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

Motion prediction of road users in traffic scenes is critical for autonomousdriving systems that must take safe and robust decisions in complex dynamicenvironments. We present a novel motion prediction system for autonomousdriving. Our system is based on the Bayesian inverse planning framework, whichefficiently orchestrates map-based goal extraction, a classical control-basedtrajectory generator and a mixture of experts collection of light-weight neuralnetworks specialised in motion profile prediction. In contrast to manyalternative methods, this modularity helps isolate performance factors andbetter interpret results, without compromising performance. This systemaddresses multiple aspects of interest, namely multi-modality, motion profileuncertainty and trajectory physical feasibility. We report on severalexperiments with the popular highway dataset NGSIM, demonstratingstate-of-the-art performance in terms of trajectory error. We also perform adetailed analysis of our system's components, along with experiments thatstratify the data based on behaviours, such as change-lane versus follow-lane,to provide insights into the challenges in this domain. Finally, we present aqualitative analysis to show other benefits of our approach, such as theability to interpret the outputs.

Flash: Fast and Light Motion Prediction for Autonomous Driving with Bayesian Inverse Planning and Learned Motion Profiles