Unmanned aerial/ground vehicles (UAV/UGV) collaboration systems are increasingly being used to perform reconnaissance and rescue missions autonomously, especially in disaster areas. The paper aims to discuss this issue.
To improve visibility, this study proposes a path-planning algorithm based on map matching. Continuous ground images are first collected aerially using the UAV vision system. Subsequently, a global map of the ground environment is created by processing the collected images using the methods of image correction, image mosaic and obstacle recognition. The local map of the ground environment is obtained using the 2D laser radar sensor of the UGV. A set of features for both global and local maps is established. Unknown values during map matching are determined via the least squares method. Based on the matched mapping, the traditional A* algorithm is used for the planning of global path in the global map, and the dynamic window method is used for adjustment of the local map.
Simulation experiments were carried out to demonstrate the effectiveness of the proposed algorithm. The experimental results show that the proposed algorithm can construct a global map of the wide environment and effectively bypass the obstacles missed by the UAV.
Prior to map matching, there is a need to extract the edge of obstacles in the global map.
This paper proposed a path planning algorithm based on map matching, yielding insights into the application of the UAV/UGV collaboration systems in disaster areas.
