%0 Journal Article
%T 基于Kinect的配电作业机器人智能人机交互方法<br>Intelligent interaction method for power distribution robot based on Kinect
%A 张冕
%A 黄颖
%A 梅海艺
%A 郭毓&lt
%A br&gt
%A Mian ZHANG
%A Ying HUANG
%A Haiyi MEI
%A Yu GUO
%J 山东大学学报（工学版）
%D 2018
%R 10.6040/j.issn.1672-3961.0.2018.228
%X 为实现操作人员与配电作业机器人的自然交互,提出一种基于Kinect手势识别的配电作业机器人智能人机交互方法。通过Kinect的深度信息及骨骼信息对操作人员的手势进行分割,选取几何不变矩Hu矩作为手势特征,采用支持向量机(support vector machine, SVM)的机器学习方法分类识别操作人员的手势。将手势映射为机器人的运动,通过手势对机器人进行运动控制。试验结果验证了本研究所提的配电作业机器人智能人机交互方法的可行性。<br>In order to realize natural interaction between the operator and the live-line working robot, an intelligent man-machine interaction method based on the Kinect gesture recognition was proposed. Based on the Kinect's depth information and skeleton information, the operator's gesture was segmented, the geometric moment Hu moment was selected as the gesture feature, and the machine learning method of SVM was used to classify and identify the operator's gesture. The gestures were mapped to the motion of the robot, and the motion control of the robot was realized by the gesture. The experimental results verified the feasibility of the intelligent human-computer interaction method of the power distribution robot.
%K 配电作业机器人
%K 智能人机交互
%K 机器学习
%K 手势分割
%K 手势识别
%K 运动控制
%K &lt
%K br&gt
%K live-line working robot
%K intelligent human-computer interaction
%K machine learning
%K gesture segmentation
%K gesture recognition
%K motion control
%U http://gxbwk.njournal.sdu.edu.cn/CN/10.6040/j.issn.1672-3961.0.2018.228