无人帆船长途路径规划研究

将多维动态规划法应用于1条无人帆船从上海到青岛的长途路径规划,在当前位置以外引入已航行路径长度作为第三维状态变量,以相邻路径点之间的短途路径规划方案作为决策变量,可以规划出一组随路径总长度变化的航行时间最短路径。结果显示,增加状态变量维度后,规划结果保留了更多备选方案,起到了很好的决策辅助作用。

Long-term Route Planning of Autonomous Sailboat

The multi-dimensional dynamic programming method was employed for the long-term route planning of an autonomous sailboat from Shanghai to Qingdao. The sailed voyage length was adopted to be the third-dimension state variable. The short-term route plan between the neighboring waypoints was defined as control variable. A group of optimal routes with the minimum voyage time could be obtained corresponding to different voyage length. With the increase of state variable dimension, more optional routes were kept in the final results, which is valuable for the better decision support.