On Space-Filling Input Design for Nonlinear Dynamic Model Learning: A Gaussian Process Approach

Yuhan Liu, Máté Kiss, Roland Tóth, Maarten Schoukens

Abstract

In nonlinear system identification, the quality of the learned model is heavily dependent on the coverage of the experimental data across the system's operating space. This paper introduces a novel input design strategy that leverages Gaussian Processes (GPs) to generate "space-filling" signals. By minimizing the average GP posterior variance across a predefined set of anchor points, the proposed method ensures that the resulting data thoroughly explores the region of interest. We demonstrate that this approach provides a smooth, differentiable cost function for optimization and guarantees specific space-filling properties. Evaluations on simulated linear and nonlinear systems show that the GP-based design significantly outperforms standard techniques like Schroeder phase multisines in terms of state-space coverage.

Introduction

Building accurate mathematical models of nonlinear systems from experimental data—a process known as system identification—remains a significant challenge. While input design for linear systems is well-understood through the maximization of the Fisher Information Matrix, nonlinear systems require a different approach. Because nonlinear behavior is state-dependent, a model's performance is often limited by generalization error: the failure to accurately predict behavior in regions of the state space where data is sparse.

To address this, researchers advocate for "space-filling" inputs that force the system to visit a wide variety of state and input combinations. However, existing methods often struggle with non-smooth cost functions or are limited to specific signal types. This paper proposes a flexible, GP-based framework to design smooth, space-filling trajectories for nonlinear systems.

Methodology

The core innovation of this work is the use of Gaussian Processes as a proxy for measuring space-filling quality. Rather than modeling the system itself, a GP prior is placed on a hypothetical system model.

Anchor Points and Variance Proxy

The strategy involves defining a grid of "anchor points" within the desired region of interest (ROI). In GP regression, the posterior variance at any given point serves as a measure of uncertainty; it is high in regions far from existing data and low near data points. The authors define a cost function as the average GP posterior variance across all anchor points.

Optimization and Space-Filling Guarantees

Minimizing this cost function effectively pushes the system's trajectory to pass near the anchor points. Because the GP variance is smooth and differentiable, standard gradient-based optimization can be used to tune input signal parameters, such as the amplitudes and phases of a multisine wave.

Space-filling performance as a function of the number of anchor points $M$. The plots illustrate how increasing the density of anchor points leads to a lower filling distance $\rho$, ensuring better coverage of the ROI.

The paper provides a mathematical proof that if the cost function reaches zero, the dataset satisfies the $\epsilon$-space filling property, meaning every point in the ROI is within a distance $\epsilon$ of a collected data point.

Experimental Evaluation

The method was tested on two simulated systems:

  1. Linear Time-Invariant (LTI) System: A second-order system used to validate the theoretical relationship between anchor point density and coverage.
  2. Nonlinear Mass-Spring-Damper System: A complex 3D model representing a mass on a rail connected to a ceiling spring. This system served as a benchmark for handling nonlinearities and spectral constraints.

Results

The GP-optimized inputs were compared against unoptimized signals and the industry-standard Schroeder phase multisine.

In the nonlinear mass-spring-damper case, the "filling distance" ($\rho$)—a metric where lower values indicate better coverage—was reduced from an initial 1.2756 to 0.3029 after optimization. This significantly outperformed the Schroeder multisine, which achieved a filling distance of 1.1811.

Visualization of the initial (blue) and GP-optimized (orange) data points within the 3D region of interest $\tilde{Z}$ for the nonlinear mass-spring-damper system. The optimized data shows significantly improved coverage.

Discussion and Conclusion

The GP-based approach offers several advantages:

  • Smooth Energy Landscape: Unlike distance-based metrics, GP variance provides a smooth surface for optimization.
  • Flexibility: The method can optimize various signal classes, including multisines and piecewise constant steps.
  • Distribution Agnostic: It focuses on coverage rather than forcing data into a specific probability distribution.

However, limitations remain. The computational cost of GP variance scales cubically ($O(N^3)$) with the number of data points, which may limit its use for very long experiments. Additionally, the method requires a prior model of the system to simulate trajectories during the design phase. Future work will focus on scaling the approach for high-dimensional systems and evaluating its direct impact on the accuracy of various nonlinear identification algorithms.

Summary updated

Abstract

While optimal input design for linear systems has been well-established, no systematic approach exists for nonlinear systems where robustness to extrapolation/interpolation errors is prioritized over minimizing estimated parameter variance. To address this issue, we develop a novel space-filling input design strategy for nonlinear system identification that ensures data coverage of a given region of interest. By placing a Gaussian Process (GP) prior on the joint input-state space, the proposed strategy leverages the GP posterior variance to construct a cost function that promotes space-filling input design. Consequently, this enables maximization of the coverage in the region of interest, thereby facilitating the generation of informative datasets. Furthermore, we theoretically prove that minimization of the cost function implies the space-filling property of the obtained data. Effectiveness of the proposed strategy is demonstrated on both an academic and a mass-spring-damper example, highlighting its potential practical impact on efficient exploration of the dynamics of nonlinear systems.
BibTeX
@article{liu2025space,
  author = {Yuhan Liu and Máté Kiss and Roland Tóth and Maarten Schoukens},
  title = {{On Space-Filling Input Design for Nonlinear Dynamic Model Learning: A Gaussian Process Approach}},
  journal = {IEEE Control. Syst. Lett},
  year = {2025},
  doi = {10.1109/lcsys.2025.3582509},
}
Figure