基于人眼检测跟踪法的教育机器人人机交互分析  

Human-computer interaction analysis of educational robot based on eye detection and tracking method

作　　者：赵小华 ZHAO Xiaohua(Xianyang Vocational&Technical College,Xianyang Shaanxi 712000,China)

机构地区：[1]咸阳职业技术学院,陕西咸阳712000

出　　处：《自动化与仪器仪表》2024年第12期243-247,共5页Automation & Instrumentation

基　　金：咸阳职业技术学院教育教学改革研究项目《元宇宙技术下高校教育教学数字化转型探究》(2024JYB11)。

摘　　要：传统的教育机器人只能执行预设的任务,无法根据学生的实际情况进行灵活调整,因此,研究设计一款基于人眼检测跟踪算法与人机交互技术的教育机器人。研究利用平均合成精密滤波人眼定位算法识别学生人脸与姿态,采用Leap Motion传感器实现与学生的自然互动。研究结果表明,研究所提算法的精准度、计算复杂度和模型性能分别为0.93、0.88、0.92,说明在多个维度上该算法都表现出了优秀的性能,能够更好地满足教育机器人的功能需求。该教育机器人对学生各种表情和姿态的识别率均保持在90%以上,说明该教育机器人能够准确识别学生状态,有效适应不同教育场景,提供精准教育服务。研究推动教育技术的创新与发展,提升教育机器人的智能水平,为教育实践提供有力支持。Traditional educational robots can only perform preset tasks and cannot be flexibly adjusted according to the actual situation of students.Therefore,an educational robot based on human eye detection and tracking algorithm and human-computer interaction technology is designed.In this paper,the average synthetic precision filter eye positioning algorithm is used to recognize the face and posture of students,and the Leap Motion sensor is used to realize the natural interaction with students.The results show that the accuracy,computational complexity and model performance of the proposed algorithm are 0.93,0.88 and 0.92,respectively,indicating that the algorithm has excellent performance in multiple dimensions and can better meet the functional requirements of educational robots.The recognition rate of the educational robot for various expressions and gestures of students is maintained above 90%,indicating that the educational robot can accurately identify the state of students,effectively adapt to different educational scenes,and provide precise education services.The educational robot has excellent performance in the field of education.

关 键 词：人眼检测跟踪法 教育机器人 人机交互 深度确定性策略梯度 Leap Motion传感器 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]