Fusion VIO: An Extendable Sensor Fusion Framework for Unmaned Vehicles

Real-time perception based on the simultaneous localization and mapping (SLAM) technology is of immense application potential in industry filed. In this work, we provide an extended Kalman filter (EKF) visual SLAM framework named Fusion VIO, which contains HDR imaging system, hardware synchronization, object detection, sensor fusion, semantic fusion. Notably, VIO well fuses loop closure information, takes effects solving error problem during operation robot improving robustness system. Besides, experimental validation shows that not only maintains high accuracy but also cost one-third resources compared to common VINS Our work demonstrates a novel fusion for unmaned vehicles.