Model-free tracking control of complex dynamical trajectories with machine learning

TL;DR

This paper introduces a model-free machine learning approach using reservoir computing for controlling complex robotic trajectories with partial observations, demonstrating robustness and effectiveness across various signals.

Contribution

It presents a novel reservoir computing-based control framework that operates without a full system model, using stochastic training with partial state observations.

Findings

Effective control of periodic and chaotic signals

Robustness against noise and disturbances

No need for complete system modeling

Abstract

Nonlinear tracking control enabling a dynamical system to track a desired trajectory is fundamental to robotics, serving a wide range of civil and defense applications. In control engineering, designing tracking control requires complete knowledge of the system model and equations. We develop a model-free, machine-learning framework to control a two-arm robotic manipulator using only partially observed states, where the controller is realized by reservoir computing. Stochastic input is exploited for training, which consists of the observed partial state vector as the first and its immediate future as the second component so that the neural machine regards the latter as the future state of the former. In the testing (deployment) phase, the immediate-future component is replaced by the desired observational vector from the reference trajectory. We demonstrate the effectiveness of the control framework using a variety of periodic and chaotic signals, and establish its robustness against measurement noise, disturbances, and uncertainties.