# Geometry-based Graph Pruning for Lifelong SLAM

arXiv: https://arxiv.org/abs/2110.01286 · HTML: https://mlsanity.com/paper/2110.01286/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2021.

## Built on by (most cited first, 7 of 7)

- [Swarm-SLAM : Sparse Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot Systems](https://mlsanity.com/paper/2301.06230/) (2023)
- [BioSLAM: A Bio-inspired Lifelong Memory System for General Place Recognition](https://mlsanity.com/paper/2208.14543/) (2022)
- [General Place Recognition Survey: Towards the Real-world Autonomy Age](https://mlsanity.com/paper/2209.04497/) (2022)
- [Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review](https://mlsanity.com/paper/2505.20503/) (2025)
- [Lifelong 3D Mapping Framework for Hand-held & Robot-mounted LiDAR Mapping Systems](https://mlsanity.com/paper/2501.18110/) (2025)
- [Practical and Performant Enhancements for Maximization of Algebraic Connectivity](https://mlsanity.com/paper/2511.08694/) (2025)
- [PiGRAND: Physics-informed Graph Neural Diffusion for Intelligent Additive Manufacturing](https://mlsanity.com/paper/2603.15194/) (2026)

## Abstract (arXiv)

Lifelong SLAM considers long-term operation of a robot where already mapped locations are revisited many times in changing environments. As a result, traditional graph-based SLAM approaches eventually become extremely slow due to the continuous growth of the graph and the loss of sparsity. Both problems can be addressed by a graph pruning algorithm. It carefully removes vertices and edges to keep the graph size reasonable while preserving the information needed to provide good SLAM results. We propose a novel method that considers geometric criteria for choosing the vertices to be pruned. It is efficient, easy to implement, and leads to a graph with evenly spread vertices that remain part of the robot trajectory. Furthermore, we present a novel approach of marginalization that is more robust to wrong loop closures than existing methods. The proposed algorithm is evaluated on two publicly available real-world long-term datasets and compared to the unpruned case as well as ground truth. We show that even on a long dataset (25h), our approach manages to keep the graph sparse and the speed high while still providing good accuracy (40 times speed up, 6cm map error compared to unpruned case).