Ephemerality meets LiDAR-based Lifelong Mapping

2025-02-19

AI Summary

To address map degradation caused by dynamic objects (e.g., temporarily parked vehicles) in long-term robotic deployment, this paper proposes ELite, a LiDAR-based lifelong mapping framework. Methodologically, it introduces, for the first time, a two-scale transient probability modeling scheme that transcends the conventional static/dynamic binary assumption, enabling fine-grained discrimination between short-term and long-term dynamic elements. The framework integrates spatiotemporal feature learning, probabilistic graphical model encoding, and an end-to-end differentiable map update network to jointly support multi-session data alignment, dynamic object removal, and incremental map maintenance. Evaluated on real-world long-term datasets, ELite significantly improves map consistency and cross-session registration robustness. The source code is publicly released and has been widely adopted by the community.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Life-Long and Continual Learning
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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 $ extit{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.

Problem

• Aligns multiple session data seamlessly in dynamic environments.
• Removes dynamic objects and updates maps end-to-end.
• Classifies map elements beyond binary using ephemerality modeling.

Innovation

• Ephemerality-aided LiDAR mapping framework
• Two-stage probabilistic ephemerality modeling
• Dynamic object removal and map updating