Stepwise Model Reconstruction of Robotic Manipulator Based on Data-Driven Method

TL;DR

This paper introduces a data-driven approach combining K-means clustering and SINDy to reconstruct robotic manipulator dynamics, reducing model complexity and noise sensitivity, and validating effectiveness through simulations and experiments.

Contribution

It presents a novel stepwise reconstruction method using data classification and sparse identification, improving model accuracy and applicability for multi-degree-of-freedom manipulators.

Findings

Reduces basis function library complexity

Decreases data noise impact on regression

Proves effectiveness through experiments

Abstract

Research on dynamics of robotic manipulators provides promising support for model-based control. In general, rigorous first-principles-based dynamics modeling and accurate identification of mechanism parameters are critical to achieving high precision in model-based control, while data-driven model reconstruction provides alternative approaches of the above process. Taking the level of activation of data as an indicator, this paper classifies the collected robotic manipulator data by means of K-means clustering algorithm. With the fundamental prior knowledge, we find the corresponding dynamical properties behind the classified data separately. Afterwards, the sparse identification of nonlinear dynamics (SINDy) method is used to reconstruct the dynamics model of the robotic manipulator step by step according to the activation level of the classified data. The simulation results show that the proposed method not only reduces the complexity of the basis function library, enabling the application of SINDy method to multi-degree-of-freedom robotic manipulators, but also decreases the influence of data noise on the regression results. Finally, the dynamic control based on the reconfigured model is deployed on the experimental platform, and the experimental results prove the effectiveness of the proposed method.