Analysis of Robust Functions for Registration Algorithms

TL;DR

This paper systematically compares 14 outlier filtering methods for ICP registration in mobile robotics, revealing their relative stability and performance across diverse environments and tuning conditions.

Contribution

It provides the first large-scale, comprehensive evaluation of outlier filters for ICP, highlighting the stability of certain filters and the effectiveness of simple L1 norm.

Findings

Most filters perform similarly when properly tuned

Var. Trim., Cauchy, and Cauchy MAD are more stable across environments

L1 norm achieves comparable accuracy without tuning

Abstract

Registration accuracy is influenced by the presence of outliers and numerous robust solutions have been developed over the years to mitigate their effect. However, without a large scale comparison of solutions to filter outliers, it is becoming tedious to select an appropriate algorithm for a given application. This paper presents a comprehensive analyses of the effects of outlier filters on the ICP algorithm aimed at mobile robotic application. Fourteen of the most common outlier filters (such as M-estimators) have been tested in different types of environments, for a total of more than two million registrations. Furthermore, the influence of tuning parameters have been thoroughly explored. The experimental results show that most outlier filters have similar performance if they are correctly tuned. Nonetheless, filters such as Var. Trim., Cauchy, and Cauchy MAD are more stable against different environment types. Interestingly, the simple norm L1 produces comparable accuracy, while been parameterless.