A Framework for Data Driven Dynamic Modeling of Serial Manipulators

Abstract

Robot dynamic modeling and parameter identification are essential for many analyses. High-fidelity multi-body dynamics simulators can model the robot's dynamic behavior, but they can't identify the robot's non-linear dynamic model needed for controller design. This study proposes a three-step machine-learning framework for extracting the dynamic equations of serial manipulators from data. This framework consists of three steps. Initially, a library of candidate functions is constructed, together with a data set based on the robot's unforced response. Secondly, the best models that can represent dynamic systems for each candidate function utilizing the training data set are then obtained using the SINDy-PI algorithm and Akaike Information Criterion (AIC). Through the MSE and test data, those best models will be reduced to get the functions that best describe the dynamic system. Finally, the dynamic equations that characterize the system are derived using the SINDy algorithm, including the applied force or torque. The proposed framework was tested on three case studies - double pendulum, two-link of KUKA robot, and two-link of Stanford robot. The framework correctly determines the structure of the dynamic system and simultaneously accurately identifies its parameters. The framework was able to deal with an ill-conditioned system of equations that arises for complex robot configuration.