Comparative analysis of PID control and MPC in CartPole and LunarLander environments

Authors

  • Gabriel Bueno Leandro Grupo de Controle e Modelagem - GCoM - Universidade Federal de São João del-Rei
  • Samir Angelo Milani Martins Grupo de Controle e Modelagem - GCoM - Universidade Federal de São João del-Rei

DOI:

https://doi.org/10.5335/rbca.v16i3.15852

Keywords:

CartPole, Model Predictive Control, Proportional-Integral-Derivative Control, LunarLander

Abstract

With technological advancement, increasingly complex systems emerge, driving the relentless pursuit of more effective control methods. In this study, the control of two Gymnasium environments will be explored: LunarLander and CartPole. LunarLander represents a simplification of vehicle autonomy, while CartPole is closely related to robotics. The goal is to apply Model Predictive Control (MPC) and Proportional-Integral-Derivative (PID) control to these environments, aiming to achieve their specific objectives. The techniques employed have shown success in controlling the environments, highlighting the effectiveness of these methods in complex challenges. Additionally, this study addresses various engineering concepts, from physical fundamentals to system identification, leveraging Python packages to offer an accessible approach for both academia and industry. This multidisciplinary analysis promises to significantly contribute to the advancement of knowledge and practical application in the field of complex system control.

Downloads

Download data is not yet available.

Published

2024-12-03

Issue

Section

Original Paper

How to Cite

[1]
2024. Comparative analysis of PID control and MPC in CartPole and LunarLander environments. Brazilian Journal of Applied Computing. 16, 3 (Dec. 2024), 74–88. DOI:https://doi.org/10.5335/rbca.v16i3.15852.