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

Occupancy maps are widely recognized as an efficient method for facilitatingrobot motion planning in static environments. However, for intelligentvehicles, occupancy of both the present and future moments is required toensure safe driving. In the automotive industry, the accurate and continuousprediction of future occupancy maps in traffic scenarios remains a formidablechallenge. This paper investigates multi-sensor spatio-temporal fusionstrategies for continuous occupancy prediction in a systematic manner. Thispaper presents FusionMotion, a novel bird's eye view (BEV) occupancy predictorwhich is capable of achieving the fusion of asynchronous multi-sensor data andpredicting the future occupancy map with variable time intervals and temporalhorizons. Remarkably, FusionMotion features the adoption of neural ordinarydifferential equations on recurrent neural networks for occupancy prediction.FusionMotion learns derivatives of BEV features over temporal horizons, updatesthe implicit sensor's BEV feature measurements and propagates future states foreach ODE step. Extensive experiments on large-scale nuScenes and Lyft L5datasets demonstrate that FusionMotion significantly outperforms previousmethods. In addition, it outperforms the BEVFusion-style fusion strategy on theLyft L5 dataset while reducing synchronization requirements. Codes and modelswill be made available.

FusionMotion: Multi-Sensor Asynchronous Fusion for Continuous Occupancy Prediction via Neural-ODE