Ground-Fusion: A Low-cost Ground SLAM System Robust to Corner Cases

TL;DR

Ground-Fusion is a robust, low-cost ground vehicle SLAM system that effectively handles diverse environments and sensor anomalies through sensor fusion, efficient initialization, and real-time mapping, outperforming existing systems in challenging scenarios.

Contribution

We propose Ground-Fusion, a novel sensor fusion SLAM system with robust initialization and anomaly detection, tailored for diverse indoor and outdoor environments.

Findings

Outperforms existing low-cost SLAM systems in corner cases

Achieves accurate localization using multi-sensor fusion

Demonstrates robustness in diverse environments

Abstract

We introduce Ground-Fusion, a low-cost sensor fusion simultaneous localization and mapping (SLAM) system for ground vehicles. Our system features efficient initialization, effective sensor anomaly detection and handling, real-time dense color mapping, and robust localization in diverse environments. We tightly integrate RGB-D images, inertial measurements, wheel odometer and GNSS signals within a factor graph to achieve accurate and reliable localization both indoors and outdoors. To ensure successful initialization, we propose an efficient strategy that comprises three different methods: stationary, visual, and dynamic, tailored to handle diverse cases. Furthermore, we develop mechanisms to detect sensor anomalies and degradation, handling them adeptly to maintain system accuracy. Our experimental results on both public and self-collected datasets demonstrate that Ground-Fusion outperforms existing low-cost SLAM systems in corner cases. We release the code and datasets at https://github.com/SJTU-ViSYS/Ground-Fusion.