Raw High-Definition Radar for Multi-Task Learning
This work addresses computational bottlenecks in automotive radar systems for autonomous driving, offering an incremental improvement over existing methods.
The paper tackles the challenge of high computational cost and data volume in High Definition (HD) radar sensing by proposing FFT-RadNet, a model that learns to recover angles from a range-Doppler spectrum instead of computing a full 3D tensor, achieving competitive performance on vehicle detection and free space segmentation tasks while requiring less compute and memory.
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.