English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper introduces the Descriptive Variational Autoencoder (DVAE), anunsupervised and end-to-end trainable neural network for predicting vehicletrajectories that provides partial interpretability. The novel approach isbased on the architecture and objective of common variational autoencoders. Byintroducing expert knowledge within the decoder part of the autoencoder, theencoder learns to extract latent parameters that provide a graspable meaning inhuman terms. Such an interpretable latent space enables the validation byexpert defined rule sets. The evaluation of the DVAE is performed using thepublicly available highD dataset for highway traffic scenarios. In comparisonto a conventional variational autoencoder with equivalent complexity, theproposed model provides a similar prediction accuracy but with the greatadvantage of having an interpretable latent space. For crucial decision makingand assessing trustworthiness of a prediction this property is highlydesirable.

Variational Autoencoder-Based Vehicle Trajectory Prediction with an Interpretable Latent Space