基于多变量时间序列的接触状态聚类分析

Contact State Clustering Analysis Based on Multivariate Time Series

针对机器人轴孔装配任务中接触状态的分类问题,该文提出了一种基于多变量时间序列的聚类方法。该方法利用深度时间聚类网络对装配过程中的接触状态变量进行编码,然后使用复杂度不变性度量对时间序列片段进行划分。该方法避免了对接触过程进行准静态分析,因此在实际中具有一定的通用性。并且利用时间序列的方式有利于提取接触状态变量的时间关联特性,从而使得聚类的结果更加鲁棒。实验结果和预期一致,验证了该算法的正确性和有效性。

Aiming at the classification problem of the contact state in the robot peg-in-hole task,this paper proposes a clustering method based on the multivariate time series.This method uses a deep temporal clustering network to encode the contact state variables in the assembly process,and then a complexity-invariant distance measure is used to classify the time series fragments.This method avoids the quasi-static analysis of the contact process and thus has a certain generality in practice.And the use of time series is beneficial to extract the timerelated characteristics of contact state variables,which can make the clustering results more robust.The experimental results are consistent with expectations,indicating the theoretical correctness and effectiveness of the proposed algorithm.