Ephemerality meets LiDAR-based Lifelong Mapping

TL;DR

ELite is a LiDAR-based lifelong mapping framework that uses probabilistic ephemerality modeling to distinguish static and transient elements, enabling accurate map updates and robust alignment in dynamic environments.

Contribution

We introduce a novel ephemerality modeling approach for LiDAR data that improves long-term mapping by accurately classifying transient and static map elements.

Findings

Effective in removing dynamic objects from maps

Improves map alignment accuracy over time

Demonstrates robustness in real-world long-term datasets

Abstract

Lifelong mapping is crucial for the long-term deployment of robots in dynamic environments. In this paper, we present ELite, an ephemerality-aided LiDAR-based lifelong mapping framework which can seamlessly align multiple session data, remove dynamic objects, and update maps in an end-to-end fashion. Map elements are typically classified as static or dynamic, but cases like parked cars indicate the need for more detailed categories than binary. Central to our approach is the probabilistic modeling of the world into two-stage $\textit{ephemerality}$, which represent the transiency of points in the map within two different time scales. By leveraging the spatiotemporal context encoded in ephemeralities, ELite can accurately infer transient map elements, maintain a reliable up-to-date static map, and improve robustness in aligning the new data in a more fine-grained manner. Extensive real-world experiments on long-term datasets demonstrate the robustness and effectiveness of our system. The source code is publicly available for the robotics community: https://github.com/dongjae0107/ELite.