Unmanned Farm Path Optimization Strategy Based On Improved A* Algorithm

Abstract

The objective of this study is to solve the problems of low search efficiency, many redundant nodes and lack of terrain consideration in the path planning of unmanned farms with the traditional A* algorithm. An improved A* algorithm was proposed to improve the efficiency of path planning, reduce the energy consumption of agricultural machinery and enhance the adaptability of actual scenarios. Firstly, in order to balance the actual cost and the heuristic estimation cost, the dynamic dynamic weight coefficient is added on the basis of the traditional A* algorithm, so that the heuristic function can achieve an adaptive effect, increasing the importance of the heuristic function when it is far away from the target point, and decreasing the importance of the heuristic function when it is close to the target point. Secondly, the refinement of the raster map and the smoothing of the path are proposed, and the terrain influence factor and Bezier curve smoothing are introduced, so that the mobile robot can avoid the high-cost area as much as possible and obtain a continuous and smooth path. Finally, the simulation laboratory was carried out by PyCharm to build a raster map of the farm, and the performance of the traditional A* algorithm and the improved A* algorithm was compared. Compared with the traditional A* algorithm, the path length of the improved A* algorithm is only about 1.12% longer than that of the original algorithm, while the search time is reduced by about 98.56%, and the search node is increased by 93.40%.The improved A* algorithm is far better than the traditional A* algorithm in terms of search efficiency, search node and path smoothness.