基于融合改进A*和ACO算法的农用无人车多目标路径规划

打开文本图片集

中图分类号：S232；TP242 文献标识码：A 文章编号：2095-5553（2025）12-0255-06

Abstract：Inorder toenableagriculturalunmannedvehicles toavoidobstaclesandquickly traversecropdiseasesat multi-target points tocompletethespraying operation，combinedwith theadvantagesof monitoringdrones toobtain global groundobject informationanddisease location information，a multi-objective path planning foragricultural unmanned vehicles based on the fusion of improved A* and ACO algorithms is proposed.Firstly，an improved A*（IA*） algorithm is proposed to solve the problem that the traditional A* algorithm plans the path with many inflection points，which is used to solvethe shrtest obstacle avoidance distance between two target points and the optimal path with fewer inflection points. Secondly，inorder to improve the convergence accuracy of ACOalgorithm，an improved antcolonyoptimization （IACO） algorithmispresented，whichisused tosolveashortestroutewith highconvergenceaccuracyand traversing multiple target points.Finaly，the IA"algorithm and IACO algorithm are fused to plantheoptimal path traversing the multi-target pointsintheobstacleavoidanceenvironment.Thesimulationresults show thattheIA’algorithmreduces the numberof inflection points by 40% in complex environment model verification.The average，standard deviation and range of the planning route length of theIACOalgorithmare beter than thoseof the ACO algorithm.When1O target points are taken，thestandarddeviationof the IACOalgorithmisO，and thealgorithm has higherconvergenceaccuracyandbeter robustness.Inthetwomodelsofpepperfieldenvironment，theoptimalpathwithfew inflectionpointsandtraversingall targetpointsisplannedbythe fusion path planningalgorithm.

Keywords：agricultural unmanned vehicle；multi-target；global’ path planning；improved A* algorithm；improved ant colony optimization algorithm；fused path planning algorithm

0 引言

随着人工智能的兴起，越来越多的新兴技术，如机器学习、计算机视觉、智能优化算法等技术逐渐应用于农业生产中，衍生了各种具备智能生产功能的农业机器人，如巡检无人机、农用无人车等。（剩余9314字）