Abstract: Path planning is a promising research direction in mobile robots. The artificial potential field method has been widely used for the path planning of mobile robots. In this paper, the principle of the artificial potential field method and the defects of the traditional artificial potential field method are analyzed. The local minimum and target unreachable problems in artificial potential field method are analyzed from the improved method, the summaries are concluded, and the existing algorithm fusion methods are classified and reviewed. Finally, the real-time operation and multi-obstacle adaptability of robot path planning in agriculture are documented by comparing various improved methods. To meet the needs of robot path planning in modern agricultural production, the current algorithm fusion research can be combined with the actual situation of agricultural production to carry out in-depth research on the selection mechanism of fusion algorithm in different agricultural production applications.