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

We introduce a motion forecasting (behavior prediction) method that meets thelatency requirements for autonomous driving in dense urban environments withoutsacrificing accuracy. A whole-scene sparse input representation allows StopNetto scale to predicting trajectories for hundreds of road agents with reliablelatency. In addition to predicting trajectories, our scene encoder lends itselfto predicting whole-scene probabilistic occupancy grids, a complementary outputrepresentation suitable for busy urban environments. Occupancy grids allow theAV to reason collectively about the behavior of groups of agents withoutprocessing their individual trajectories. We demonstrate the effectiveness ofour sparse input representation and our model in terms of computation andaccuracy over three datasets. We further show that co-training consistenttrajectory and occupancy predictions improves upon state-of-the-art performanceunder standard metrics.

StopNet: Scalable Trajectory and Occupancy Prediction for Urban Autonomous Driving