Operation Path Planning Method Of Agricultural Robot In Wheat Field Environment

Wheat is an important food crop,and China is the world’s largest wheat producing and consuming country.With the modernization of society,labor shortage has become an important factor affecting the safety of wheat production,and agricultural robots with autonomous operation can weaken the dependence of agricultural production on labor and have broad application prospects in wheat production.Therefore,this paper takes wheat fields as the research object and focuses on the key technologies in path planning of agricultural robots,focusing on the full-coverage path planning and local path planning of agricultural robots in practices such as wheat planting and harvesting,and providing technical support to effectively improve the autonomous operation efficiency and operation quality of agricultural robots.The main research of this paper is as follows:(1)To study machine vision-based wheat field navigation path extraction for agricultural robots.Firstly,the acquired images are preprocessed according to the wheat field image features,and the image preprocessing operations include extracting the region of interest(ROI),selecting the light-independent S component of the HSI color model,using the maximum interclass variance method for image segmentation,image binarization inverse color,advanced morphological processing,and edge detection using the Sobel operator.Secondly,the machine vision-based Zhang-Suen parallel refinement algorithm,Hough transform and LIDAR-based laser SLAM three methods for extracting path information.Finally,according to the results of the above three methods,it is known that the Hough transform is better in real time and more efficient for the needs of path planning of single operation in large wheat fields.The results of angular deviation show that the navigation path extracted based on Hough transform can be used to adjust the driving direction of agricultural robots and improve the accuracy of autonomous operation of agricultural robots.(2)To study the full-coverage path planning for agricultural robots in wheat fields based on travel quotient(TSP)model.In this paper,to avoid the inefficiency problem of traditional operation methods,the agricultural robot full-coverage path planning problem is transformed into a travel quotient problem,and the TSP-based full-coverage path planning method for wheat fields is proposed with minimizing the total non-working distance as the objective function and solved by using ant colony algorithm.Finally,a comparison test is conducted based on MATLAB platform,and the test results show that the TSP-based full-coverage path planning method for wheat fields can not only select a better operation method and turning path for agricultural robots,so that the turning path length of agricultural robots is the shortest,but also get the optimal operation path trajectory of agricultural robots in wheat fields and improve the operation efficiency of agricultural robots.(3)To study the local obstacle avoidance planning of agricultural robots in wheat fields based on the improved artificial potential field method.In the complex environment of wheat field,the local path planning method based on the improved artificial potential field method is studied for the obstacle avoidance needs of agricultural robots in operation.This paper addresses the problems of the traditional artificial potential field method and improves the algorithm to solve the problem of local minima by adding additional forces to make the agricultural machine break the force equilibrium,and solves the problem of unreachable target of the agricultural robot by optimizing the repulsion function.Finally,the simulation test is conducted based on MATLAB platform,and the test results show that the improved artificial potential field method can plan the local obstacle avoidance path for the agricultural robot in the wheat field environment with obstacles,so that the agricultural robot can reach the target point smoothly and meet the safety requirements of the agricultural robot.