Exploiting Virtual Array Diversity for Accurate Radar Detection [ICASSP’23]

Using millimeter-wave radars as a perception sensor provides self-driving cars with robust sensing capability in adverse weather. However, mmWave radars currently lack sufficient spatial resolution for semantic scene understanding. This paper introduces Radatron++, a system leverages cascaded MIMO (Multiple-Input Multiple-Output) radar to achieve accurate vehicle detection for self-driving cars. We develop a novel hybrid radar processing and deep learning approach to leverage the 10× finer angular resolution while combating unique challenges of cascaded MIMO radars. We train and evaluate Radatron++ with a novel cascaded radar dataset. Radatron++ achieves 93.9% and 58.5% Average Precisions with 0.5 and 0.75 Intersection over Union thresholds respectively in 2D bounding box detection, outperforming prior work using low-resolution radars by 9.3% and 18.1% respectively.

Paper:

Exploiting Virtual Array Diversity for Accurate Radar Detection

Junfeng Guan, Sohrab Madani, Waleed Ahmed, Samah Hussein, Saurabh Gupta, Haitham Hassanieh
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
[PDF]