基于KINECT和全局视觉的机器人避碰研究  

Robot Collision Avoidance Research Based on KINECT and Comprehensive Surveillance Video

作　　者：杨晓宁[1] 叶锦华[1] 

机构地区：[1]福州大学机械工程及自动化学院,福建福州350108

出　　处：《机械制造与自动化》2016年第5期156-160,共5页Machine Building & Automation

基　　金：福州大学科研启动项目(510078);福州大学科技发展基金项目(650053)

摘　　要：为了提高工业机器人作业过程中的安全性,在六自由度工业机器人平台上,提出了一种全局视频和Kinect相结合的人体运动检测与预测方法,并进一步实时控制工业机器人的避碰运动,从而确保人在机器人工作空间的安全性。首先利用Kinect人体骨架检测技术精确检测出人体位置信息,利用帧连续卡尔曼滤波器预测肢体运动;然后通过全局视觉检测出机器人运动空间内包括人在内的障碍物,依据检测结果判别危险性,并针对非人体障碍物和不同人体部位及运动趋势,采取相应的运动控制措施。实验结果证明,该方法能够实时、有效地提高机器人工作的安全性。To improve the safety of the industrial robot in work,this paper presents a real-time collision avoidance approach combined with the vision technology and the human skeleton detection technology of Kinect,based on the industrial robot platform with six degrees of freedom to controll the robot in real-time to ensure the personal safety in the robot workspace. The Kinect is used to detect the positional information of the skeleton and then the body movement is predicted by the Kalman Filter with the continuous frames. The obstacle and bodies position are detected by the comprehensive surveillance video. The collision danger is judged based on the detected information of the Kinect and the video,and then the corresponding control measures are used to avoid the collision.The experimental results demonstrate the effectiveness of the system in improving the safety of the industrial robot.

关 键 词：工业机器人 人体骨架检测 卡尔曼滤波 全局视觉 

分 类 号：TP242.2[自动化与计算机技术—检测技术与自动化装置]