Document Type

Conference Paper

Publication Date

2024

Publication Title

Proceedings of the American Society for Engineering Management 2024 International Annual Conference

Pages

1-10

Conference Name

American Society for Engineering Management 2024 International Annual Conference

Abstract

Acquiring the necessary skills to perform a work effectively and efficiently requires a significant investment of time and computing power. Previous applications of Reinforcement Learning (RL) for action optimization in humanoid robotics have shown how promising this technology is for moving robotics towards true autonomy and versatility. Therefore, this study offers the first use of RL to create an entirely optimal kicking action for the Alderbaran Nao robot. Kicking motions that were steady, precise, quick, and able to kick farther than any existing RoboCup squad were generated by optimizing for a multi-objective reward function. We demonstrate that the ideal kicking motions can be modified to produce angled kicks by putting a dynamic kicking module into practice. We also research on various kicking movements and more intricate search spaces that can benefit from the methodology presented in this study.

Rights

Copyright © 2024. Reprinted with permission of the American Society for Engineering Management. International Annual Conference.

ORCID

0000-0003-2824-4528 (Alla)

Original Publication Citation

Dodda, S., Chintala, S. K., Mallreddy, S. R., Macha, S. C., Vasa, Y., Bonala, S. B., Kamuni, N., & Alla, S. (2024). Reinforcement learning for optimal kicking actions in humanoid robotics: Advancing robotic autonomy and versatility [Paper presentation]. American Society for Engineering Management 2024 International Annual Conference, Virginia Beach, Virginia.

Download

Share

COinS