Army surprises RIDE towards an extended reality future
Researchers at the Institute for Creative Technologies built the Rapid Integration and Development Environment, a test bed for evaluating modeling and simulation technologies for internal use. But the system, which plays a role in creating the military’s tactical computing environment, finds users in the Department of Defense and the defense industry.
The system, known as RIDE, has been found to be useful in developing a wide range of capabilities for technology-generated realities, including virtual, augmented, and extended realities. RIDE combines functionality inherent in commercial game engines with many immersive technologies developed at the institute, commonly known as ICT. ICT is a university affiliated research center associated with the University of Southern California and is directly supported by funding from the Department of Defense.
An ICT website describes RIDE as a “modern, state-of-the-art simulation research and development framework that has proven invaluable in advancing ICT research, collaborators, and stakeholders in new areas. multiple areas. RIDE combines and integrates Army One World Terrain data and tools; machine learning; speech recognition; natural language processing; the behaviors of artificial intelligence (AI) characters; and the development of scenario events. It is integrated with commercial game engines, enabling the reuse of visual arts, 3D models and other simulation technologies in the common platform, reducing the effort required to create divergent simulation prototypes. While it was built using the Unity game engine, it is also designed to be independent, meaning it can be used with virtually any game engine.
The ICT team started building RIDE because they couldn’t find the tools they needed, explains Volkan Ustun, ICT associate director of cognitive architectures. He conducts many experiments with AI and reinforcement learning that require fast simulation environments that can create data as quickly as possible to train AI models. Models created in the simulation environment can be shared between AI experiments, and the system can provide a common repository for reusing or reusing technologies.
“When I looked at things in the military two years ago, there was nothing that was able to handle the type of things that I need. RIDE provides me with a realistic, game-engine-based simulation environment capable of generating the data in a format that I can use to train these models, ”says Ustun.
The system has come a long way in two years. “The impetus for RIDE was to help our internal research projects have a more cohesive understanding and structure, and then that very quickly turned into today’s RIDE, which is that platform that we provide. across the Department of Defense to revive existing ideas and research and provide a base where multiple collaborators can work on integrated projects that might have disparate technologies, ”says Kyle McCullough, director of ICT, modeling and simulation. “It really got bigger. It quickly became a much bigger use case than what we were doing with ICT. “
The United States Army’s Center for Simulation, Training and Technology (STTC) in Orlando is a major sponsor of the system. “They also use the RIDE platform – as do a number of our collaborators at STTC, other entrepreneurs working on science and technology research – all leveraging RIDE to start integrating our research, in the same way that we did it in ICT, where we show everything we’ve done in this cohesive environment, ”McCullough reports.
The Office of Naval Research has also found RIDE useful. “Many collaborators and performers who work in the Human Performance Education and Training program under the leadership of Dr. Peter Squire have created software programs and applications using the Unity game engine,” says McCullough. .
RIDE can also work with existing or so-called ‘legacy’ systems, such as ICT’s Aerial Terrain Line-of-Sight Analysis (ATLAS) system, which is hosted on MilGaming, the military’s web portal. for play systems used for training. The version of ATLAS available on MilGaming is around 18 months old, the researchers estimate. But now if someone creates a new version with 3D data, RIDE can serve as a basic foundation to support that data. “It works in all of those other use cases – the prototyping, the modeling and simulation environments that we created, but it can also be directly integrated into the ATLAS software, which is now built from RIDE,” says McCullough. . .
He adds that the Office of Naval Research uses RIDE to connect disparate technologies. “One of the big efforts on this side has been to unify a lot of software foundations, because they were all built through these sparse efforts among these different companies and people. Part of the work that we do, for example with Lockheed Martin, is to tie it all together in the RIDE platform, so you have this fundamental codebase. “
ICT researchers tout this ability to link disparate research from diverse disciplines as one of the main benefits – and challenges – of RIDE. Arno Hartholt, Director of Research and Development Integration at ICT, cites the Army’s Future Synthetic Training Environment as an example, which will bring together live, virtual and constructive training environments to train troops. disembarked and mobile, air platform crews and command post personnel wherever training is needed.
“How do you get researchers to work with developers, to work with industry, to work with subject matter experts from the Army and the military as a whole?” And what specific capacities do you need to put in place and how do you make them work together to meet a real need? RIDE addresses these challenges and provides a blueprint for how it is possible to propose a way forward, ”says Hartholt.
The challenge, he says, is to keep RIDE applicable to a wide variety of users while increasing its capabilities. “What we’re doing moving forward is really listening to what the gaps are, what individual groups have, and trying to find common features while maintaining the scalability and core design of RIDE. This is the main challenge: to ensure that any researcher and developer is able to take advantage of RIDE for their purposes while developing it in terms of maturity and new capabilities. “
Future improvements will include the use of AI to improve the behaviors of simulated characters, including enemy forces. Lifestyle behaviors are also likely to be improved. For example, military simulations must accurately describe the behavior of civilian populations.
Ustun says these behaviors include more realistic representations of the characters’ behaviors or abilities in particular types of terrain. “On top of that, you have other constraints coming from military doctrine and guidelines and things like that where certain squads or infantry can do certain things in the environment, and you have to incorporate those things into those models. of AI. So when you train and create behaviors, they have to follow certain guidelines while trying to optimize their goals in their environment for the task they are trying to accomplish. “
A service-based architecture for RIDE is also likely. “One of the keys is that RIDE currently supports a lot of these integrations that we’re doing for all of these different capabilities. What we learn as we build this is where the requirements are to improve, perhaps, by creating some of that capability as an accessible service-based architecture, ”says McCullough.
A good example of this, he says, is the work done by the ICT team for modeling geospecific 3D terrain data. “For example, part of the work we do is to take advantage of this service-based architecture to support something like the Next Generation Combat Vehicle, or any other work being done by the Ground Vehicle Systems Center. Especially when you think about using these types of things when you need them, you won’t want every device running RIDE and having this full simulation system, ”McCullough adds.
The service-based architecture would allow users, for example, to note their current location in the simulation and their destination. “RIDE performs line-of-sight analysis on enemy locations. RIDE uses the classification of the materials on the ground, knows the specifications of the vehicle you are in and provides the best route at that time, ”says McCullough.
Other potential improvements include extending RIDE to support more external machine learning frameworks; adding the ability for researchers and developers to more easily configure new scenarios, new contexts, and new ways of defining the scenarios and environments they need; improved support for data collection, creation and analysis; and the ability to run RIDE on different types of hardware to provide native support for augmented and virtual reality, which would advance the Army’s goal of providing technology-generated reality training when and where it is needed.
While RIDE’s future path may include becoming a commercial product, the goal is to provide the military with a research and development platform, suggests Hartholt. “We are a non-commercial entity, so we see it as a test bed. We will use RIDE to help the Army define their acquisition needs and goals, and as such we really help lead the program and identify opportunities and gaps. I don’t see us turning RIDE into something that we start selling to the government. It is an open platform to support, initially, the research and development of the army, then beyond. “