首页|Research Data from University of Washington Update Understanding of Robotics (Ac tive Data-enabled Robot Learning of Elastic Workpiece Interactions)
Research Data from University of Washington Update Understanding of Robotics (Ac tive Data-enabled Robot Learning of Elastic Workpiece Interactions)
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 – New study results on robotics have bee n published. According to news reporting from the University of Washington by Ne wsRx journalists, research stated, “During manufacturing processes, such as clam ping and drilling of elastic structures, it is essential to maintain tool-workpi ece normality to minimize shear forces and torques, and thereby preventing damag e to the tool or the workpiece.” Our news reporters obtained a quote from the research from University of Washing ton: “The challenge arises in making precise model-based predictions of the rela tively large deformations that occur as the applied normal force (e.g., clamping force) is increased. However, precision deformation predictions are essential f or selecting the optimal robot pose that maintains force normality. Therefore, r ecent works have employed force-displacement measurements at each work location to determine the robot pose for maintaining tool normality. Nevertheless, this a pproach, which relies on local measurements at each work location and at each gr adual increment of the applied normal force, can be slow and consequently, time prohibitive. The main contributions of this work are to use: Gaussian Process me thods to learn the robot-pose map for force normality at unmeasured workpiece lo cations; active learning to optimally select and minimize the number of measurem ent locations needed for accurate learning of the robot-pose map.”
University of WashingtonEmerging Techn ologiesMachine LearningRobotRobotics
NETL
NSTL
