Introduction

This is the homepage of Ground-Fusion: A Low-cost Ground SLAM System Robust to Corner Cases (ICRA2024). 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.

The source code is released at https://github.com/SJTU-ViSYS/Ground-Fusion

The dataset is released at https://github.com/sjtuyinjie/M2DGR-plus. 

Method

The system adopts an adaptive initialization strategy based on the robot's motion state. Potential sensor faults will be detected and handled accordingly. Real-time dense color mapping is supported to facilitate navigation tasks.

Demo Video

This video provides a comprehensive demonstration of the robustness of Ground-Fusion in motion blur and severe occlusion. Furthermore, the system is shown to be capable to construct real-time dense color map.

Dense Mapping 

The following is the result of point cloud map reconstructed in color using Ground-Fusion algorithm in different indoor scenes, with good density and continuity.