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

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...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE Intelligent Vehicles Symposium (IV) pp. 484 - 491
Main Authors Wurst, Jonas, Balasubramanian, Lakshman, Botsch, Michael, Utschick, Wolfgang
Format Conference Proceeding
LanguageEnglish
Published IEEE 05.06.2022
Subjects
Clustering
Deep Learning
Design methodology
Feature extraction
Labeling
Manuals
Network architecture
Novelty Detection
Representation learning
Scenario-Based Testing
Stability analysis
Online AccessGet full text

Cover

More Information
Summary: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.
DOI:10.1109/IV51971.2022.9827187