农机化研究2025，Vol.47Issue(7)：271-278,8.DOI:10.13427/j.issn.1003-188X.2025.07.041
农机轮式机器人自动驾驶控制研究及试验
Research and Experiment on Autonomous Driving Control of Agricultural Machinery Wheeled Robot
摘要
Abstract
Manual driving of agricultural machinery requires operators to rely on their subjective experience for operation-al control.During busy farming periods,high intensity work pressure can increase operational difficulty,reduce opera-tional accuracy,and even cause safety issues.In response to this,this article conducted research on the automatic driv-ing control scheme of agricultural machinery,aiming to implement a low-cost agricultural machinery wheeled robot con-trol system based on the STM32F107 microcontroller.The system was composed of multiple components such as ARM control core,positioning acquisition and recording module,steering control module,and interface circuit.It could obtain real-time position information and plan paths of agricultural machinery,and automatically issue steering control com-mands based on positioning deviation information,thus achieving the purpose of automatic navigation homework.The main research content was divided into two points:Firstly,based on a two-dimensional plane coordinate system,the task path was planned through boundary coordinate points,and the task baseline was generated;Secondly,the movement characteristics of agricultural machinery were analyzed,and the mathematical models of dynamics and kinematics of agri-cultural machinery were established.On this basis,the mathematical relationship between steering control and path track-ing was studied,and the tracking scheme based on the yaw angle control of agricultural machinery was proposed.At the same time,in order to reduce the amount of ARM calculation and improve the tracking effect,the fuzzy control idea was used to establish a fuzzy control query table,constructed fuzzy control rules for steering angle based on path deviation and heading error,and set membership functions for fuzzy input and output,simplifying complex operations into simple table lookup operations.The test showed that the initialization time of the model car system was 4.4 s,at an average speed of 0.618 m/s,the lateral deviation of path tracking did not exceed 5.4 cm.关键词
农机自动驾驶/单片机/路径规划/路径追踪/模糊控制Key words
automatic driving of agricultural machinery/single chip microcomputer/path planning/path tracking/fuzzy control分类
农业工程引用本文复制引用
余科松,武志明,马玮..农机轮式机器人自动驾驶控制研究及试验[J].农机化研究,2025,47(7):271-278,8.基金项目
山西省重点研发项目(201903D221029) （201903D221029）
