DOD STTR 24.B Annual

Active
No
Status
Open
Release Date
April 17th, 2024
Open Date
May 15th, 2024
Due Date(s)
June 12th, 2024
Close Date
June 12th, 2024
Topic No.
A24B-T020

Topic

Drone Swarm Detection Using Artificial Intelligence Based on Ultrafast Neural Networks

Agency

Department of DefenseN/A

Program

Type: STTRPhase: Phase IYear: 2024

Summary

The Department of Defense (DOD) is seeking proposals for a Small Business Technology Transfer (STTR) project focused on drone swarm detection using artificial intelligence (AI) based on ultrafast neural networks. The goal is to develop a neural network architecture and learning processing algorithms for drone identification based on ultra-fast neural networks with low power consumption. The project aims to identify airborne drones from their radio frequency transmissions or radar signatures using AI and neuromorphic computing. The project will be conducted in two phases. In Phase I, computer simulations will be used to demonstrate the possibility of using ultra-fast neural networks for processing multiple microwave drone signals. In Phase II, the project will determine optimum materials for the development of ultra-fast neural networks, develop principles for building large neural networks, and test learning algorithms for drone identification. The project will also explore dual-use applications, including lightweight antennas for drones, real-time monitoring systems, and autonomous driving platforms. The deadline for proposal submission is June 12, 2024. For more information, visit the solicitation agency's website at [link].

Description

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Advanced Computing and Software

 

OBJECTIVE: Drone swarm detection using Artificial Intelligence. Develop a neural network architecture, and learning processing algorithms for drone identification based on ultra-fast neural networks with low power consumption.

 

DESCRIPTION: The goal of this Army Small Business Technology Transfer (STTR) topic is the identification of airborne drones from their radio frequency transmissions or radar signatures using ultra-fast neural networks [1]. The drone identification and classification are done by rapidly analyzing RF signals from one or several receiving antennas. As several target drones are often present in the antenna’s range, the received signal may represent a result of interference of several sources. For such a multiple target identification in a drone swarm, it is crucial to be able to process information in parallel and directly at the carrier microwave frequency.

 

Recent research into applications of artificial intelligence (AI) based on neuromorphic networks (in particular, using magnetic artificial neurons [1-5]) was executed to solve a variety of computational and signal processing problems. The purpose of neuromorphic computing is to replicate the human brain functionality in nanoscale using man-made neurons and synapses. The advantage of this approach is highly parallelized computing with large amounts of memory in close proximity to the computing elements, which results in a substantially increased speed and reduced power consumption of computing.

 

The methodologies described in [1-5] are particularly suited for defense-related computing due to a number of unique features, such as nano-scale sizes, simple implementation of memory elements and strongly nonlinear dynamics. Of a particular interest for military applications is the low power consumption of the network elements, and possibility of operation in GHz [2, 3] and even THz [4, 5] frequency ranges. These high-frequency properties allow one to utilize neural networks for parallel processing of drone microwave signals at the carrier frequency without digitization or super-heterodyning.

 

Another important consideration in the drone identification problem is the power requirements of the device. Recently, it has been demonstrated [6], that neural networks based on artificial antiferromagnetic neurons are capable of performing simple identification tasks in sub-nanosecond time with extremely low power consumption of less than 1 pJ per synaptic operation. These results look very promising for the development of mobile ultra-fast and low-power devices for neuromorphic identification of drones.

 

The goal of this call is to develop a neural network capable of simultaneous ultra-fast (time scale of nanoseconds) identification and targeting of large groups (swarms) of drones threatening ground vehicles. Another goal is to design an optimal architecture of an ultra-fast neural networks with integrated memory, and to develop and test learning and data-processing network algorithms suitable for ultra-fast detection of multiple drones in a drone swarm.

 

PHASE I: Using computer simulations, demonstrate the possibility of using artificial intelligence in the form of an ultra-fast neural network for processing multiple microwave drone signals without super-heterodyning or/and digitization. Demonstrate possibility of classification of drone microwave signals using ultra-fast neural networks in a case when the input signals from drones are monochromatic (unmodulated).

 

PHASE II: Determine optimum materials for the development of ultra-fast, lower power consumption neural networks. Develop principles of building large neural networks that will utilize ultra-fast processing capabilities of the chosen network elements (artificial neurons). Develop and test learning algorithms for drone identification in the presence of a single and multiple (2-5) drone signatures and modulated drone signals. Using computer simulations, demonstrate successful drone classification using a developed ultra-fast neural network. Determine processing time, power consumption, weight and size of an anti-drone device based on neural networks.

 

PHASE III DUAL USE APPLICATIONS: Demonstrate successful drone identification using an experimental prototype of a developed neural network. Demonstrate possibility of simultaneous identification of multiple drone targets. Potential applications include: light weight, ultracompact antenna for use in reconnaissance and observation drones (commercial and military); real-time monitoring of frequency agile microwave K band signals with potential applications to Active and Passive protection systems. Commercial application: Autonomous driving platforms and radar-based collison avoidance systems.

 

REFERENCES:

J. Grollier, D. Querlioz, K.Y. Camsari, et al., “Neuromorphic spintronics.” Nat. Electron. 3, 360–370 (2020). https://doi.org/10.1038/s41928-019-0360-9; 
A. Ross, N. Leroux, A. De Riz, et al., “Multilayer spintronic neural networks with radiofrequency connections.” Nat. Nanotechnol. (2023). https://doi.org/10.1038/s41565-023-01452-w; 
J. Torrejon, M. Riou, 3.  F. Araujo, et al., “Neuromorphic computing with nanoscale spintronic oscillators.” Nature 547, 428–431 (2017). https://doi.org/10.1038/nature23011; 
R. Khymyn, I. Lisenkov, J. Voorheis, et al., “Ultra-fast artificial neuron: generation of picosecond-duration spikes in a current-driven antiferromagnetic auto-oscillator.” Sci. Rep. 8, 15727 (2018). https://doi.org/10.1038/s41598-018-33697-0; 
H. Bradley, S. Louis, C. Trevillian, et al., “Artificial neurons based on antiferromagnetic auto-oscillators as a platform for neuromorphic computing.” AIP Advances 13, 015206 (2023). https://aip.scitation.org/doi/10.1063/5.0128530
H. Bradley, S. Louis, V. Tiberkevich, et al., “Pattern recognition using spiking antiferromagnetic neurons.” (Aug 2023). https://www.researchgate.net/publication/373246558

 

KEYWORDS: artificial intelligence, ultra-fast, artificial neuron, drone identification, learning algorithm

Similar Opportunities

DOD SBIR 24.4 Annual - xTechScalable AI
Department of Defense
The Department of Defense (DOD) is seeking proposals for the topic of "xTechScalable AI" as part of the SBIR program. The Army branch is specifically interested in novel and disruptive concepts and technology solutions that can address the vulnerabilities of current machine learning pipelines and models. The goal is to develop comprehensive security models that can defend against universal AI threat vectors and are scalable to rapidly evolving threats. The Army is particularly interested in proposals that focus on systematic testing and evaluation methods, trusted and secure validation and verification strategies, continuous monitoring capabilities, improved transparency and assurance of code and data, and improved telemetry capabilities. The Army will prioritize submissions from winners of the xTechScalable AI prize competition. The project will involve a Direct to Phase II submission, followed by the production of prototype solutions that are easy to operate by soldiers. Phase III will focus on maturing the technology to TRL 6/7 and producing prototypes for further development and commercialization. The deadline for proposal submission is March 31, 2025. For more information and to submit a proposal, visit the solicitation agency's website at [solicitation_agency_url].
DOD SBIR 24.4 Annual - Novel Positioning, Navigation, and Timing (PNT) Signal Classification Techniques
Department of Defense
The Department of Defense (DOD) is seeking proposals for a novel positioning, navigation, and timing (PNT) signal classification techniques. The purpose of this solicitation is to develop the capability to classify signals in real-time that impact navigation systems. The goal is to better understand the type(s) of signal(s) experienced in relevant environments to apply mitigation techniques before harm can be done. The research will focus on improving performance, cost savings, and expanding the application of the technology sensor solution set to include additional Army aviation assets. The project will involve developing adaptive learning techniques using AI/Machine Learning (ML) algorithms to perform PNT signal classification. The proposed solution aims to build upon the progress made in AI/ML signal classification and move towards real-time signal classification. The project will have a Phase I and Phase II, with Phase II requiring the development of two antenna systems capable of detecting and classifying interference signals in real-time. The project also aims to make the antenna design portable to support upgrading antenna systems and providing support to other antenna systems in the same environment. The anticipated duration of the project is until March 31, 2025. For more information and to submit proposals, visit the DOD SBIR website.
DOD SBIR 24.4 Annual - Development of an Unmanned Aerial Systems (UAS) Passive Detection, Tracking, and Identification System for Ground Vehicles.
Department of Defense
The Department of Defense (DOD) is seeking proposals for the development of an Unmanned Aerial Systems (UAS) Passive Detection, Tracking, and Identification System for Ground Vehicles. The goal of this Army Small Business Innovative Research (SBIR) topic is to develop a passive sensor system capable of detecting, tracking, and identifying single and multiple drones threatening ground vehicles. The system should have a range of up to 2km and provide full hemispherical coverage. It should also include a soldier user interface control panel and the ability to alert at least one operator. The system should be able to operate in wooded/dense environments or large metropolitan areas and be installable on tactical and combat ground vehicles, including Army watercraft. In Phase I, the technical feasibility of passive sensors for drone detection will be determined through computer simulations. The possibility of using passive electromagnetic acoustic, optical, and other innovative sensing for processing multiple drone signatures will be demonstrated. The classification of drone signatures using these passive sensor systems will also be explored. In Phase II, the solution to achieve the capabilities outlined in Phase I will be developed. Optimum materials for the development of passive low-power consumption sensors for UAS detection, tracking, and identification will be identified. Principles of building networks of passive sensors that utilize fast processing capabilities will be developed, along with learning algorithms for drone identification. The system will be evaluated for compliance with the GVSC owned vehicle base kit in the GVSC Vehicle Protection Integration Lab (VPIL). A prototype system will be delivered to GVSC for evaluation and demonstration. Phase III will focus on expanding the capabilities of the solution to simulate different environments and conditions, demonstrating its applicability for municipal security, law enforcement, and commercial vehicles. The solicitation is open until March 31, 2025. For more information and to submit a proposal, visit the DOD SBIR website at [solicitation_agency_url].
DOD SBIR 24.4 Annual - Continuous Time Spiking Neural Network Field Programmable Neural Network Array
Department of Defense
The Department of Defense (DOD) is seeking proposals for the development of a continuous time spiking neural network field programmable neural network array. This technology falls under the Integrated Network Systems-of-Systems critical technology area. The objective is to create a mixed signal, programmable spiking neural network array integrated circuit. This field programmable neural network array would provide flexibility and low cost for neural network applications in the DoD and Army. The research will focus on the feasibility of developing the network using analog memory, field programmable gate arrays (FPGA), and field programmable analog arrays (FPAA). The project will be conducted in two phases, with the second phase involving the development of a prototype and the proposal of a Future of Vertical Flight/UAS demonstration project. The ultimate goal is to fabricate the neural network array integrated circuit and commercialize it for both government and commercial applications, including automotive vision, medical electronics, and big data analytics. The project duration is from 2024 to 2025, and interested parties can find more information on the grants.gov website.