Enemy Location Prediction in Naval Combat Using Deep Learning; Social Construction of Technology Analysis on the use of Artificial Intelligence in Military Operations

Author:
Ningtyas, Adinda, School of Engineering and Applied Science, University of Virginia
Advisors:
Beling, Peter, EN-Eng Sys and Environment, University of Virginia
Elliott, Travis, EN-Engineering and Society, University of Virginia
Abstract:

The rise of Artificial Intelligence is evident through its implementation in practically every sector. AI is transforming how tasks are being completed and increasing the speeds at which they occur. Implementing AI for military use has transformed how warfare is conducted and its complexity will only continue to increase in the future. An example of the benefits of AI on the battlefield is through the ability to aid in the decision-making process. However, while the benefits of AI are undeniable- there are clearly some risks that is involved in implementing such technology. Additionally, elements of controversy exists with regards to the adoption of AI for military use.

My STS research paper focuses on the use of Artificial Intelligence for military operations. The analysis of the research was conducted through the STS framework of Social Construction of Technology (SCOT). SCOT is a framework that analyzes the meaning of a technology to groups of relevant stakeholders. The stakeholders involved in my research were technology producers, the US military, and the general US public. I analyzed the factors for why each of these groups would benefit from military AI. I also discussed the drawbacks of the use of military AI along with the controversial elements that are involved with its employment. I determined that AI technology use will only continue to grow in the future and that each stakeholder group shall continue to have their own vested interests related to it. However, I note that since AI is currently being implemented to perform certain tasks by the military this technology on the path to widespread adoption.

One of the controversies regarding the use of AI in military operations involves allowing autonomous systems to make decisions- some of which may be lethal. Keeping humans in-the-loop is a critical element to consider in the development of these systems. In the decision-making4 process, AI can provide military leaders with a strategic advantage over the enemy. The goal of my technical project was to create a predictive system for identifying the locations of enemy vessels in simulated naval combat. We simulated naval combat through the online video game World of Warships (WoWs). After each game played, a replay file is automatically stored. As a result, data was collected through a WoWs tournament. Once the data was parsed and organized, we utilized machine learning techniques in order to predict the locations of the enemy vessels in the video game. While a video game is a controlled environment compared to real world naval combat, our research determined that it was feasible with reasonable accuracy to obtain predictive information about an adversary using machine learning.

Our research highlights the benefits of using AI for adversarial intent inference through the method of simulated naval combat. Utilizing AI in the decision making can prove to be a valuable asset in combat. My STS research highlights the attitudes of the various stakeholder groups to utilizing AI in military operations through SCOT. The SCOT lens can be applied to the technical project as applying AI in the manner conducted for research highlights that the technology is well on its way to widespread adoption. The links between both the STS and technical research are clear in which both concern the use of military AI; the STS research in a broad sense while the technical project focused on a specific application.

Degree:
BS (Bachelor of Science)
Keywords:
Artificial Intelligence, Naval Combat, Social Construction of Technology, Intent Inference, Machine Learning, Military Operations
Notes:

A Technical Report for SYS 4054

School of Engineering and Applied Sciences

Bachelor of Science in Systems Engineering

Technical Advisor: Peter Beling

STS Advisor: S. Travis Elliott

Technical Team Members:

Morgan Freiberg

Kent McLaughlin

Oliver Taylor

Language:
English
Issued Date:
2021/05/14