Document Type
Honors Thesis
Abstract
Reinforcement Learning is a Machine Learning paradigm that involves simulating learning through rewards and penalties in intelligent systems. This technique is often employed in robotics when traditional control methods are insufficient or when human intuition does not provide a good solution on how to control robot systems, This project involves training a Segway-style Mobile Inverted Pendulum (MIP) robot to balance and push a box forward. The BeagleBone Blue board is used that includes a built-in Inertial Measurement Unit (IMU) and encoder ports. These sensors enable the system to measure its current state. The goal is to find the optimal leaning angle needed to push a box forward while balancing on two wheels.
The findings from this study can contribute to the development of self- balancing robots that can fit through tighter spaces, which can potentially improve operational efficiency in environments where space is a valuable resource, such as industrial warehouses.
Disciplines
Artificial Intelligence and Robotics | Computer Sciences | Robotics
Publication Date
5-2025
Language
English
Faculty Mentor of Honors Project
Manfred Huber
License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Recommended Citation
Mediratta, Aryan, "Controlling a Mobile Inverted Pendulum and Optimizing Leaning Angle to Apply Force Using Reinforcement Learning" (2025). 2025 Spring Honors Capstone Projects. 20.
https://mavmatrix.uta.edu/honors_spring2025/20