首页|Findings from University of the West of England Provide New Insights into Roboti cs (Multifingered Grasp Planning Based On Gaussian Process Implicit Surface and Its Partial Differentials)
Findings from University of the West of England Provide New Insights into Roboti cs (Multifingered Grasp Planning Based On Gaussian Process Implicit Surface and Its Partial Differentials)
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-Fresh data on Robotics are presented i n a new report. According to news reporting out of Bristol, United Kingdom, by N ewsRx editors, research stated, "Grasp planning for irregularly shaped objects u sing multifingered robotic hands is challenging due to the high dimensionality o f the search space and a lack of proper modeling methods for object geometry. To address these issues, we propose a grasp planning approach based on Gaussian pr ocess implicit surfaces (GPIS)." Our news journalists obtained a quote from the research from the University of t he West of England, "To explore the object geometry and identify feasible contac t positions and normals, our method introduces several moving points called attr actors along with a dynamical system. The dynamical system constrains and guides the attractors with the partial differentials of the GPIS, which can be conveni ently obtained through the linear expression of a GP. The hand motion is also gu ided by the dynamical system. In addition, an inverse kinematics method, which c onsiders finger joint limits, is developed to simultaneously adjust the palm pos e and finger joint angles for a feasible grasp. The performance of our method is demonstrated using various robotic hands and objects, and real robot experiment s are conducted to validate the planned grasp's effectiveness in reality."
BristolUnited KingdomEuropeEmergin g TechnologiesGaussian ProcessesMachine LearningRoboticsRobotsUniversi ty of the West of England
NETL
NSTL
