ABSTRACT
This chapter proposes a novel force sensing and robotic learning algorithm based teaching interface for home-automated robot massagin. Dynamic movement primitive (DMP) is utilised to model and generalise the human-like movements. In order to learn from multiple demonstrations, Dynamic Time Warping (DTW) is used for the preprocessing of the data recorded on the robot platform, and Gaussian Mixture Model (GMM) is employed for the evaluation of DMP to generate multiple patterns after the completion of the teaching process. Movement is a necessary way to directly produce skill effects. The Expectation Maximisation (EM) algorithm can be used for parameter estimation provided that there is a relatively complex nonlinear interaction between the probability function and the template parameters, and the peak value cannot be determined according to the standard probability estimation process.
