基于深度摄像头的人手控制机械臂装置设计  

Design of manual control manipulator device based on depth camera

作　　者：章彬 巢明[2] 马驰[2] 崔承毅[2] 董元涛 王开宇[2] ZHANG Bin;CHAO Ming;MA Chi;CUI Chengyi;DONG Yuantao;WANG Kaiyu(School of Microelectronics,Dalian University of Technology,Dalian 116600,China;Electrical and Electronic National Experimental Teaching Demonstration Center,Dalian University of Technolo-gy,Dalian 116024,China;Faculty of Electronic Information and Electrical Engineering,Dalian U-niversity of Technology,Dalian 116024,China)

机构地区：[1]大连理工大学微电子学院,辽宁大连116600 [2]大连理工大学电工电子国家级实验教学示范中心,辽宁大连116024 [3]大连理工大学电子信息与电气工程学部,辽宁大连116024

出　　处：《实验室科学》2022年第4期81-85,共5页Laboratory Science

基　　金：中国高等教育理科教育专业委员会高等理科教育研究课题项目(项目编号:02020);大连理工大学“电工电子创新实践基地与专业深度融合的建设与研究”重点研究项目(项目编号:ZD2020002)。

摘　　要：随着计算机技术的不断突破,人机交互在社会、经济和国家安全等领域中扮演着越来越重要的角色。在这样的背景下,利用Intel RealSense F200深度摄像头和LOBOT机械臂,设计了一套可以识别部分人手动作并且能让机械臂同步相同动作的系统装置。其优点在于用户不需要穿戴任何设备,只需在摄像头前做相应的动作,就可以实现对机械臂的实时、精准控制,并且用户可以在窗口界面中观察到人手的深度图像和关节的坐标信息,交互性和实时性强。同时,利用深度摄像头也为二次开发提供了方便,为延时要求更低、精度要求更高、准确性要求更强的开发工作提供了帮助。With the continuous breakthrough of computer technology, human-computer interaction plays an increasingly important role in the fields of society, economy and national security. In this context, using the Intel RealSense F200 depth camera and LOBOT robot arm to design a system device that can recognize part of the human hand movement and allow the robot arm to synchronize the same action. The advantage of this device is that the user don’t need to wear any equipment, and only needs to perform corresponding actions in front of the camera, real-time and precise control of the robot arm can be realized, and the user can observe the depth image of the human hand and the coordinate information of the joint in the window interface, which is highly interactive and real-time. At the same time, the use of the depth camera also provides convenience for secondary development, and provides assistance for development work with lower delay requirements, higher accuracy requirements, and higher accuracy requirements.

关 键 词：深度摄像头 机械臂 人机交互 手势识别 

分 类 号：TP241[自动化与计算机技术—检测技术与自动化装置] TP391.41[自动化与计算机技术—控制科学与工程]