Deep Representation Learning and Clustering of Traffic Scenarios

Determining the traffic scenario space is a major challenge for the homologation and coverage assessment of automated driving functions. In contrast to current approaches that are mainly scenario-based and rely on expert knowledge, we introduce two data driven autoencoding models that learn a latent...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Harmening, Nick, Marin Biloš, Günnemann, Stephan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 15.07.2020
Subjects
Clustering
Homology
Permutations
Representations
Online AccessGet full text

Cover

More Information
Summary:Determining the traffic scenario space is a major challenge for the homologation and coverage assessment of automated driving functions. In contrast to current approaches that are mainly scenario-based and rely on expert knowledge, we introduce two data driven autoencoding models that learn a latent representation of traffic scenes. First is a CNN based spatio-temporal model that autoencodes a grid of traffic participants' positions. Secondly, we develop a pure temporal RNN based model that auto-encodes a sequence of sets. To handle the unordered set data, we had to incorporate the permutation invariance property. Finally, we show how the latent scenario embeddings can be used for clustering traffic scenarios and similarity retrieval.
ISSN:2331-8422