On Koopman-based surrogate models for non-holonomic robots

TL;DR

This paper investigates Koopman-based surrogate models for non-holonomic robots, analyzing their approximation quality and hyperparameter dependence through simulations and experiments to guide efficient model design.

Contribution

It provides the first systematic analysis of Koopman-based surrogate models for non-holonomic robots, including guidelines for data-efficient model design.

Findings

Hyperparameters significantly affect model accuracy

Simulation and experimental data validate the analysis

Guidelines improve surrogate model design for non-holonomic systems

Abstract

Data-driven surrogate models of dynamical systems based on the extended dynamic mode decomposition are nowadays well-established and widespread in applications. Further, for non-holonomic systems exhibiting a multiplicative coupling between states and controls, the usage of bi-linear surrogate models has proven beneficial. However, an in-depth analysis of the approximation quality and its dependence on different hyperparameters based on both simulation and experimental data is still missing. We investigate a differential-drive mobile robot to close this gap and provide first guidelines on the systematic design of data-efficient surrogate models.