首页|Studies from Chang'an University Describe New Findings in Robotics (Skeleton-rgb Integrated Highly Similar Human Action Prediction In Human-robot Collaborative Assembly)
Studies from Chang'an University Describe New Findings in Robotics (Skeleton-rgb Integrated Highly Similar Human Action Prediction In Human-robot Collaborative Assembly)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ro botics. According to news reporting originating in Xi'an,People's Republic of C hina,by NewsRx journalists,research stated,"Human-robot collaborative assembl y (HRCA) combines the flexibility and adaptability of humans with the efficiency and reliability of robots during collaborative assembly operations,which facil itates complex product assembly in the mass personalisation paradigm. The cognit ive ability of robots to recognise and predict human actions and make responses accordingly is essential but currently still limited,especially when facing hig hly similar human actions." Financial supporters for this research include China Postdoctoral Science Founda tion,National Natural Science Foundation of China (NSFC),Scientists & Engineers Team Project of Shaanxi Province,Swedish Research Council,Swedish Re search Council. The news reporters obtained a quote from the research from Chang'an University,"To improve the cognitive ability of robots in HRCA,firstly,a two-stage skelet on-RGB integrated model focusing on human-parts interaction is proposed to recog nise highly similar human actions. Specifically,it consists of a feature guidan ce module and a feature fusion module,which can balance the accuracy and effici ency of human action recognition. Secondly,an online prediction approach is dev eloped to predict human actions ahead of schedule,which includes a pre-trained skeleton-RGB integrated model and a preprocessing module. Thirdly,considering t he positioning accuracy of the parts to be assembled and the continuous update o f human actions,a dynamic response scheme of the robot is designed. Finally,th e feasibility and effectiveness of the proposed model and approach are verified by a case study of a worm-gear decelerator assembly. The experimental results de monstrate that the proposed model achieves precise human action recognition with a high accuracy of 93.75% and a lower computational cost. Specifi cally,only 15 frames from a skeleton stream and 5 frames (less than 16 frames i n general) from an RGB video stream are adopted. Moreover,it only takes 1.026 s to achieve online human action prediction based on the proposed prediction meth od. The dynamic response scheme of the robot is also proven to be feasible."
Xi'anPeople's Republic of ChinaAsiaEmerging TechnologiesMachine LearningNano-robotRobotRoboticsChang'an University
NETL
NSTL
