DID YOU KNOW? DTIC has over 3.5 million final reports on DoD funded research, development, test, and evaluation activities available to our registered users. Click
HERE to register or log in.
Accession Number:
AD1132186
Title:
First-Year Report of ARL Directors Strategic Initiative (FY20-23): Artificial Intelligence (AI) for Command and Control (C2) of Multi-Domain Operations (MDO)
Report Date:
2021-05-05
Abstract:
This report describes efforts conducted in fiscal year 2020 under the US Army Combat Capabilities Development Command Army Research Laboratorys Directors Strategic Initiative (DSI) project Artificial Intelligence (AI) for Command and Control (C2) of Multi-Domain Operations (MDO). The speed and complexity of MDO against a near-peer adversary in hyperactive environments calls for high-speed decision-making and execution that may often exceed human cognitive ability. Recently, emerging AI techniques such as deep reinforcement learning (DRL) have outperformed human world champions in complex, relatively unstructured, partial-information, strategic games such as Dota 2 and StarCraft II. This suggests the potential of such AI to contribute to C2 of MDO. However, many questions about the behaviors and limits of such new AI techniques remain unanswered. As part of this DSI, we are investigating whether DRL might support future agile and adaptive C2 of multi-domain forces that would enable the commander and staff to exploit rapidly and effectively fleeting windows of superiority. In our first year, we have developed two novel C2 testbeds and DRL-based learning within these testbeds. This report includes an overview of the project and demonstrates preliminary research results where an artificial commander executes an integrated planning-execution process in a simulated brigade-scale battle.
Document Type:
Conference:
Journal:
Pages:
32
File Size:
2.35MB
Contracts:
Grants:
Distribution Statement:
Approved For Public Release
