Function Decomposition for Accelerating the Learning of Robot Kinematics

摘要：

This paper proposes an approach to reduces the number of movements that need to learn the inverse kinemati (IK)to a given accuracy. The large number of training samples such as robot movements required to attain an acceptable precision is the main drawback of example-based learning procedures to approximate the inverse kinemati. The approach is designed specifically to express the IK as a composition of learnable functions. We propose both Off-line and on-line training schemes to learn these component functions. The nearest neighbors and selforganizing map obtain experimental results show the time savings growing with the precision.

关键词： Function Decomposition inverse kinemati Robot

作者: Xiayu Mei Hao Min

作者单位: Machinery design, Manufacturing and Automation Huazhong University of Science and Technology Wuhan, China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer Engineering and Applications(2011第三届计算机工程与应用国际会议 ICCEA2011)

会议地点: 海口

会议语种:英文

页码: 370-374

在线出版日期: 2011-07-15（万方平台首次上网日期，不代表论文的发表时间）