LT-mapper: A Modular Framework for LiDAR-based Lifelong Mapping
This work addresses the need for robots to navigate reliably in non-stationary real-world settings, presenting an incremental improvement in lifelong mapping with modular and open-source tools.
The paper tackles the problem of long-term 3D map management for robots in dynamic urban environments by developing LT-mapper, a modular LiDAR-based framework that handles multi-session SLAM, change detection, and change management, achieving reliable performance under year-level variations in real-world experiments.
Long-term 3D map management is a fundamental capability required by a robot to reliably navigate in the non-stationary real-world. This paper develops open-source, modular, and readily available LiDAR-based lifelong mapping for urban sites. This is achieved by dividing the problem into successive subproblems: multi-session SLAM (MSS), high/low dynamic change detection, and positive/negative change management. The proposed method leverages MSS and handles potential trajectory error; thus, good initial alignment is not required for change detection. Our change management scheme preserves efficacy in both memory and computation costs, providing automatic object segregation from a large-scale point cloud map. We verify the framework's reliability and applicability even under permanent year-level variation, through extensive real-world experiments with multiple temporal gaps (from day to year).