Real-time implementation of MPC for tracking in embedded systems: Application to a two-wheeled inverted pendulum

TL;DR

This paper demonstrates a real-time model predictive control implementation for a two-wheeled inverted pendulum robot, showcasing its effectiveness on embedded hardware with millisecond sampling times.

Contribution

It introduces a specialized sparse solver based on ADMM for real-time MPC in embedded systems, tailored for tracking control of a two-wheeled inverted pendulum.

Findings

Solver operates effectively with millisecond sample times

Implementation feasible on current embedded hardware

Enhanced control performance over standard MPC

Abstract

This article presents the real-time implementation of the model predictive control for tracking formulation to control a two-wheeled inverted pendulum robot. This formulation offers several advantages over standard MPC formulations at the expense of the addition of a small number of decision variables, which complicates the inner structure of the matrices of the optimization problem. We implement a sparse solver, based on an extension of the alternating direction method of multipliers, in the system's embedded hardware. The results indicate that the solver is suitable for controlling a real system with sample times in the range of milliseconds using current, readily-available hardware.