Model Predictive Control of Nonlinear Latent Force Models: A Scenario-Based Approach

TL;DR

This paper develops a scenario-based model predictive control method for nonlinear latent force models with Gaussian process uncertainty, enabling effective autonomous vehicle motion planning and potentially benefiting broader robotics control tasks.

Contribution

It introduces a novel scenario-based MPC framework for nonlinear latent force models using Gaussian process state-space representation, enhancing control under uncertainty.

Findings

Effective in autonomous vehicle motion planning

Handles nonlinear uncertainties with Gaussian processes

Shows promising simulation results

Abstract

Control of nonlinear uncertain systems is a common challenge in the robotics field. Nonlinear latent force models, which incorporate latent uncertainty characterized as Gaussian processes, carry the promise of representing such systems effectively, and we focus on the control design for them in this work. To enable the design, we adopt the state-space representation of a Gaussian process to recast the nonlinear latent force model and thus build the ability to predict the future state and uncertainty concurrently. Using this feature, a stochastic model predictive control problem is formulated. To derive a computational algorithm for the problem, we use the scenario-based approach to formulate a deterministic approximation of the stochastic optimization. We evaluate the resultant scenario-based model predictive control approach through a simulation study based on motion planning of an autonomous vehicle, which shows much effectiveness. The proposed approach can find prospective use in various other robotics applications.