3D Point Cloud Processing and Learning for Autonomous Driving

TL;DR

This paper reviews recent advances in processing and learning from 3D LiDAR point clouds for autonomous driving, emphasizing their importance in perception, mapping, and localization.

Contribution

It provides a comprehensive overview of current algorithms, identifies gaps, and discusses future challenges in 3D point cloud processing for autonomous vehicles.

Findings

LiDAR-based methods are crucial for accurate perception in autonomous driving.

Recent algorithms improve object detection and scene understanding from 3D point clouds.

Open issues include real-time processing and robustness in diverse environments.

Abstract

We present a review of 3D point cloud processing and learning for autonomous driving. As one of the most important sensors in autonomous vehicles, light detection and ranging (LiDAR) sensors collect 3D point clouds that precisely record the external surfaces of objects and scenes. The tools for 3D point cloud processing and learning are critical to the map creation, localization, and perception modules in an autonomous vehicle. While much attention has been paid to data collected from cameras, such as images and videos, an increasing number of researchers have recognized the importance and significance of LiDAR in autonomous driving and have proposed processing and learning algorithms to exploit 3D point clouds. We review the recent progress in this research area and summarize what has been tried and what is needed for practical and safe autonomous vehicles. We also offer perspectives on open issues that are needed to be solved in the future.