Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LT-mapper: A Modular Framework for LiDAR-based Lifelong Mapping

About

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).

Giseop Kim, Ayoung Kim• 2021

Related benchmarks

TaskDatasetResultRank
Multi-robot map mergingOutdoor A01-H01
RMSE (m)4.328
6
Multi-robot map mergingNTU 01-02
RMSE (m)3.679
6
Multi-robot map mergingNTU 01-10
RMSE (m)3.34
6
Multi-robot map mergingNTU Avg.
RMSE (m)3.51
6
Multi-robot map mergingOutdoor A01-A02
RMSE (m)121.2
6
Multi-robot map mergingOutdoor Avg.
RMSE (m)122
6
Multi-robot map mergingOutdoor A01-S01
RMSE Error270.8
6
Multi-robot map mergingOutdoor A01-S02
RMSE (m)86.612
6
Change DetectionLT-ParkingLot seq. 03 → 04
PD Precision9.4
4
Multi-robot map mergingRoundabout 01-02
e_rmse (m)7.787
3
Showing 10 of 15 rows

Other info

Follow for update