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

Accurate and robust trajectory predictions of road users are needed to enablesafe automated driving. To do this, machine learning models are often used,which can show erratic behavior when presented with previously unseen inputs.In this work, two environment-aware models (MotionCNN and MultiPath++) and twocommon baselines (Constant Velocity and an LSTM) are benchmarked for robustnessagainst various perturbations that simulate functional insufficiencies observedduring model deployment in a vehicle: unavailability of road information, latedetections, and noise. Results show significant performance degradation underthe presence of these perturbations, with errors increasing up to +1444.8\% incommonly used trajectory prediction evaluation metrics. Training the modelswith similar perturbations effectively reduces performance degradation, witherror increases of up to +87.5\%. We argue that despite being an effectivemitigation strategy, data augmentation through perturbations during trainingdoes not guarantee robustness towards unforeseen perturbations, sinceidentification of all possible on-road complications is unfeasible.Furthermore, degrading the inputs sometimes leads to more accurate predictions,suggesting that the models are unable to learn the true relationships betweenthe different elements in the data.

Robustness Benchmark of Road User Trajectory Prediction Models for Automated Driving