 1991


    Columnist - Scarcity scarcely lasts

    Coates, John | Online Contents | 2003


    Expert System Controlled Vision Guided Welding Workcell

    Lovoi, P. A. | SAE Technical Papers | 1989