Reproduce “Adversarial Robustness of Camera-Radar Sensor Fusion for Autonomous Driving” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Ce Zhou, Yubo Wu, Khang Nguyen, Liyang Xiao, Thomas Hou, Qiben Yan

The authors evaluate five camera–radar systems on 3D detection and depth estimation by corrupting one sensor at a time while leaving the other unchanged. Camera blur lowers RADIANT’s detection mAP from 0.363 to 0.290 and raises Cam&mmWave depth MAE from 2.037 to 10.029. Tested radar corruptions have smaller, task-dependent effects. Results cover nuScenes test data, not simultaneous attacks or defenses.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.