NVRadarNet: Real-Time Radar Obstacle and Free Space Detection for Autonomous Driving

TL;DR

NVRadarNet is a novel deep neural network that uses automotive RADAR sensors to detect obstacles and free space in real time, enhancing autonomous vehicle perception with sparse RADAR data.

Contribution

This work introduces the first deep neural network that utilizes sparse RADAR signals for real-time obstacle and free space detection in autonomous driving.

Findings

Runs faster than real time on embedded GPU

Generalizes well across different geographic regions

Successfully deployed in real self-driving scenarios

Abstract

Detecting obstacles is crucial for safe and efficient autonomous driving. To this end, we present NVRadarNet, a deep neural network (DNN) that detects dynamic obstacles and drivable free space using automotive RADAR sensors. The network utilizes temporally accumulated data from multiple RADAR sensors to detect dynamic obstacles and compute their orientation in a top-down bird's-eye view (BEV). The network also regresses drivable free space to detect unclassified obstacles. Our DNN is the first of its kind to utilize sparse RADAR signals in order to perform obstacle and free space detection in real time from RADAR data only. The network has been successfully used for perception on our autonomous vehicles in real self-driving scenarios. The network runs faster than real time on an embedded GPU and shows good generalization across geographic regions.