Webinar: Collaborative and Adversarial 3D Perception for Autonomous Driving

Robust and reliable perception systems serve as the “eyes” of autonomous vehicles. LiDAR is a widely applied perception sensor in autonomous vehicles for capturing 3D geometry information of the environment. However, LiDAR-based perception faces many challenges such as data sparsity, occlusions, and motion distortion. In this talk, I will show how we design novel 3D deep learning algorithms from two aspects, collaborative and adversarial, in order to improve the robustness of LiDAR-based 3D perception. For effective and efficient collaborative perception, we propose DiscoNet. It uses a dynamic directed graph with matrix-valued edge weight for an ego-vehicle to adaptively retrieve the most important complementary information from its neighboring vehicles, which could improve its own perception performance and robustness. Besides collaborative perception, we also study the adversarial robustness of LiDAR-based perception, and reveal an often-overlooked vulnerability that lies in the LiDAR motion correction process. We show that spoofing of a vehicle’s trajectory estimation with small adversarial perturbations can jeopardize LiDAR perception. We hope our collaborative and adversarial 3D perception research can help improve the robustness and safety of autonomous driving systems.