Written by Feliks Olko
1 min read
What Are Synthetic Training Environments?
- Military Simulations
Synthetic Training Environments are high-fidelity, ultra-realistic simulations that replicate real-world engagements using real-time data. Organisations from the MoD to NATO utilise them as a way of avoiding unnecessary economic and human loss, as well as de-escalating potential conflict. The more accurate the environment, the more it drives better decision-making in real-world scenarios.
Synthetic Training Environments are made up of three key areas:
- Tactical Augmented Reality Heads-Up Displays, which mix real and virtual worlds and have live data fed to them in real-time, allowing for better-informed tactical decisions.
- Synthetic Psychological Environments provide an overview of the broader picture modelling behavioural influences to individuals and groups as a result of their culture – be that demographical, legal, or religious. Scenarios can be simulated in real-time and controlled entirely by AI to see how potential situations may play out.
- Sentient World Simulations provide an overview of all other activities, forecasting the potential impact of military activities, including any potential unrest by building an artificial mirror of the real world. These simulations are calibrated with current real-world information, including significant events, opinion polls, and demographic and economic reports.
All simulations use a common synthetic environment that integrates and replicates common global data. The significant volume of training data allows for better feedback in after-action debriefs and lowers cost by removing the overheads associated with physical exercises. The ultimate intention is to forecast risk, avoid conflict and increase preparations in the face of an emergency.
The scope of synthetic training environments is currently limited to a finite number of users and AI entities, defined by the limits of computational power. It takes a vast amount of bandwidth to create highly-complex, real-time, hyper-scale simulations based on the array of disparate data sources across the world.
As the simulations scale, they become increasingly unreliable and understanding the implications of a vast number of variables becomes increasingly resource-intensive. It is currently impossible to replicate city-size simulations on a global scale – combining millions of agents and AI entities – while incorporating real-world data.
Ultimately, these computational limitations mean that the practical implementation of synthetic training environments remains tactical and local in scale.
Accurate Scenario Planning
Through dynamically distributed computing, the potential of synthetic training environments can be realised. Big data can be ingested and processed in near-real time, creating intuitive simulations and analysis. Accurate, high-fidelity simulations will lead to better and more informed decision making.
The maintenance is lowered, and the practical considerations of running a simulation are greatly simplified. With the right technology, synthetic training environments will be both customisable and scalable, introducing vastly increased sophistication and complexity.
On the one hand, organisations will be able to create real-time global simulations based on consistent and reliable data, while at the same time being tailored to specific situations.
Find out more about how you can optimise and scale your simulation while keeping it adaptable and responsive to real-time data.
Aether Engine | Life Sciences
May 27, 2020 4:58:07 PM | 2 min read
COVID-19 continues to impact populations around the globe and researchers are working tirelessly to answer key ...
May 5, 2020 5:08:10 PM | 1 min read
Synthetic Training Environments are high-fidelity, ultra-realistic simulations that replicate real-world engagements ...
View all Blog articles
Posts by Tag
- May 2020
- April 2020
- March 2020
- February 2020
- January 2020
- December 2019
- November 2019
- October 2019
- September 2019
- August 2019
- July 2019
- June 2019
- May 2019
- April 2019
- March 2019
- February 2019
- January 2019
- December 2018
- November 2018
- July 2018
- June 2018
- May 2018
- April 2018
- March 2018
- February 2018
- January 2018
- December 2017
- November 2017