广东东软学院本科毕业设计（论文） 智能移动垃圾分拣机器人 The intelligent mobile garbage sorting robot 内容摘要本课题探讨一种基于机器视觉识别技术的智能移动垃圾分拣机器人系统。该系统实现了简单背景下进行路径规划遍历待清扫区域，目标对象的识别和定位。系统采用深度学习的方法实现简单背景下目标垃圾的真实性识别，由目标检测模块、导航模块以及分拣控制模块三大部分组成。自动导航基于 ROS 分布式框架，采用激光雷达采集清扫区域环境信息，运用扫描匹配算法的 SLAM 功能，通过最优路径算法进行路径规划遍历清扫区域。机器人遍历过程中，目标检测模块通过 SSD_ MobileNet_V2 深度学习算法对摄像头获取的图像进行目标检测以及目标分类，获取目标的坐标及其角度信息作为分拣控制模块的输入信息，控制分拣控制模块执行垃圾抓取任务。关键词：机器视觉 垃圾分拣 深度学习 自动导航1广东东软学院本科毕业设计（论文）AbstractThis paper discusses an intelligent mobile garbage sorting robot system based on machine vision recognition technology. The system realizes the path planning, traversing the area to be cleaned, and identifying and locating the target object in a simple background. The system uses the method of deep learning to realize the authenticity identification of the target garbage in the simple background, which is composed of three parts: the target identification unit, navigation unit and the sorting control unit. Based on the ROS distributed framework, automatic navigation uses lidar to collect the environment information of the cleaning area, uses the slam function of scanning matching algorithm, and uses the optimal path algorithm to plan and traverse the cleaning area. In the process of robot traversal, the target recognition unit detects and classifies the image acquired by the camera through the SSD_MobileNet_V2 deep learning algorithm, obtains the coordinates and angle information of the target as the input information of the sorting...
VIP
