This paper proposes a global positioning system (GPS)-aided visual simultaneous localization and mapping (SLAM) called GO-SLAM for adaptive UAV navigation. The proposed system offers a solution by the method to address the adaptive navigation challenge, wherein the navigation path needs to pass through an indoor area or outdoor area. GO-SLAM relies on a GPS receiver sensor and camera for visual SLAM to provide local positioning information for UAV navigation. Specifically, a transition system was designed by converting geocentric coordinates from the last coordinate and assigned goal position. The experimental result showed that the GO-SLAM is able to switch navigation, achieving lower travel time and lower computation memory.