首页|Studies from Chinese Academy of Sciences Further Understanding of Robotics (A No vel Positioning Accuracy Improvement Method for Polishing Robot Based On Levenbe rg-marquardt and Opposition-based Learning Squirrel Search Algorithm)
Studies from Chinese Academy of Sciences Further Understanding of Robotics (A No vel Positioning Accuracy Improvement Method for Polishing Robot Based On Levenbe rg-marquardt and Opposition-based Learning Squirrel Search Algorithm)
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-Investigators publish new report on Robotics. Acc ording to news reporting originating from Chengdu, People's Republic of China, b y NewsRx correspondents, research stated, "Achieving highprecision manufacturin g of optical components requires improving the absolute positioning accuracy of the robot to the highest possible level. Identifying the robot's kinematic param eters and compensating for kinematic errors are effective methods for improving the robot's positioning accuracy." Our news editors obtained a quote from the research from the Chinese Academy of Sciences, "This paper proposes a hybrid algorithm that combines the Levenberg-Ma rquardt algorithm and an oppositionbased learning squirrel search algorithm to identify the kinematic parameters of a polishing robot. Firstly, the Levenberg-M arquardt algorithm is utilized to solve the suboptimal values of kinematic param eter deviations. Secondly, an opposition-based learning strategy is integrated i nto the standard squirrel search algorithm to increase the diversity of the popu lation and prevent the population from getting stuck in local optima. The subopt imal values obtained by the Levenberg-Marquardt algorithm are subsequently used as the central values to generate the initial population for the opposition-base d learning squirrel search algorithm, which helps identify more accurate kinemat ic parameter deviations. Ultimately, the kinematic parameters of the robot are e ffectively calibration. The calibration experimental results showed that the pro posed method achieved a high level of calibration accuracy, resulting in a 62.61 % improvement in absolute positioning error compared to before cal ibration." According to the news editors, the research concluded: "Offline machining experi ments have validated the effectiveness of LM-OBLSSA in reducing deviations in th e dwell points of optical components during the machining process."
ChengduPeople's Republic of ChinaAsi aAlgorithmsEmerging TechnologiesMachine LearningRobotRoboticsSearch AlgorithmsChinese Academy of Sciences
NETL
NSTL
