CoVeRaP: Cooperative Vehicular Perception through mmWave FMCW Radars

TL;DR

CoVeRaP introduces a cooperative FMCW radar dataset and a multi-vehicle perception framework that significantly enhances 3D object detection accuracy in autonomous driving scenarios.

Contribution

The paper releases a large, synchronized multi-vehicle radar dataset and proposes a novel fusion-based perception method that improves detection performance over single-vehicle systems.

Findings

Middle fusion with intensity encoding increases detection accuracy by up to 9x at IoU 0.9.

The proposed framework outperforms single-vehicle baselines across diverse maneuvers.

First reproducible benchmark for multi-vehicle FMCW radar perception.

Abstract

Automotive FMCW radars remain reliable in rain and glare, yet their sparse, noisy point clouds constrain 3-D object detection. We therefore release CoVeRaP, a 21 k-frame cooperative dataset that time-aligns radar, camera, and GPS streams from multiple vehicles across diverse manoeuvres. Built on this data, we propose a unified cooperative-perception framework with middle- and late-fusion options. Its baseline network employs a multi-branch PointNet-style encoder enhanced with self-attention to fuse spatial, Doppler, and intensity cues into a common latent space, which a decoder converts into 3-D bounding boxes and per-point depth confidence. Experiments show that middle fusion with intensity encoding boosts mean Average Precision by up to 9x at IoU 0.9 and consistently outperforms single-vehicle baselines. CoVeRaP thus establishes the first reproducible benchmark for multi-vehicle FMCW-radar perception and demonstrates that affordable radar sharing markedly improves detection robustness. Dataset and code are publicly available to encourage further research.