A Maximum Likelihood Approach to Extract Polylines from 2-D Laser Range Scans

TL;DR

This paper introduces a probabilistic maximum likelihood method for extracting polylines from 2-D laser scans, effectively representing man-made environments with improved accuracy over existing methods.

Contribution

It presents a novel probabilistic approach that maximizes likelihood to accurately extract polylines from raw laser data, outperforming prior techniques.

Findings

Outperforms state-of-the-art methods in accuracy

Maintains comparable computational efficiency

Validated on real-world and simulated datasets

Abstract

Man-made environments such as households, offices, or factory floors are typically composed of linear structures. Accordingly, polylines are a natural way to accurately represent their geometry. In this paper, we propose a novel probabilistic method to extract polylines from raw 2-D laser range scans. The key idea of our approach is to determine a set of polylines that maximizes the likelihood of a given scan. In extensive experiments carried out on publicly available real-world datasets and on simulated laser scans, we demonstrate that our method substantially outperforms existing state-of-the-art approaches in terms of accuracy, while showing comparable computational requirements. Our implementation is available under https://github.com/acschaefer/ple.