N221-017 TITLE: Manned-Unmanned Teaming Survival in an Adaptive World

OUSD (R&E) MODERNIZATION PRIORITY: Artificial Intelligence (AI)/Machine Learning (ML);Autonomy;General Warfighting Requirements (GWR)

TECHNOLOGY AREA(S): Battlespace Environments;Electronics;Information Systems

OBJECTIVE: Develop and demonstrate an innovative, mission effective Unmanned Air Vehicle (UAV) capability to assist manned-unmanned teaming (MUM-T) to challenge and/or negate radars and radar networks by enabling UAVs to automatically sense and communicate weaknesses in a radar and/or radar networks.

DESCRIPTION: Current airborne electronic warfare (EW) systems must first identify a threat radar to determine the appropriate preprogrammed electronic countermeasure (ECM) technique. This approach loses effectiveness as radars evolve from fixed analog systems to programmable digital variants with unknown behaviors and agile waveforms. Future radars will likely present an even greater challenge as they will be capable of sensing the environment and adapting transmissions and signal processing to maximize performance and mitigate interference effects.

A growing concept in the field of MUM-T is the idea of using a team of cooperating unmanned and manned air vehicles to significantly challenge and/or negate existing and/or new, unknown, and adaptive radar networks in real time. Some MUM-T strategies to challenge radar networks may include using either jamming techniques, deception techniques, or a combination of the two, to assist in completing MUM-T mission objectives. A UAV may be tasked to engage a radar or radar network using noise jamming to mask its radar return or that of another vehicle. Similarly, a UAV may be assigned to deceive a radar by directing a delayed signal toward the victim radar, which has the effect of producing a radar phantom perceived by the radar as an object at a false range and/or bearing. Depending on the number of UAVs in the MUM-T and the number of radars in the radar network, the UAVs may be able to employ different strategies simultaneously.

A characteristic of these MUM-T strategies is that they require the UAVs to follow time-critical, directionally dependent trajectories with tight constraints in order to be successful, from the start of the defensive task to the very end. It is absolutely necessary that UAVs are able to control their own movements during defensive tasks, as well as navigate in a coordinated fashion enroute to the subsequent tasking. A valid configuration for a UAV is a position in the three-dimensional space environment, which is collision free. At any given trajectory, the algorithm generates a random node and, subsequently, inspects the trajectory path from the generated node to closest previously expanded node for collisions. If collisions exist along the trajectory path, the generated node is discarded and a new random node is generated; otherwise, the generated node is added to the set of expanded nodes. The goal state is reached and ultimately a collision-free path from start to goal state in the three-dimensional environment. UAVs participating in MUM-T missions will need to have local analysis and action capabilities, as well as the ability to speak with and update each other.

The successful completion of this SBIR effort will culminate in demonstrations of the MUM-T challenge and/or negate capabilities being able to:

• Isolate unknown radar signals in the presence of other hostile, friendly, and neutral signals.
• Deduce the threat posed by a radar and/or a radar network.
• Synthesize and transmit signals to achieve a desired effect on the radar and/or a radar network.
• Assess the effectiveness of strategies based on radar and radar network behaviors.

Simulation-based demonstrations of the effectiveness of small UAV sensor suites in performing various challenging and/or negating missions will help planners and decision makers determine the appropriate mix of UAVs and sensors that will be required to support MUM-T missions, and will show performance as a function of system cost. The flexibility of distributing the sensors across several Group 1-5 UAV platforms enables customized sensor suite solutions that both meet various mission needs and minimize cost. Therefore, a MUM-T member will not have to pay for sensing capabilities that they do not want or require.

This SBIR topic seeks to develop a MUM-T challenging and/or negating product(s), which includes the following features and functions:

• High-Level Decision Maker—adaptive allocation to each payload manager
• Director—multifunction optimization and conflict resolution
• Multiobjective Optimization and Learning Engine—dynamic, context-based learning
• Weight Adjuster—autonomously adapt to multiple UAV trajectories
• Compliant interfaces—seamless connection to external subsystems
• Multiobjective reasoning in dynamically changing environments
• Context-based consideration of long-term benefits and tradeoffs in effect option set selection
• Efficient resource allocations
• Reinforcement learning framework that overcomes uncertainty and avoids reliance on static models
• Adaptation across multiple timescales to accommodate dynamic contested environment
• Robust to different environments through contextual processing
• Integration with nonstandard platforms via translation with platform agnostic reasoning
• Vendor-agnostic integration with various Group 1-5 UAV platforms and their respective systems and subsystems
• Hybrid decentralized approach for local decisions to support multiplatform collaboration
• Near real-time mission feedback with reduced processing times
• Lightweight signaling in a hierarchical command and control (C2) structure supporting battlefield applications with multiple distributed platforms
• Negating radio frequency (RF), cyber takeover of unmanned air vehicles

Work produced in Phase II may become classified. Note: The prospective contractor(s) must be U.S. owned and operated with no foreign influence as defined by DoD 5220.22-M, National Industrial Security Program Operating Manual, unless acceptable mitigating procedures can and have been implemented and approved by the Defense Counterintelligence and Security Agency (DCSA) formerly Defense Security Service (DSS). The selected contractor must be able to acquire and maintain a secret level facility and Personnel Security Clearances. This will allow contractor personnel to perform on advanced phases of this project as set forth by DCSA and NAVAIR in order to gain access to classified information pertaining to the national defense of the United States and its allies; this will be an inherent requirement. The selected company will be required to safeguard classified material IAW DoD 5220.22-M during the advanced phases of this contract.

PHASE I: Research, develop, and propose a design concept with the potential of realizing the goals in the Description above. Describe and quantify how the proposed solution offers enhancement(s) over current technology approaches and/or how it augments other strategies/technologies. Conduct necessary investigation and simulation on the design and performance of the components to demonstrate the feasibility and practicality of the proposed system design, minimizing user input. Identify any technical challenges that may cause a performance parameter(s) not to be met, results of any modeling, safety issues, and estimated costs. The Phase I effort will include prototype plans to be developed under Phase II.

PHASE II: Develop, optimize, demonstrate, and deliver the technology identified in Phase I. The technology derived designs will then be modified as necessary to produce final prototypes. Work with the Government team to test the algorithms against data collected from candidate sensors relevant to the Navy with Government furnished MUM-T air vehicles. The prototypes must be capable of demonstrating the performance goals stated in the Description above in a rapid prototype experiment demonstration (RPED) environment. Phase II will include MUM-T field testing against a radar of interest with at least 10 UAVs and one manned aircraft to validate performance claims. Document the design specifications, performance characterization, and any recommendations for future development.

Work in Phase II may become classified. Please see note in Description paragraph.

PHASE III DUAL USE APPLICATIONS: Incorporate the lessons learned from Phase II into the detailed design. Further, refine detailed design to address any unique requirements and to improve performance robustness and capability for manned-unmanned team operational scenarios. Develop preproduction and production components and subsystems for integration into manned and unmanned air and ground vehicles. Further miniaturization and low-cost manufacturability of the capability may be required. Develop relevant environment test methods and evaluate the final designed system performance in field or at sea demonstrations.

Integrate the technology using engineering model of proposed product/platform or software, along with full report of development, capabilities, and measurements (showing specific improvement metrics).

Military Application: Integration of the products and resulting capabilities with current and future manned and unmanned aircraft teams will enhance team survivability during electronic warfare engagements against layered defense systems.

Commercial Application: Potential low-cost development program for unmanned systems to autonomously, interoperate with other unmanned and manned systems in uncontrolled, unsupervised, underwater, ground, and airspace environments or operations safely, e.g., package delivery and photography.

REFERENCES:

1. Pachter, M., Chandler, P. R., Purvis, K. B., Waun, S. D., & Larson, R. A. (2004). Multiple radar phantom tracks from cooperating vehicles using range-delay deception. In Theory and Algorithms for Cooperative Systems (pp. 367-390). https://doi.org/10.1142/9789812796592.
2. Vakin, S. A., Shustov, L. N., & Dunwell, R. H. (2001). Fundamentals of electronic warfare. Artech. https://www.worldhistory.biz/download567/FundamentalsofElectronicWarfare_worldhistory.biz.pdf.
3. Dubins, L. E. (1957). On curves of minimal length with a constraint on average curvature, and with prescribed initial and terminal positions and tangents. American Journal of Mathematics, 79(3), 497-516. https://doi.org/10.2307/2372560.
4. Dennis Jr, J. E., & Schnabel, R. B. (1996). Numerical methods for unconstrained optimization and nonlinear equations. Society for Industrial and Applied Mathematics. https://books.google.com/books?hl=en&lr=&id=ksvJTtJCx9cC&oi=fnd&pg=PR1&ots=BKjNEK9Jxx&sig=D_WgyKYkpZY8Xv_mEs4qGe-RSbA#v=onepage&q&f=false.
5. Grabbe, M. T., & Hamschin, B. M. (2013). Geo-location using direction finding angles. John Hopkins APL Technical Digest, 31(3), 254-262. https://www.jhuapl.edu/Content/techdigest/pdf/V31-N03/31-03-Grabbe.pdf.
6. Hughes, E. (2018, October). Detecting drones with Doppler-based radar. Aerospace & Defense Technology. Retrieved June 28, 2021, from https://www.aerodefensetech.com/component/content/article/adt/features/articles/33023.
7. de Quevedo, Á. D., Urzaiz, F. I., Menoyo, J. G., & López, A. A. (2019). Drone detection and rcs measurements with ubiquitous radar. Information Processing and Telecommunications Center. Universidad Politécnica de Madrid, Madrid, Spain, 2019. https://radar2018.org/abstracts/pdf/abstract_74.pdf.
8. Department of Defense. (2006, February 28). DoD 5220.22-M National Industrial Security Program Operating Manual (Incorporating Change 2, May 18, 2016). Department of Defense. https://www.esd.whs.mil/portals/54/documents/dd/issuances/dodm/522022m.pdf.

KEYWORDS: Unmanned Air Vehicle; UAV; Manned-Unmanned Team; MUM T; electronic warfare; EW; reinforcement learning; simulation; radar