Research Summaries

Back Application of Dueling Networks to Unmanned Aerial Vehicle (UAV)

Fiscal Year 2019
Division Graduate School of Operational & Information Sciences
Department Operations Research
Investigator(s) Yoshida, Ruriko
Sponsor Air Force Institute of Technology (Air Force)
Summary We would like to control an unmanned aerial vehicle (UAV) without human interaction. In order to do so, a UAV has to predict
1. its safe path
2. its target’s path
from the input vision in a short amount of time. In this proposed research we would like to apply deep learning methods to train a machine on the path for a UAV as well as its path to its target efficiently.
Keywords Deep Learning Dueling Networks Q-networks UAV
Publications Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal
Data Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal