Learning an Overlap-based Observation Model for 3D LiDAR Localization

TL;DR

This paper introduces a neural network-based observation model for 3D LiDAR localization that predicts scan overlap and yaw offset, improving vehicle localization accuracy in urban environments.

Contribution

We propose a novel neural network model for LiDAR scan overlap prediction integrated into Monte-Carlo localization, demonstrating superior performance over existing methods.

Findings

Reliable urban vehicle localization demonstrated

Outperforms beam-end point and histogram-based methods

Requires fewer particles for accurate localization

Abstract

Localization is a crucial capability for mobile robots and autonomous cars. In this paper, we address learning an observation model for Monte-Carlo localization using 3D LiDAR data. We propose a novel, neural network-based observation model that computes the expected overlap of two 3D LiDAR scans. The model predicts the overlap and yaw angle offset between the current sensor reading and virtual frames generated from a pre-built map. We integrate this observation model into a Monte-Carlo localization framework and tested it on urban datasets collected with a car in different seasons. The experiments presented in this paper illustrate that our method can reliably localize a vehicle in typical urban environments. We furthermore provide comparisons to a beam-end point and a histogram-based method indicating a superior global localization performance of our method with fewer particles.