首页|Report Summarizes Androids Study Findings from University of Birmingham (Learnin g By Doing: a Dual-loop Implementation Architecture of Deep Active Learning and Human-machine Collaboration for Smart Robot Vision)
Report Summarizes Androids Study Findings from University of Birmingham (Learnin g By Doing: a Dual-loop Implementation Architecture of Deep Active Learning and Human-machine Collaboration for Smart Robot Vision)
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-Research findings on Robotics - Androi ds are discussed in a new report. According to news reporting from Birmingham, U nited Kingdom, by NewsRx journalists, research stated, "To develop vision system s for autonomous robotic disassembly, this paper presents a dual-loop implementa tion architecture that enables a robot vision system to learn from human vision in disassembly tasks. The architecture leverages human visual knowledge through a collaborative scheme named ‘learning-by-doing." Financial supporters for this research include Engineering & Physi cal Sciences Research Council (EPSRC), National Natural Science Foundation of Ch ina (NSFC), China Scholarship Council. The news correspondents obtained a quote from the research from the University o f Birmingham, "In the dual-loop implementation architecture, a human-robot colla borative disassembly loop containing autonomous perception, human-robot interact ion and autonomous execution processes is established to address perceptual chal lenges in disassembly tasks by introducing human operators wearing augmented rea lity (AR) glasses, while a deep active learning loop is designed to use human vi sual knowledge to develop robot vision through autonomous perception, human-robo t interaction and model learning processes. Considering uncertainties in the con ditions of products at the end of their service life, an objective ‘informativen ess' matrix integrating the label information and regional information is design ed for autonomous perception, and AR technology is utilised to improve the opera tional accuracy and efficiency of the human-robot interaction process. By sharin g the autonomous perception and humanrobot interaction processes, the two loops are simultaneously executed. To validate the capability of the proposed archite cture, a screw removal task was studied. The experiments demonstrated the capabi lity to accomplish challenging perceptual tasks and develop the perceptual abili ty of robots accurately, stably, and efficiently in disassembly processes."
BirminghamUnited KingdomEuropeAndr oidsAutonomous RobotEmerging TechnologiesHuman-Robot InteractionMachine LearningRobotRoboticsRobotsUniversity of Birmingham
NETL
NSTL
