4D Radar Meets LiDAR and Camera: Cooperative Perception under Adverse Weather

2026-05-29

AI Summary

This work addresses the degradation of camera and LiDAR performance under adverse weather conditions, which compromises collaborative perception systems. To mitigate this issue, the study systematically introduces 4D imaging radar into a collaborative perception framework for the first time, establishing dual fusion pipelines—radar-camera and LiDAR-radar—and proposes a Doppler-guided spatial attention mechanism to enhance multi-agent feature alignment. The authors construct the first radar-augmented collaborative perception benchmark incorporating physically realistic LiDAR degradation. Extensive evaluations in both simulated environments and real-world scenarios (MAN TruckScenes) demonstrate that the proposed method significantly improves perception robustness in fog and rain, particularly when radar substitutes for degraded LiDAR, exhibiting strong cross-platform generalization capabilities.

Abstract

Cooperative perception is important for autonomous driving but remains fragile when cameras and LiDAR degrade in adverse weather. We address this challenge by integrating 4D imaging radar as a weather-robust modality into collaborative perception and introducing a Doppler-guided spatial attention mechanism for multi-agent fusion. Our approach extends two representative backbones: a radar-camera pipeline where radar substitutes LiDAR, and a LiDAR-radar pipeline where radar complements LiDAR. To support evaluation, we release radar-augmented benchmarks, OPV2V-R and Adver-City-R, with physics-based LiDAR degradation. Experiments show strong robustness gains in fog and rain, including substantial improvements when radar replaces degraded LiDAR. Additional validation on MAN TruckScenes demonstrates transfer beyond simulation. Overall, our results highlight 4D imaging radar as a robust modality for all-weather collaborative perception. Dataset and code are available at: https://url.fzi.de/SlimComm.

Problem

• cooperative perception
• adverse weather
• 4D radar
• LiDAR degradation
• autonomous driving

Innovation

• 4D imaging radar
• cooperative perception
• Doppler-guided attention
• adverse weather robustness
• multi-modal fusion