The US Army’s XM30 Program Office has contracted Duality AI for the development of a counter-drone AI Target Detection and Recognition (AiTDR) system.
Duality AI is the developer of Falcon, a platform specialising in digital twin simulations.
Go deeper with GlobalData
The AiTDR system is being designed and developed to protect personnel on board a vehicle by detecting and recognising drone threats.
To facilitate this, the Army’s Project Linchpin, focused on AI and Machine Learning, will collaborate with the Army Research Lab (ARL) to use synthetic data from Falcon’s virtual sensors.
The partnership with Duality AI adopts a digital-first strategy to accelerate the AiTDR system’s development before its physical implementation.
By using Falcon for digital twin simulation from the outset, the XM30 team aims to overcome significant development hurdles more efficiently, reducing both time and cost for deployment in the field.
The platform will be instrumental in producing diverse sets of quality training data, optimising sensor placement, and evaluating model efficacy within simulated environments.
This contract underscores a continued commitment to a digital-first methodology initiated at the programme’s inception and reinforces a shift towards engaging non-traditional combat vehicle contractors in defence projects.
Duality CEO and co-founder Apurva Shah said: “We are thrilled to work with the Project Linchpin and ARL teams to push the possibilities of AI defence systems for the US Army.
“The XM30 digital-first approach to AI model deployment is farsighted and precisely the type of system development approach for which Falcon’s digital twin workflows have been designed. The XM30 programme is transforming how tomorrow’s military technology is developed and we’re honoured that Falcon is contributing to that future.”
The ARL team will use Falcon to create and simulate a wide range of scenarios, incorporating various drones, environments, and visual conditions. They can generate the necessary data using the platform’s assortment of virtual sensors.
Initially, the team will develop an AI model that operates in conjunction with the Falcon simulator.
Subsequent efforts will focus on enhancing the algorithm’s first iteration by optimising both the model itself and the simulation methodology through a collaborative effort with Duality’s AI engineers.
As the project progresses, there will be an evaluation of how digital twin simulation within Falcon can be applied more broadly to meet their growing requirements for AI/ML training data.
Duality AI co-founder and chief product officer Michael Taylor said: “Accomplishing these critical early steps with digital twins is vital for a viable future of field-deployable AI systems.
“Falcon’s complete control over simulation environments gives the Army ability to train and test the AiTDR model in complex conditions, explore varied drone detection scenarios, and validate potential solutions in simulation before the physical hardware is even ready for field testing.”
