Detecting the Anomalies in LiDAR Pointcloud

TL;DR

This paper introduces a mathematical, label-free method for detecting anomalies in LiDAR pointclouds by analyzing spatial and intensity distributions, enhancing safety and diagnostics in autonomous driving.

Contribution

A novel, scalable anomaly detection approach based on pointcloud quality metrics that does not require training or labeling, suitable for online and offline use.

Findings

Effective detection of various known and unknown anomalies

Validated on diverse real-world LiDAR data sets

Can be deployed online for safety monitoring or offline for analysis

Abstract

LiDAR sensors play an important role in the perception stack of modern autonomous driving systems. Adverse weather conditions such as rain, fog and dust, as well as some (occasional) LiDAR hardware fault may cause the LiDAR to produce pointcloud with abnormal patterns such as scattered noise points and uncommon intensity values. In this paper, we propose a novel approach to detect whether a LiDAR is generating anomalous pointcloud by analyzing the pointcloud characteristics. Specifically, we develop a pointcloud quality metric based on the LiDAR points' spatial and intensity distribution to characterize the noise level of the pointcloud, which relies on pure mathematical analysis and does not require any labeling or training as learning-based methods do. Therefore, the method is scalable and can be quickly deployed either online to improve the autonomy safety by monitoring anomalies in the LiDAR data or offline to perform in-depth study of the LiDAR behavior over large amount of data. The proposed approach is studied with extensive real public road data collected by LiDARs with different scanning mechanisms and laser spectrums, and is proven to be able to effectively handle various known and unknown sources of pointcloud anomaly.