典型文献
A Visual-Based Gesture Prediction Framework Applied in Social Robots
文献摘要：
In daily life, people use their hands in various ways for most daily activities. There are many applications based on the position, direction, and joints of the hand, including gesture recognition, gesture prediction, robotics and so on. This paper proposes a gesture prediction system that uses hand joint coordinate features collected by the Leap Motion to predict dynamic hand gestures. The model is applied to the NAO robot to verify the effectiveness of the proposed method. First of all, in order to reduce jitter or jump generated in the process of data acquisition by the Leap Motion, the Kalman filter is applied to the original data. Then some new feature descriptors are introduced. The length feature, angle feature and angular velocity feature are extracted from the filtered data. These features are fed into the long-short time memory recurrent neural network (LSTM-RNN) with different combinations. Experimental results show that the combination of coordinate, length and angle features achieves the highest accuracy of 99.31％, and it can also run in real time. Finally, the trained model is applied to the NAO robot to play the finger-guessing game. Based on the predicted gesture, the NAO robot can respond in advance.
文献关键词：
中图分类号：
作者姓名：
Bixiao Wu;Junpei Zhong;Chenguang Yang
作者机构：
College of Automation Science and Engineering,South China University of Technology,Guangzhou 510640,China;Shien-Ming Wu School of Intelligent Engineering,South China University of Technology,Guangzhou 511442,China
文献出处：
引用格式：
[1]Bixiao Wu;Junpei Zhong;Chenguang Yang-.A Visual-Based Gesture Prediction Framework Applied in Social Robots)[J].自动化学报（英文版）,2022(03):510-519
A类：
B类：
Visual,Based,Gesture,Prediction,Framework,Applied,Social,Robots,In,daily,life,people,their,hands,various,ways,most,activities,There,are,many,applications,position,direction,joints,including,recognition,prediction,robotics,This,paper,proposes,system,that,uses,coordinate,features,collected,by,Leap,Motion,dynamic,gestures,model,applied,NAO,verify,effectiveness,proposed,method,First,order,reduce,jitter,jump,generated,process,data,acquisition,Kalman,original,Then,some,new,descriptors,introduced,length,angle,angular,velocity,extracted,from,filtered,These,fed,into,long,short,memory,recurrent,neural,network,RNN,different,combinations,Experimental,results,show,achieves,highest,accuracy,can,also,run,real,Finally,trained,play,finger,guessing,game,predicted,respond,advance
AB值：
0.581037
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
