Raw High-Definition Radar for Multi-Task Learning

TL;DR

This paper introduces FFT-RadNet, a novel high-definition radar model that efficiently detects vehicles and segments free space by learning from range-Doppler spectra, reducing computational costs while maintaining high accuracy.

Contribution

The paper presents FFT-RadNet, a new HD radar sensing model that avoids 3D tensor computation and learns to recover angles directly, improving efficiency and performance.

Findings

FFT-RadNet achieves competitive accuracy with less compute and memory.

The model effectively detects vehicles and segments free space.

A new annotated dataset, RADIal, is introduced for radar research.

Abstract

With their robustness to adverse weather conditions and ability to measure speeds, radar sensors have been part of the automotive landscape for more than two decades. Recent progress toward High Definition (HD) Imaging radar has driven the angular resolution below the degree, thus approaching laser scanning performance. However, the amount of data a HD radar delivers and the computational cost to estimate the angular positions remain a challenge. In this paper, we propose a novel HD radar sensing model, FFT-RadNet, that eliminates the overhead of computing the range-azimuth-Doppler 3D tensor, learning instead to recover angles from a range-Doppler spectrum. FFT-RadNet is trained both to detect vehicles and to segment free driving space. On both tasks, it competes with the most recent radar-based models while requiring less compute and memory. Also, we collected and annotated 2-hour worth of raw data from synchronized automotive-grade sensors (camera, laser, HD radar) in various environments (city street, highway, countryside road). This unique dataset, nick-named RADIal for "Radar, Lidar et al.", is available at https://github.com/valeoai/RADIal.