A real-time GP based MPC for quadcopters with unknown disturbances

TL;DR

This paper introduces a real-time Gaussian Process-based Model Predictive Control framework for quadcopters that can learn and adapt to unknown disturbances online, significantly improving performance while maintaining computational efficiency.

Contribution

It presents a novel online learning framework using state-space GPs for quadcopters, enabling disturbance prediction and MPC integration in real-time.

Findings

Achieves disturbance prediction within milliseconds.

Enhances quadcopter control performance in simulations.

Proves real-time feasibility on Raspberry Pi 4 B.

Abstract

Gaussian Process (GP) regressions have proven to be a valuable tool to predict disturbances and model mismatches and incorporate this information into a Model Predictive Control (MPC) prediction. Unfortunately, the computational complexity of inference and learning on classical GPs scales cubically, which is intractable for real-time applications. Thus GPs are commonly trained offline, which is not suited for learning disturbances as their dynamics may vary with time. Recently, state-space formulation of GPs has been introduced, allowing inference and learning with linear computational complexity. This paper presents a framework that enables online learning of disturbance dynamics on quadcopters, which can be executed within milliseconds using a state-space formulation of GPs. The obtained disturbance predictions are combined with MPC leading to a significant performance increase in simulations with jMAVSim. The computational burden is evaluated on a Raspberry Pi 4 B to prove the real-time applicability.