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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Robust motion forecasting of the dynamic scene is a critical component of anautonomous vehicle. It is a challenging problem due to the heterogeneity in thescene and the inherent uncertainties in the problem. To improve the accuracy ofmotion forecasting, in this work, we identify a new consistency constraint inthis task, that is an agent's future trajectory should be coherent with itshistory observations and visa versa. To leverage this property, we propose anovel cycle consistency training scheme and define a novel cycle loss toencourage this consistency. In particular, we reverse the predicted futuretrajectory backward in time and feed it back into the prediction model topredict the history and compute the loss as an additional cycle loss term.Through our experiments on the Argoverse dataset, we demonstrate that cycleloss can improve the performance of competitive motion forecasting models.

Improving Motion Forecasting for Autonomous Driving with the Cycle Consistency Loss