LiDAR News: Quanergy, Ouster, AI Spoofing

Quanergy publishes a video explanation of its LiDAR approach:



Ouster article "The Dead Bug Problem" emphasize the importance of larger lens:

"...lidar sensors with smaller optical apertures are less resilient to obscurants. Opaque or refractive obscurants, like a raindrop, can deflect laser light, attenuate the lidar signal and thereby reduce range in that pixel. With larger beam aperture, signal strength is only partially attenuated instead of completely blocked, and the point cloud would show minimal impact."

University of Michigan and University of California, Irvine project "Adversarial Sensor Attack on LiDAR-based AV Perception" claims to find a way to fool Baidu Apollo AI-based autonomous driving platform into perceiving an obstacles in close distances to the front of a victim AV:

"In this work, we perform the first security study of LiDAR-based perception in AV systems. We consider LiDAR spoofing attacks as the threat model, and set the attack goal as spoofing front-near obstacles. We first reproduce the state-of-the-art LiDAR spoofing attack, and find that blindly applying it is insufficient to achieve the attack goal due to the machine learning-based object detection process. We thus perform analysis to fool the machine learning model by formulating the attack task as an optimization problem. We first construct the input perturbation function using local attack experiments and global spatial transformation-based modeling, and then construct the objective function by studying the post-processing process. We also identify the inherent limitations of directly using optimization-based methods and design a new algorithm that increases the attack success rates by 2.65× on average. As a case study, we further construct and evaluate two attack scenarios that may compromise AV safety and mobility. We also discuss defense directions at AV system, sensor, and machine learning model levels."