IR-MCL: Implicit Representation-Based Online Global Localization

TL;DR

This paper introduces IR-MCL, a novel online global localization method using neural implicit scene representations to synthesize LiDAR scans, significantly improving accuracy over existing methods.

Contribution

It proposes a neural occupancy field for scene modeling that enhances Monte-Carlo localization with more accurate scan synthesis.

Findings

Outperforms state-of-the-art localization methods

Provides more accurate LiDAR scan predictions

Achieves efficient and precise robot localization

Abstract

Determining the state of a mobile robot is an essential building block of robot navigation systems. In this paper, we address the problem of estimating the robots pose in an indoor environment using 2D LiDAR data and investigate how modern environment models can improve gold standard Monte-Carlo localization (MCL) systems. We propose a neural occupancy field to implicitly represent the scene using a neural network. With the pretrained network, we can synthesize 2D LiDAR scans for an arbitrary robot pose through volume rendering. Based on the implicit representation, we can obtain the similarity between a synthesized and actual scan as an observation model and integrate it into an MCL system to perform accurate localization. We evaluate our approach on self-recorded datasets and three publicly available ones. We show that we can accurately and efficiently localize a robot using our approach surpassing the localization performance of state-of-the-art methods. The experiments suggest that the presented implicit representation is able to predict more accurate 2D LiDAR scans leading to an improved observation model for our particle filter-based localization. The code of our approach will be available at: https://github.com/PRBonn/ir-mcl.