Data-Driven MPC for Quadrotors

TL;DR

This paper introduces a data-driven approach using Gaussian Processes integrated into Model Predictive Control to improve high-speed trajectory tracking of quadrotors by accurately modeling aerodynamic effects in real-time.

Contribution

It presents a novel method combining Gaussian Process modeling with MPC to effectively account for aerodynamic disturbances in quadrotor control at high speeds.

Findings

Achieves up to 70% reduction in trajectory tracking error

Validates effectiveness through synthetic and real-world experiments

Operates effectively at speeds up to 14 m/s and accelerations beyond 4g

Abstract

Aerodynamic forces render accurate high-speed trajectory tracking with quadrotors extremely challenging. These complex aerodynamic effects become a significant disturbance at high speeds, introducing large positional tracking errors, and are extremely difficult to model. To fly at high speeds, feedback control must be able to account for these aerodynamic effects in real-time. This necessitates a modelling procedure that is both accurate and efficient to evaluate. Therefore, we present an approach to model aerodynamic effects using Gaussian Processes, which we incorporate into a Model Predictive Controller to achieve efficient and precise real-time feedback control, leading to up to 70% reduction in trajectory tracking error at high speeds. We verify our method by extensive comparison to a state-of-the-art linear drag model in synthetic and real-world experiments at speeds of up to 14m/s and accelerations beyond 4g.