United States

Understanding and improving readiness is a critical task for Naval Aviation. The Digital Aviation Readiness Technology Engine (DARTE) is a proven paradigm for predicting readiness metrics such as mission capable (MC) status and expected quarterly flight hour (FH) execution for F/A-18 squadrons. The next generation of DARTE implements cutting-edge AI/ML techniques such as Long Short Term Memory networks with Attention and Hyper Deep Ensembles to extend MC prediction time horizons. We explore adding new capabilities to DARTE by utilizing Topological Data Analysis to yield new data insights, Natural Language Processing/Understanding to incorporate new data sources, Reinforcement Learning to recommend maintainer movements across the fleet, and expanding the MC prediction model to the MH-60. Additionally, we show how the products of these models can be delivered to the warfighter.

NAML 2022

Daily Readiness Predictions with the Digital Aviation Readiness Technology Engine

predictice analytics

readiness

topological data analysis

lstm

reinforcement learning

Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop.

The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

* To spread awareness of current machine learning research relevant to Naval applications

* To connect machine learning researchers with experts in military requirements

* To build and strengthen collaborations within the defense research community

**Watch this video to hear about the AFCEA purpose.**

<iframe width=1280 height=706 frameborder="0" scrolling="no" src="https://screencast-o-matic.com/player/creleVVcvRh?v=6&ff=1&title=0&controls=1" allowfullscreen="true"></iframe>

NAML 2021

technical paper

##### For full functionality of Underline, please SHUT OFF your VPN, or use a personal device.


Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop.

The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

To spread awareness of current machine learning research relevant to Naval applications

To connect machine learning researchers with experts in military requirements

To build and strengthen collaborations within the defense research community


<figure class="video_container">
  <iframe src="https://s3.amazonaws.com/pf-user-files-01/u-59356/uploads/2022-03-22/hk13mxo/NAML_ReceptionWithtitle.mp4" width=826  height=526  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop. The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

To spread awareness of current machine learning research relevant to Naval applications

To connect machine learning researchers with experts in military requirements

To build and strengthen collaborations within the defense research community



Task scheduling on multiple channels is a mature field of research and is a critical component of modern multifunction radars. Management of the radar timeline can significantly impact the overall performance by directly affecting the ability to detect and track targets. Determining the optimal schedule given the channel availabilities and a set of search/track tasks can require a prohibitive amount of computation, especially when the radar scheduler needs to operate in real time. Suboptimal solutions can be generated with fast algorithms, including traditional methods such as Monte Carlo tree search; however, if the number of tasks is large, the search space may be too voluminous and the required performance may not be met. To enable fast, high-performance schedulers, machine learning can be employed. If there is statistical similarity among the different problems the scheduler solves, then the scheduler can learn from previous problems and operate on novel ones using knowledge not exploited by a classic scheduler. Given that optimal schedulers such as Branch-and-Bound are available, a sensible approach is to use supervised learning - saved scheduling problems can be solved offline and used to generate labeled data. This work will demonstrate how supervised learning can be used to create policy neural networks that outperform various traditional schedulers (even without integration into search algorithms) while still maintaining fast execution for real-time implementation. The scheduling problem will be cast into the form of a Markov decision process. A specific focus will be how the tasks are encoded into the observation space; it will be shown that intelligent design of this "feature extraction" can allow even policies with modest degrees-of-freedom to perform well. Different reward functions will also be considered. Implementation of the framework and algorithms discussed are available as a Python package, "task-scheduling" (https://spork.nre.navy.mil/nrl-radar/CRM/task-scheduling). Access to the source code is restricted to U.S. DoD members with accounts on NRE Fusion.

Markov Decision Process Design for Supervised Learning of Task Schedulers

The space domain is becoming ever more congested and complex. The number of satellite launches is growing exponentially; commercialisation of various space-based imaging services and the number of space-capable nations continues to rise; and adversaries increasingly operate in grey-zones, attempting to evade attribution of their activities. Simultaneously, the variety and quantity of available data is growing, providing a complex challenge for space analysists trying to build an accurate picture. Machine Learning (ML) techniques can offer assistance to analysts in managing these burdens: ML can exploit excess data to provide timesaving, wider-reaching, or novel capability, and release human effort to focus on complex or higher-priority issues.

This presentation demonstrates the feasibility and effectiveness of machine learning models for satellite characterisation. Dstl has developed models to predict the operational status and the bus (structural frame type) of satellites using ground-based time-series observations of reflected sun-light or reflected radar. We found classical ML models (e.g. Random Forests) performed as well as Deep Learning approaches: our LSTM (long short-term memory) models struggled to retain their high performance when generalising to non-iid (independent identically distributed), out-of-distribution samples. The full range of characterisation tasks is significantly broader than those investigated here and considerable scope remains for further low-TRL research.

Data was a critical and limiting factor throughout this work. Based on the sources available, Wide Field Lens Array telescopes offered the best data for LEO characterisation while traditional commercial world-wide networks of Newtonian telescopes offered the best data for GEO characterisation. Open-source labels were not always available to high enough accuracy, limiting model performance in some cases. Furthermore, open-source labels are not openly archived, complicating the use of historic observations.

Machine Learning for Satellite Characterisation

New operating concepts are focused on a distributed, smaller, lighter, and more agile tactical force in the littorals and the maritime. This requires a change in medical evacuation strategy. In future operating environments, aviation-based evacuation may be infeasible due to hostile conditions or proximity to land. This presentation discusses previous research on modeling UAV routing under adversary threat and its transition to current research on the routing of Unmanned Surface Vessels (USuV) under adversary threat in support of casualty evacuation. Computational experiments are designed using a grid-world environment with randomized demand (location of casualties) and adversary movements to explore different routing strategies through the network. Initial findings are discussed, including the limitations of explored models and considerations for the development of the grid-world.

Modeling Medical Evacuation USuV Routing Under Stochastic Demands and Adversary Movements Using Online Optimization

Current naval operations require sailors to make time-critical and high-stakes decisions based on uncertain situational knowledge in dynamic operational environments. Recent tragic events have resulted in unnecessary casualties and represent the decision complexity involved in naval operations and specifically highlight challenges within the OODA loop (Observe, Orient, Decide, and Assess). Kill chain decisions involving the use of weapon systems are a particularly stressing category within the OODA loop—with unexpected threats that are difficult to identify with certainty, shortened decision reaction times, and lethal consequences. An effective kill chain requires the proper setup and employment of shipboard sensors, the identification and classification of unknown contacts, the analysis of contact intentions based on kinematics and intelligence, awareness of the environment, and decision analysis and resource selection. This project is exploring the use of automation and artificial intelligence (AI) to improve naval kill chain decisions. The team is studying naval kill chain functions and developing specific evaluation criteria for each function for determining the efficacy of specific AI methods. The team is identifying AI methods and applying evaluation criteria to map specific AI methods to specific kill chain functions.

Battle Management Aids: Leveraging Artificial Intelligence for Tactical Decisions

We demonstrate an innovative framework (CoEvSoarRL) that lever-ages machine learning algorithms to optimize and simulate a resilient and agile complex enterprise to improve the readiness and sustainment, as well as reduce the operational risk. The CoEv-SoarRL is an asymmetrical wargame simulation that leverages reinforcement learning and coevolutionary algorithms to improve total value of the enterprise. We address two of the key challenges: (1) the need to leverage holistic artificial intelligence to learn, optimization, and wargame (LAILOW) to simulate and improve the enterprise readiness; (2) the uncertainty and lack of data which require large-scale systematic what-if scenarios and analysis of alternatives to simulate and generate potential new data and unknown situations. Our CoEvSoarRL learns a model of an enterprise environment from historical data with Soar reinforcement learning. Then the Soar model is used to evaluate new decisions and operating conditions. We simulate the enterprise vulnerability (risk) and evolve new and more difficult operating conditions (tests);meanwhile we also coevolve better enterprise decision (solutions) to counter the tests. We apply lexical link analysis to discover probabilistic rules and patterns from historical data and use them for evaluating the feasibility of new data generation. We highlight proof-of-concept results from a US Marine Corps maintenance and supply chain data set, a cyber defense data set, and a force strategic lay down data set.
 



Simulating a Complex Enterprise Using an Asymmetrical Wargame Simulation with Soar Reinforcement Learning, Coevolutionary Algorithms, and Lexical Link Analysis

A rapidly approaching issue is a lack of decision support for Test and Evaluation, Verification, Validation (TEVV/LVC) facilities that have difficulty replicating adequate complexity and are therefore challenged with creating “realistic” battle engagement test scripts for autonomous products teaming/interacting with humans. The Automated White Cell (TAWC) is based on multi-model data integration, using AI/ML/Game Theory solutions, enhancing the predictive fidelity of TEVV/LVC facilities in assessing Autonomous technology strengths and weaknesses. The TAWC adjudication approach will be able to standardize existing TEVV/LVC facilities by providing a cost effective, common TEVV/LVC simulation environment through interface adaptation. The end goal is for TAWC to test autonomous systems that are designed to dynamically learn and adapt during a manned-unmanned teaming operation. TAWC is developed to provide real-time decision support and test script manipulation in the form of adjudication based on the simulation of events or discrete time. This research describes how TAWC is designed to create simulated environments augmenting TEVV/LVC facility capabilities. The design structure focuses on modeling manned and unmanned teaming opposing players that include: (1) Mixed manned and unmanned synchronous operations over complex battle engagement exchanges; (2) Varying offensive and defensive kinetic and non-kinetic assets moving at varying speeds and lethality; (3) Deception and counter deception techniques and related technology; (4) Human to autonomy interaction “teamwork” challenges; (5) Cyber tactical mixes; (6) Cyber vulnerabilities associated with security operations; (7) Logistics requirements for replenishment and repair; and (8) Crew readiness human factors, with the goal of representing greater realism and potential deployment challenges within a simulated environment.

White cell automated adjudication for TEVV/LVC facilities in assessing Autonomous technology strengths and weaknesses

Abstract: The goal of the proposed research is to make a theoretical contribution to understanding artificial intelligence/machine learning (AI/ML) in a naval fleet architecture to speed up the decision-making process and show commanders confidence in the predictions within a command and control (C2) headquarters afloat or ashore. Predictability means that models are reliable and data are representatively complete. The end state is merging the Future Knowledgebase System of Systems (FKSS) with AI/ML Engines to maximize system reliability and data availability for decision support. This knowledge architecture can offer a diffusion of ideas in an adaptive learning environment. The naval fleet unit will need to dynamically adapt its System of System (SoS) reliability and availability management methods with AI/ML agents. These analytic data problems involve three dimensions to meet the challenges—People, algorithms, and machines. The decision-makers can address overall risk management values, and the AI/ML algorithms can adjust to the individual machines and their data. The overall reliability and availability of the FKSS will be gauged by the ability to access individual systems when required to migrate authoritative data into one location or a few corresponding locations where AI/ML can act on it. The "gauge" is assisted by information sciences, data science, and risk management.


Maximizing Data Capabilities for Decision Making with Artificial Intelligence (AI) / Machine Learning (ML) in a Naval Future Knowledgebase System of Systems (FKSS)

GTRI is deploying Artificial Intelligence (AI) and Machine Learning (ML) via a model-based systems engineering (MBSE) approach to optimize aircraft maintenance scheduling and risk management in DoD and commercial applications. Leveraging big data analytics and multivariable optimization methods, GTRI is coupling industry best practices with AI/ML to maximize aircraft readiness and minimize costs at global enterprise scale.

Understanding relationships between aggregated aircraft maintenance and routing data is critical to inform and automate business decisions in aerospace operations. GTRI is using AI/ML methods, particularly random forest regression and classification, on curated DoD and commercial data sets to predict maintenance costs and operational risks of aircraft assignments on flown and unflown flight schedules. By correlating aircraft risk values, maintenance resource requirements, and fleet reliability metrics, GTRI is developing an MBSE logistics framework and model to optimize readiness costs and profits/losses in a near-real time, automated, and dynamic manner.   

Specific technical material will include data collection, exploration, and processing, AI/ML technique selection (e.g., deciding between elastic net regularized regression, gradient boosting, and random forest), and advanced scheduling theory algorithms such as P||Cmax to minimize operational loads on aircraft.

This model will provide operations managers/planners recommended schedules and quantitative data to globally optimize the tactical execution of operations. Additionally, the models wholistic insight into operations and logistics complexities enable innovation, experimentation, and simulation for Condition Based Maintenance, irregular operations, and integration of applied technologies and commercial best practices.  
    
GTRI’s efforts directly support the Joint AI Center's Joint Logistics National Mission Initiative and commercial partnerships, specifically with Delta Air Lines, on advancing industry standards on maintenance and reliability programs (e.g, Maintenance Steering Group-4). Specific opportunities to apply this research to Naval/Marine aviation fleets in collaboration with NAVAIR will be discussed. Other GTRI research referenced in support of this abstract will include AI/ML virtual reconstruction of H-60 IVHMS data and AI/ML characterization and modeling of rocket plume performance.


AI Driven Cost-Wise Readiness: Machine Learning Applications in Aircraft Maintenance Scheduling Optimization and Risk Management

The Naval Safety Center has shown in previous modeling efforts that longitudinal analysis of personnel experience can indicate at-risk units. However, data acquisition processing delays result in out-of-date input data, which leads to time-late and, sometimes, misleading predictions. Previous NAML presentations have discussed the high correlation amongst chronological longitudinal experience features, and the unique challenges these types of features present when fitting regression models. However, this multicollinearity is an asset for generating reliable predictions of feature values in future time periods with the added inclusion of a decision model that considers patterns in the variation. This paper goes through the process of building an ensemble model that predicts feature values for future time periods, and then uses those predicted feature values as inputs for risk predictions. This paper also shows that accurate modeling predictions are possible for future time periods, even when that future time period’s input data is not yet available.

Ensemble Machine Learning to Facilitate High Confidence Chronological Augmentation of Input Data Sets Used for Predictive Risk Modeling

In this presentation, we will explore the general challenges to developing predictive analytics for mission readiness applications, from data sourcing to interface design, and how a contested logistics environment can alter the technical requirements and architectural considerations.

Downloads

Next from NAML 2022

Markov Decision Process Design for Supervised Learning of Task Schedulers

Similar lecture

Improving the Efficiency of the Naval FA-18 Fleet Using The Predictive Cost of Readiness Engine (PCORE)

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from NAML 2022

Markov Decision Process Design for Supervised Learning of Task Schedulers

Similar lecture

Improving the Efficiency of the Naval FA-18 Fleet Using The Predictive Cost of Readiness Engine (PCORE)

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads