Path planning on satellite images for unmanned surface vehicles

International Journal of Naval Architecture and Ocean Engineering

Chien-Ming Tseng¹  Joe-Ming Yang²  P.S. Tseng² 

[1] Department of Electrical Engineering and Computer Science, Masdar Institute, Abu Dhabi, UAE.;Department of Systems and Naval Mechatronic Engineering, National Cheng Kung University Tainan, Taiwan;

关键词: A* algorithm;    Collision avoidance;    Image analysis;   

DOI  :  10.1515/ijnaoe-2015-0007

来源: DOAJ

【 摘 要 】

In recent years, the development of autonomous surface vehicles has been a field of increasing research interest. There are two major areas in this field: control theory and path planning. This study focuses on path planning, and two objectives are discussed: path planning for Unmanned Surface Vehicles (USVs) and implementation of path planning in a real map. In this paper, satellite thermal images are converted into binary images which are used as the maps for the Finite Angle A * algorithm (FAA *), an advanced A * algorithm that is used to determine safer and suboptimal paths for USVs. To plan a collision-free path, the algorithm proposed in this article considers the dimensions of surface vehicles. Furthermore, the turning ability of a surface vehicle is also considered, and a constraint condition is introduced to improve the quality of the path planning algorithm, which makes the traveled path smoother. This study also shows a path planning experiment performed on a real satellite thermal image, and the path planning results can be used by an USV

【 授权许可】

Unknown