首页|Reports from School of Computer Science Add New Study Findings to Research in Robotics (Dust detection and cleanliness assessment based on S-YOLOv5s for NPP reactor containment wall-climbing cleaning robot)
Reports from School of Computer Science Add New Study Findings to Research in Robotics (Dust detection and cleanliness assessment based on S-YOLOv5s for NPP reactor containment wall-climbing cleaning robot)
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 DailyNews Daily News – Current study results on robotics have been published. According to news reportingfrom the School of Computer Science by NewsRx journalists, research stated, “NPP reactor containmentdust can easily turn into radioactive dust, endangering staff health and the environment.”The news correspondents obtained a quote from the research from School of Computer Science: “However,the nuclear reactor containment wall-climbing cleaning robot cleans blindly without the ability to cleanthe dust in a timely and thoroughly. In this paper, ShuffleNetV2-YOLOv5s (S-YOLOv5s) model is proposedto solve the problem of wall-climbing robots unable to detect different categories of dust in time. The useof ShuffleNetV2 in the backbone of the network not only ensures a large number of characterized channelsand a large network capacity, but also reduces the complexity of the model; SIoU is chosen for the lossfunction to improve the model accuracy. Then, planar cleaning index (PCI) is proposed by combining theresults of S-YOLOv5s to evaluate whether the wall-climbing cleaning robot cleans thoroughly. Comparedto other methods, PCI considers amount and area occupation of different classes of dust. The dust dataset is collected to train the designed model, and the model size is reduced to 14 % of the original model,and the FPS is 7.313 higher than the original model.”
School of Computer ScienceEmerging TechnologiesMachine LearningRobotRobotics
NETL
NSTL
