Deep Representation Learning and Clustering of Traffic Scenarios

07/15/2020
by   Nick Harmening, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/19/2022

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

Clustering traffic scenarios and detecting novel scenario types are requ...
research
08/16/2022

A Latent Feature Analysis-based Approach for Spatio-Temporal Traffic Data Recovery

Missing data is an inevitable and common problem in data-driven intellig...
research
11/24/2022

Self Supervised Clustering of Traffic Scenes using Graph Representations

Examining graphs for similarity is a well-known challenge, but one that ...
research
11/24/2022

Fingerprint of a Traffic Scene: an Approach for a Generic and Independent Scene Assessment

A major challenge in the safety assessment of automated vehicles is to e...
research
05/05/2021

Novelty Detection and Analysis of Traffic Scenario Infrastructures in the Latent Space of a Vision Transformer-Based Triplet Autoencoder

Detecting unknown and untested scenarios is crucial for scenario-based t...

Please sign up or login with your details

Forgot password? Click here to reset