Real-Time Swing-up of a Linear Inverted Pendulum Using Reinforcement Learning

Authors

DOI:

https://doi.org/10.5755/j02.mech.39202

Keywords:

deep deterministic policy gradient, reinforcement learning, control systems, deep learning, dynamical systems, single inverted pen

Abstract

This study focused on applying and enhancing the Deep Deterministic Policy Gradient (DDPG) algorithm to effectively control a Single Inverted Pendulum (SIP) system. The primary objective was to improve the algorithm's performance by addressing common challenges such as overestimation of Q-values and convergence to local optima. The system's behaviour was analyzed through simulation and real-world experiments, showcasing the algorithm's ability to offer faster responses, enhanced stability, and reduced pendulum displacement. The research introduced key modifications to the experience replay mechanism and the Critic network, which played a significant role in improving the efficiency of the learning process and the robustness of the control strategy. By combining Reinforcement Learning with traditional control methods, this approach successfully managed the nonlinear dynamics of the SIP system. Nevertheless, certain challenges persist, particularly in terms of
the efficiency of deep reinforcement learning algorithms and their stability in real-world environments. These findings suggest that future research should focus on further refining DRL algorithms to increase their practical application in physical control systems. In conclusion, the research highlights the potential of combining DRL techniques with conventional control strategies for tackling complex control problems. The success achieved in controlling the SIP system indicates a promising direction for further exploration and development in this field.

Downloads

Published

2025-05-06

Issue

Section

DESIGN AND OPTIMIZATION OF MECHANICAL SYSTEMS