期刊文献+

室内环境中人穿携物品归属关系自主学习框架 预览

Self-learning framework for attribution relationship of people carrying objects under family environment
在线阅读 下载PDF
分享 导出
摘要 为了满足机器人个性化服务需求,使机器人可以根据不同的服务对象来选择专属物品进行任务的推理和规划,需要服务机器人具备自主获取人穿携物品与人的归属关系的能力.针对家庭环境下人穿携物品与人的归属关系获取问题,提出人穿携物品归属关系自主学习框架.采用基于物品检测模型SSD与人体姿态估计模型OpenPose相结合的人穿携物品检测定位方法,实现人穿携物品检测.利用基于迁移学习的卷积神经网络提取物品特征,通过后端分类器完成物品实例属性识别,使用人脸检测与识别模型MTCNN完成服务对象身份识别.通过归属关系自主学习策略,完成归属关系的自主学习.实验结果表明,提出的人穿携物品归属关系自主学习框架能够准确、高效地完成归属关系的学习,有效排除环境干扰因素对归属关系学习的影响,具有良好的准确性和鲁棒性. It is necessary for service robots to have the ability to independently obtain the attribution relationship between people and their carrying objects in order to satisfy the requirements of robot personalized service and enable robots to select exclusive objects to perform inference and planning according to different service individual. A self-learning framework for the attribution relationship between people and their carrying objects was proposed aiming at the problem of the attribution relationship between people carrying objects and people in the family environment.The method of detecting and locating people carrying objects was used based on the object detection model SSD and the human posture estimation model OpenPose in order to realize the detection of human carrying objects.The face detection and recognition model MTCNN were used to complete the service individual identification by extracting the objects features by convolutional neural network based on migration learning and using the backend classifier to complete the object instance attribute identification.The self-learning of the attribution relationship was completed through the self-learning strategy.The experimental results show that the proposed self-learning framework for attribution relationship of people carrying objects can accurately and efficiently complete the learning of attribution relationship,effectively eliminating the influence of environmental interference factors on attribution learning.The proposed framework has good accuracy and robustness.
作者 吴皓 李文静 田国会 陈兆伟 杨勇 WU Hao;LI Wen-jing;TIAN Guo-hui;CHEN Zhao-wei;YANG Yong(School of Control Science and Engineering,Shandong University,Jinan 250061,China;Jinan Haoyuan AutomaticControl System Engineering Limited Company,Jinan 250061,China)
出处 《浙江大学学报:工学版》 EI CAS CSCD 北大核心 2019年第7期1315-1322,共8页 Journal of Zhejiang University(Engineering Science)
基金 国家自然科学基金资助项目(62773239,U1813215) 山东省自然科学基金资助项目(ZR2017MF014) 山东省科技重大专项资助项目(2015ZDXX0101F03) 山东省重大研发计划资助项目(2015GGX103034).
关键词 服务机器人 个性化服务 深度学习 穿携物品 物品归属关系 service robot personalized service deep learning carrying object attribution relationship of objects
作者简介 吴皓(1972-),女,副教授,从事智能机器人的研究.orcid.org/0000-0001-6993-8863.E-mail:wh911@sdu.edu.cn;通信联系人:田国会,男,教授.orcid.org/0000-0001-8332-3064.E-mail:g.h.tian@sdu.edu.cn.
  • 相关文献
投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈