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

The ability to predict multiple possible future positions of the ego-vehiclegiven the surrounding context while also estimating their probabilities is keyto safe autonomous driving. Most of the current state-of-the-art Deep Learningapproaches are trained on trajectory data to achieve this task. Howevertrajectory data captured by sensor systems is highly imbalanced, since by farmost of the trajectories follow straight lines with an approximately constantvelocity. This poses a huge challenge for the task of predicting futurepositions, which is inherently a regression problem. Current state-of-the-artapproaches alleviate this problem only by major preprocessing of the trainingdata, e.g. resampling, clustering into anchors etc. In this paper we propose anapproach which reformulates the prediction problem as a classification task,allowing for powerful tools, e.g. focal loss, to combat the imbalance. To thisend we design a generative probabilistic model consisting of a deep neuralnetwork with a Mixture of Gaussian head. A smart choice of the latent variableallows for the reformulation of the log-likelihood function as a combination ofa classification problem and a much simplified regression problem. The outputof our model is an estimate of the probability density function of futurepositions, hence allowing for prediction of multiple possible positions whilealso estimating their probabilities. The proposed approach can easilyincorporate context information and does not require any preprocessing of thedata.

PrognoseNet: A Generative Probabilistic Framework for Multimodal Position Prediction given Context Information