Human-Inspired Long-Term Indoor Localization in Human-Oriented Environment

TL;DR

This paper reviews a human-inspired approach to long-term indoor localization for service robots, utilizing geometric, textual, and semantic data, validated over months of real-world sequences with open-source tools.

Contribution

It introduces a comprehensive overview of long-term indoor localization methods that incorporate geometric priors and semantic information, with validation on extended real-world data.

Findings

Validated on challenging multi-month sequences

Integrated geometric, textual, and semantic information

Released open source implementations

Abstract

Lifelong localization is crucial for enabling the autonomy of service robots. In this paper, we present an overview of our past research on long-term localization and mapping, exploiting geometric priors such as floor plans and integrating textual and semantic information. Our approach was validated on challenging sequences spanning over many months, and we released open source implementations.