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

Achieving robust and real-time 3D perception is fundamental for autonomousvehicles. While most existing 3D perception methods prioritize detectionaccuracy, they often overlook critical aspects such as computationalefficiency, onboard chip deployment friendliness, resilience to sensor mountingdeviations, and adaptability to various vehicle types. To address thesechallenges, we present NVAutoNet: a specialized Bird's-Eye-View (BEV)perception network tailored explicitly for automated vehicles. NVAutoNet takessynchronized camera images as input and predicts 3D signals like obstacles,freespaces, and parking spaces. The core of NVAutoNet's architecture (image andBEV backbones) relies on efficient convolutional networks, optimized for highperformance using TensorRT. More importantly, our image-to-BEV transformationemploys simple linear layers and BEV look-up tables, ensuring rapid inferencespeed. Trained on an extensive proprietary dataset, NVAutoNet consistentlyachieves elevated perception accuracy, operating remarkably at 53 frames persecond on the NVIDIA DRIVE Orin SoC. Notably, NVAutoNet demonstrates resilienceto sensor mounting deviations arising from diverse car models. Moreover,NVAutoNet excels in adapting to varied vehicle types, facilitated byinexpensive model fine-tuning procedures that expedite compatibilityadjustments.

NVAutoNet: Fast and Accurate 360$^{\circ}$ 3D Visual Perception For Self Driving