DOI：10.3969/j.issn.1672-3872.2025.10.006
基金项目：大学生创新创业训练计划项目“基于yolo系列深度学习的辣椒采摘养护一体机”（202410566009）；广东海洋大学深蓝智能机电产品创新团队（CXTD2023009）
作 者：刘锦辉 2，3 ，余 江 1，3 ，熊铎云 1，3 ，林钰贵 2，3 ，徐芷婷 1，3 ，董振烨 1，3
（1. 广东海洋大学机械工程学院，广东 湛江 524088；2. 广东海洋大学电子与信息工程学院，广东 湛江 524088；3. 广东海洋大学深蓝智能机电产品创新团队，广东 湛江 524088）
摘 要：【目的】解决传统辣椒采摘机器人存在的控制复杂、采摘精度低、成本高、无法满足大规模作业的问题。【方法】介绍了一种基于嵌入式系统的辣椒采摘机器人，首先使用D-H参数法对机械手进行运动学分析，优化运动控制；其次采用STM32单片机作为主控板，结合YOLOv5视觉识别算法，实现对辣椒的精准识别与定位；最后通过二自由度机械手与三轴传动机构实现协同控制，同时引入激光测距模块，实现末端位置的精确定位与操作。【结果】通过现场实地作业测试，该机器人具备高效的辣椒识别与采摘能力，在运动学模型与控制算法优化后，机械手操作更加精准，能够提升采摘效率并降低生产成本。【结论】本研究具有广阔的应用前景，有助于采摘机器人在农业领域的推广和应用，为农业现代化的实现提供科技助力。
关键词：辣椒采摘；嵌入式系统；运行学分析；视觉识别；多轴协同
Design of a Chili-Picking Robot Based on an Embedded System
Author:Liu Jinhui2,3, Yu Jiang1,3, Xiong Duoyun1,3, Lin Yugui2,3, Xu Zhiting1,3, Dong Zhenye1,3
(1.School of Mechanical Engineering, Guangdong Ocean University, Zhanjiang 524088, China; 2.School of Electronic and Information Engineering, Guangdong Ocean University, Zhanjiang 524088, China; 3.Robotics Laboratory Innovation Team in Guangdong Ocean University, Zhanjiang 524088, China)
Abstract: [Objective] To solve the problems of complex control, low picking accuracy, high cost, and inability to meet large-scale operations of traditional pepper picking robots. [Method] Introduces a chili picking robot based on an embedded system. Firstly, the D-H parameter method is used to analyze the kinematics of the robotic arm and optimize the motion control; Secondly, STM32 microcontroller is used as the main control board, combined with YOLOv5 visual recognition algorithm, to achieve precise recognition and positioning of chili peppers; Finally, collaborative control is achieved through a two degree of freedom robotic arm and a three-axis transmission mechanism, while introducing a laser ranging module to achieve precise positioning and operation of the end position. [Result] Through on-site operation testing, the robot has efficient chili recognition and picking capabilities. After optimizing the kinematic model and control algorithm, the robotic arm operation is more precise, which can improve picking efficiency and reduce production costs. [Conclusion] This study has broad application prospects and will contribute to the promotion and application of harvesting robots in the agricultural field, providing technological assistance for the realization of agricultural modernization.
Keywords: chili picking; embedded systems; kinematic analysis; visual recognition; multi-axis coordination.
引文信息：[1]刘锦辉，余江，熊铎云，等.基于嵌入式系统的辣椒采摘机器人设计[J].南方农机，2025，56(10)：24-27+32.
查看全文请下载PDF文件↓
