G2TT
来源类型Report
规范类型报告
DOIhttps://doi.org/10.7249/RR4311
来源IDRR-4311-RC
Air Dominance Through Machine Learning: A Preliminary Exploration of Artificial Intelligence–Assisted Mission Planning
Li Ang Zhang; Jia Xu; Dara Gold; Jeff Hagen; Ajay K. Kochhar; Andrew J. Lohn; Osonde A. Osoba
发表日期2020-05-29
出版年2020
语种英语
结论

RL can tackle complex planning problems but still has limitations, and there are still challenges to this approach

  • Pure RL algorithms can be inefficient and prone to learning collapse.
  • Proximal policy optimization is a recent step in the right direction for addressing the learning collapse issue: It has built-in constraints preventing the network parameters from changing too much in each iteration.
  • ML agents are capable of learning cooperative strategies. In simulations, the strike aircraft synergized with jammer or decoy effects on a SAM.
  • Trained algorithms should be able to deal with changes in mission parameters (number and locations of assets) fairly easily.
  • Few real-world data exist on successful and unsuccessful missions. Compared with the volumes of data used to train contemporary ML systems, very few real missions have been flown against air defenses, and virtually all of them were successful.
  • For analyses involving the use of large simulations in place of large datasets, the required computational burden will continue to be a significant challenge. The scaling of computational power and time required to train realistic sets of capabilities (dozens of platforms) against realistic threats (dozens of SAMs) remains unclear.
  • Developing trust in AI algorithms will require more-exhaustive testing and fundamental advances in algorithm verifiability, and safety and boundary assurances.
摘要

U.S. air superiority, a cornerstone of U.S. deterrence efforts, is being challenged by competitors—most notably, China. The spread of machine learning (ML) is only enhancing that threat. One potential approach to combat this challenge is to more effectively use automation to enable new approaches to mission planning.

,

The authors of this report demonstrate a prototype of a proof-of-concept artificial intelligence (AI) system to help develop and evaluate new concepts of operations for the air domain. The prototype platform integrates open-source deep learning frameworks, contemporary algorithms, and the Advanced Framework for Simulation, Integration, and Modeling—a U.S. Department of Defense–standard combat simulation tool. The goal is to exploit AI systems' ability to learn through replay at scale, generalize from experience, and improve over repetitions to accelerate and enrich operational concept development.

,

In this report, the authors discuss collaborative behavior orchestrated by AI agents in highly simplified versions of suppression of enemy air defenses missions. The initial findings highlight both the potential of reinforcement learning (RL) to tackle complex, collaborative air mission planning problems, and some significant challenges facing this approach.

目录
  • Chapter One

    Introduction

  • Chapter Two

    One-Dimensional Problem

  • Chapter Three

    Two-Dimensional Problem

  • Chapter Four

    Computational Infrastructure

  • Chapter Five

    Conclusions

  • Appendix A

    2-D Problem State Vector Normalization

  • Appendix B

    Containerization and ML Infrastructure

  • Appendix C

    Managing Agent-Simulation Interaction in the 2-D Problem

  • Appendix D

    Overview of Learning Algorithms

主题Air Defense ; Air Warfare ; Machine Learning ; Military Information Technology Systems
URLhttps://www.rand.org/pubs/research_reports/RR4311.html
来源智库RAND Corporation (United States)
引用统计
资源类型智库出版物
条目标识符http://119.78.100.153/handle/2XGU8XDN/524110
推荐引用方式
GB/T 7714
Li Ang Zhang,Jia Xu,Dara Gold,等. Air Dominance Through Machine Learning: A Preliminary Exploration of Artificial Intelligence–Assisted Mission Planning. 2020.
条目包含的文件
文件名称/大小 资源类型 版本类型 开放类型 使用许可
RAND_RR4311.pdf(1217KB)智库出版物 限制开放CC BY-NC-SA浏览
x1590756424788.jpg.p(1KB)智库出版物 限制开放CC BY-NC-SA浏览
个性服务
推荐该条目
保存到收藏夹
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Li Ang Zhang]的文章
[Jia Xu]的文章
[Dara Gold]的文章
百度学术
百度学术中相似的文章
[Li Ang Zhang]的文章
[Jia Xu]的文章
[Dara Gold]的文章
必应学术
必应学术中相似的文章
[Li Ang Zhang]的文章
[Jia Xu]的文章
[Dara Gold]的文章
相关权益政策
暂无数据
收藏/分享
文件名: RAND_RR4311.pdf
格式: Adobe PDF
文件名: x1590756424788.jpg.pagespeed.ic.WwtUcqwRvW.jpg
格式: JPEG

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。