MAD-ICP: It Is All About Matching Data -- Robust and Informed LiDAR Odometry

TL;DR

MAD-ICP introduces a robust LiDAR odometry system that overcomes environmental and sensor assumptions, leveraging PCA-based ICP with uncertainty management, achieving domain-agnostic performance and open-source release.

Contribution

The paper presents a novel ICP-based LiDAR odometry method that is robust across diverse conditions and includes an open-source real-time implementation.

Findings

Operates reliably under varying environmental conditions.

Achieves performance comparable to domain-specific methods.

Provides an open-source real-time implementation.

Abstract

LiDAR odometry is the task of estimating the ego-motion of the sensor from sequential laser scans. This problem has been addressed by the community for more than two decades, and many effective solutions are available nowadays. Most of these systems implicitly rely on assumptions about the operating environment, the sensor used, and motion pattern. When these assumptions are violated, several well-known systems tend to perform poorly. This paper presents a LiDAR odometry system that can overcome these limitations and operate well under different operating conditions while achieving performance comparable with domain-specific methods. Our algorithm follows the well-known ICP paradigm that leverages a PCA-based kd-tree implementation that is used to extract structural information about the clouds being registered and to compute the minimization metric for the alignment. The drift is bound by managing the local map based on the estimated uncertainty of the tracked pose. To benefit the community, we release an open-source C++ anytime real-time implementation.