Department of the navy (don) 17. 1 Small Business Innovation Research (sbir) Proposal Submission Instructions introduction

3. Y. Jiang, C. Zhang, D. Wu, and P. Liu. “Feature-based Software Customization: Preliminary Analysis, Formalization, and Methods.” In Proceedings of the 17th IEEE High Assurance Systems Engineering Symposium (HASE), Orlando, FL, 2016.

4. T. Kalibera, P. Maj, F. Morandat, and J. Vitek. “A Fast Abstract Syntax Tree Interpreter for R.” In Proceedings of the International Conference on Virtual Execution Environments, New York, NY, 2014.-

KEYWORDS: software; feature reduction; Java; JavaScript; Python; C/C++; programming; efficiency; cyber; security; performance

Questions may also be submitted through DoD SBIR/STTR SITIS website.

N171-084

TITLE: Artificial Intelligence for Infantry Simulation in Small Unit Decision Making Training

TECHNOLOGY AREA(S): Human Systems

ACQUISITION PROGRAM: CMP-FY15-01: Accelerating Development of Small Unit Decision Makers

OBJECTIVE: Develop technologies to support the construction of Artificial Intelligence agents for use in simulations in infantry small unit decision making training. Agents must have realistic “thinking”, require minimal manual coding and editing of behaviors, and the tools must be capable of developing behaviors across a range of military infantry activities.

DESCRIPTION: Simulation is a key enabler for training that allows Warfighters to develop their skills without incurring costs associated with training (e.g. fuel, munitions, etc.) or putting their safety at risk [1]. The use of first-person simulations (e.g., Virtual Battle Space 3) for infantry training is manpower-intensive, requiring additional operators (i.e., pucksters) to control friendly and enemy military units, limiting the ability to training only individual unit leaders (e.g. squad) without additional manpower support.

Historically, the military has long supported the use of constructive agents and virtual humans [2, 3] –although their application within the Marine Corps has been limited [1]. Infantry small unit leaders need simulation-based training without the manpower costs associated with pucksters –such as training that leverages intelligent and behaviorally realistic agents that are easy to teach. Agents are autonomous entities capable of goal-directed activities based on their perception of the simulated environment, such that military personnel interacting with them would not require extensive training nor amount to a frustrating undertaking.

Advances in Artificial Intelligence (AI) have increased machines' capability to learn and allow machines to outperform humans on video games and board games [4, 5]. However, these techniques require a very large dataset for training and are mostly constrained to discrete domains. As such, these approaches are not easily extensible to the infantry simulation where rules and environments are ill-defined and action spaces are continuous. Aside from deep reinforcement learning, other approaches that complement traditional human learning have been investigated. For example, Interactive Task Learning (ITL) is an approach to support artificial agents learning new tasks through natural interactions and observations with humans [6]. The Air Force Research Laboratory (AFRL) has been developing a Synthetic Teammate capability [7], but there has been limited application to the infantry domain.

The goal of this effort is to develop technologies to support the construction of intelligent artificial agents in order to reduce the manpower required to develop and oversee the execution of those agents within infantry training first-person simulations. The focus of the training is on developing AI-based behavior for friendly and enemy agents to support Marine Corps Forward Observers training. In addition to the technologies for agent learning, there is also a need to develop metrics and evaluations that can span across multiple Infantry tasks and domains.

All development and demonstrations should be done with simulation engines that have no or minimal licensing fees for development or run-time execution (e.g. Unity).

PHASE I: Required Phase I deliverables will include a feasibility study. Included in this study will be an initial concept design for Artificial Intelligence for Infantry Simulation in Small Unit Decision Making Training that models key elements as well as a detailed outline of success criteria. Additionally, at least one behavior using the technologies proposed should be developed. Since access to Marine Corps personnel will not be supported during Phase I, surrogate tasks are acceptable for proof of concept. A final report will be generated, including system performance metrics and plans for Phase II. Ensuring an “open architecture” to allow integration with other military relevant systems (e.g. Augmented Immersive Team Trainer, Virtual Battle Space 3) will be considered a critical performance metric. Phase II plans should include key component technological milestones and plans for at least two demonstrations.

PHASE II: Phase II will include further behavioral development and evaluations with at least two evaluations from SME representatives that will be identified from the government. Required Phase II deliverables will include the construction, demonstration, and validation of a prototype system based on results from Phase I. All appropriate engineering testing will be performed and a critical design review will be performed to finalize the design and technologies before the evaluations. Additional deliverables will include: 1) a working prototype, 2) any associated drawings and specification for its construction, and 3) test data on its performance, in accordance with the demonstration success criteria developed in Phase I.

PHASE III DUAL USE APPLICATIONS: The performer will be expected to support the Marine Corps in transitioning the software products that enable the construction of intelligent and behavioral realistic agents for Infantry small unit training. The software products are expected to support and/or be integrated with existing Marine Corps training simulations (e.g. Augmented Immersive Team Trainer, Virtual Battle Space 3). Phase III tasks will include certifying and qualifying the system for Marine Corps use, delivering a Marine Corps user manual for the product, and providing Marine Corps system specification materials. Private Sector Commercial Potential: It is anticipated this technology will have broad applications in military as well as commercial settings. The use of artificial intelligence (AI) is continuing to grow, but it is currently limited to certain sets of tasks. For example, virtual reality is currently being used by some professional sports teams (e.g. NFL), but has limited or no AI application. It would be very beneficial to allow position specific (e.g. Quarterback) training that supports realistic agent behavior so that players can practice for upcoming games and specific opponents either with their team or independently.

REFERENCES:

1. Naval Research Advisory Committee. (2009). Immersive Simulation for Marine Corps Small Unit Training. Retrieved 6 June 2016 from http://www.nrac.navy.mil/docs/2009_rpt_Immersive_Sim.pdf

2. Pew, R. W., & Mavor, A. S. (Eds.). (1998). Modeling human and organizational behavior: Application to military simulations. National Academies Press.

3. Zacharias, G. L., MacMillan, J., & Van Hemel, S. B. (Eds.). (2008). Behavioral modeling and simulation: From individuals to societies. National Academies Press.

4. Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., ... & Petersen, S. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529-533.

5. Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., ... & Dieleman, S. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587), 484-489.

6. Laird, J. (2014). Report on the NSF-funded Workshop on Taskability (Interactive Task Learning).

7. Ball, J., Myers, C., Heiberg, A., Cooke, N. J., Matessa, M., Freiman, M., & Rodgers, S. (2010). The synthetic teammate project. Computational and Mathematical Organization Theory, 16(3), 271-299.-

KEYWORDS: Artificial Intelligence (AI); Simulation Training; Autonomous Agents; Human-Robot Interaction (HRI); Machine Learning; Constructive Agents; Virtual Humans

Questions may also be submitted through DoD SBIR/STTR SITIS website.

TECHNOLOGY AREA(S): Materials/Processes, Sensors, Weapons

ACQUISITION PROGRAM: PMS-405, Navy Directed Energy and Electric Weapons program office, Surface Navy Laser Weapon System (SNLWS) Program

OBJECTIVE: The objective of this topic is to develop, design, construct, and deliver a compact, transportable instrument that can characterize ultra-short pulsed laser pulses including all spatial, temporal, spectral, pulse energy, and phase properties on a pulse-by-pulse basis.

DESCRIPTION: The characterization of ultra-short pulsed laser (USPL) pulses typically requires multiple instruments that separately measure and report key properties of the pulse, followed by analyses that incorporate the various data streams into a consolidated understanding of the laser performance. Individual instruments often include average power or pulse power meters, devices for measuring pulse duration, spectrum analyzers, instruments for measuring the wavefront, and beam spatial profilers. This is unsatisfactory for Navy needs because the individual instruments often require significant expertise to operate, maintain, and interpret. Furthermore, the individual instruments are often bulky and highly sensitive to the environment, and are not easily or readily co-integrated with one another. More importantly, using separate, non-integrated instruments prevents the user from having a holistic and easily interpreted understanding of the laser performance without detailed analysis. Finally, the physical size and weight of carrying multiple instruments is unsatisfactory for Navy needs where deck (or rack) space, weight, power, and cooling services are severely restricted. .

The Navy is interested in developing a single, robust, fully integrated and user-friendly instrument suite that measures and reports USPL pulse characteristics in a holistic manner in a compact and transportable package. A comprehensive USPL characterization suite would incorporate, at a minimum, instruments to measure pulse energy, pulse duration (including residual long pulse 'pedestals'), beam spatial profile, spectral content, and a means to evaluate the pulse phase. The system would implement a comprehensive software package for pulse analysis and include a user interface that allows a single trained operator to control the system and monitor all of the salient properties of an ultra-short pulsed laser beam on a single display screen.

Physically, the system should be transportable by no more than 2 persons, run off of standard electrical supplies (120VAC, or preferably, rechargeable battery supplies) and interface with a single laptop computer or, preferably, a single hand-held device. Systems that require external cooling supplies or become inoperable outside narrowly controlled environmental conditions are undesirable.

PHASE I: The Phase I effort should focus on identifying commercial or developmental instrument(s) that can be used to measure the spectral, spatial, temporal, and energetic properties of a Ultra Short Pulsed Laser (USPL) beam, and which can be miniaturized or integrated into a single platform or suite of diagnostic tools. The resulting product concept should be capable of comprehensively and holistically reporting the key properties of a USPL beam in real time with a user-friendly interface and packaged in a compact, transportable package suitable for outdoor field testing. Required Phase I deliverables will include a mature design concept of required instrumentation to perform the requisite pulse measurements, an estimate of the size, weight, and power required for the system, and a complete description of the concept of operation, packaging concepts, and proposed user interface.

PHASE II: The Phase II effort will produce the proposed product concept in a prototypical configuration. The small business will perform the requisite engineering processes to complete the design, acquire the necessary components, integrate them into a single package, build, demonstrate, and validate that the product can comprehensively and holistically measure and report the key properties of a USPL beam in real time with a user-friendly interface. The resulting system must be demonstrated in an outdoor field test environment and operated by a single user with minimal maintenance of internal components.

PHASE III DUAL USE APPLICATIONS: Phase III activities will include the development and execution of a plan to manufacture a production-level instrument based on the Phase II prototype and assist in the engineering, integration, and testing of the production level system with existing or future Naval programs (potential future transition programs may include the Surface Navy Laser Weapons System, or a future PEO IWS sponsored program of record or Navy prototype system. Integration into Navy Directed Energy test ranges as a test asset may also be possible. Beyond these projected Navy transition paths, there are a variety of potential commercial applications; a comprehensive and user friendly diagnostic instrument suite would find utility in any manufacturing or laboratory environment where ultra-short pulsed lasers are used. Private Sector Commercial Potential: A comprehensive, transportable, USPL diagnostic system will have a multitude of commercial applications, ranging from a scientific laboratory instrument to a tool for maintaining USPL-intensive manufacturing equipment.

REFERENCES:

1. G. P. Agrawal, Nonlinear Fiber Optics, Third Edition, San Diego, CA: Academic Press, 2001.

2. J-C. Diels and W. Rudolph, Ultrashort Laser Pulse Phenomena, Academic Press 1996. -

KEYWORDS: laser, lasers, ultra-short pulsed lasers, laser instrument, instrument, diagnostic tools, transportable

Questions may also be submitted through DoD SBIR/STTR SITIS website.

N171-086

TITLE: Compact, Low Loss, Broadband Power Inductors for Navy Sonar Applications

TECHNOLOGY AREA(S): Electronics, Sensors

ACQUISITION PROGRAM: Undersea Tracking Range Equipment Program, NAVSEA 05H3

OBJECTIVE: Develop compact, low loss, high power inductors with inductances >25 mH to match single crystal projectors to power amplifiers in a size suitable for use in Unmanned Underwater Vehicles (UUV), improving energy efficiency by at least 50% and thereby increasing vehicle operational availability.

DESCRIPTION: Single crystal transducers are of interest in Navy and maritime application for their compact size, high acoustic output and broad bandwidth. These single crystal transducers require tuning inductors to provide optimal matching to the power amplifier. Such matching can allow nearly 100% of the amplifier power to reach the transducer over as much as 2.5 octaves of frequency, which allows an efficiency improvement of nearly 100% over the band over current ceramic based transducer technology. Such power matching is critical to efficiently utilize power in platforms with limited energy resources such as UUVs. Particularly at lower frequencies, the tuning inductance values can be quite large (>25 mH). Additionally, these inductors must be able to withstand input voltages up to 600 Vrms. It must also have low losses (DC resistance less than 2 ohms) and low harmonic distortion. For both size and energy constrained environments like UUVs, inductors with values this large that are stable over a wide bandwidth and have low loss do not exist in a compact form factor. Current high power inductors with values >25 mH are either too large for size constrained platforms like UUVs or have DC resistance values of 20 ohms or more. The objective of this program is to develop compact high power tuning inductors that exhibit stable properties over a 10-40 kHz bandwidth, and operate under drive voltages able to withstand up to 600 Vrms and input power levels of 180 W with harmonic distortion levels of -50 dB or less at the 2nd harmonic. The maximum size should be less than 0.85” OD by 0.54”H, and the inductance and loss must remain constant over a temperature range from -10°C to 85°C. Producing these inductors may require use of novel magnetic materials, manufacturing and/or packaging. Availability of these broad band, low loss, high power tuning inductors can extend operational availability of UUVs by better utilizing available energy resources.

PHASE I: Develop a conceptual design for a low loss, broadband, compact tuning inductor to meet the inductance, loss and distortion level targets identified in the objective and description sections. Identify candidate materials and topologies to meet these requirements. Conduct a proof of feasibility analysis on the stability of the inductance over the frequency range and estimate the potential heat generated during operation under 180 W input.

PHASE II: Fully develop candidate inductor designs identified in Phase I. Construct prototypes that conform to the required 0.85” OD by 0.54”H size constraint. Demonstrate conformance to inductance, loss and distortion requirements over the frequency and temperature ranges identified in the Description section. Using a dummy load representative of a notional single crystal transducer provided by the Navy TPOC, demonstrate stable performance using 600 V and 180 W input using both sine and white noise pulses. Demonstrate reproducibility of design by constructing and testing no fewer than 5 inductors of the chosen design. Identify any issues with manufacturing scalability of the selected design and estimate potential production costs.

PHASE III DUAL USE APPLICATIONS: Demonstrate scalability of the design by constructing 100 of the tuning inductors and testing for conformance with the design goals in the Description section. Working with the Navy POC, transition the inductor technology into the Undersea Tracking Range Equipment (UTRE) Program. Private Sector Commercial Potential: Unmanned underwater vehicles have become ubiquitous in the oceanographic community and oil exploration industry. The use of single crystal transducers provide a high power, compact, broadband transducer technology for acoustic communications and surveying. Since the vehicles have considerable power constraints, providing compact tuning inductors to utilize available energy resources more effectively.

REFERENCES:

1. K.A. Snook, P.W. Rehrig*, W.S. Hackenberger, and X. Jiang, "Advanced Piezoelectric Single Crystal Based Transducers for Naval Sonar Applications," Smart Structures and Materials 2005: Active Materials: Behavior and Mechanics, Proceedings of SPIE Vol. 5

2. M.B. Moffett MB, H.C. Robinson, J.M. Powers and P.D. Baird, "Single-crystal lead magnesium niobate-lead titanate (PMN/PT) as a broadband high power transduction material", J Acoust Soc Am., vol. 121, pp. 2591-2599 (2007).

3. D. Stansfield, Underwater Electroacoustic Transducers, Peninsula Publishing (2000).-

KEYWORDS: transducer; single crystal; tuning; inductor; broadband; transduction

Questions may also be submitted through DoD SBIR/STTR SITIS website.

TECHNOLOGY AREA(S): Air Platform, Ground/Sea Vehicles

ACQUISITION PROGRAM: Autonomous Aerial Cargo Utility System (AACUS) INP, MCSC Program Manager for Armor and Fire Support Systems (PM AFSS) Fire Support Systems

OBJECTIVE: Develop an autonomous cargo loading/unloading system to be demonstrated in conjunction with the Autonomous Aerial Cargo Utility System (AACUS) equipped UH-1H Optionally Piloted Aircraft (OPA) that will provide a capability to deliver supplies autonomously to a manned or unmanned location.

DESCRIPTION: Currently no system exists that allows for autonomous loading/unloading of cargo in a tactical/austere landing zone after touchdown of the AACUS equipped UH-1H aircraft (AEH-1) and the UH-1Y aircraft. Cargo missions today still require manpower for deploying and unloading of cargo from the air vehicle. This results in a reliance on manpower for unloading tasks, as well as fire teams in unsecured locations. Autonomous capability to load and unload cargo would greatly reduce burden on troops in the field to move supplies out of the supplying aircraft. Manual handling of cargo increases time the aircraft is on the ground in the Landing Zone and increases exposure of personnel.

AACUS is a sensor suite and software package designed to operate an unmanned rotary wing aircraft into and out of an unprepared landing site while conducting the Assault Support mission. It is an applique (i.e. kit) that is installed on an aircraft and the effort would be an additional capability of the kit for applicable aircraft. The UH-1H demo will be a proof of concept for installing on later aircraft such as the UH-1Y and H-60. This will expand the autonomous capabilities of the AEH-1 by developing an unmanned/automatic solution to handling cargo in an unprepared and unmanned landing zone. This Autonomous Cargo Handling System (ACHS) should leverage the AACUS kit‘s STANAG-4586 [1] compliance to enable real-time sensor data sharing and communication with the AACUS system. Technical Risks will include Autonomous interaction of manned/unmanned platforms, effectiveness in unprepared environments, “cargo agnostic” handling capabilities and integration with legacy aircraft and expansion ability to future platforms including the UH-1Y. Current load capacity and characteristics, center of gravity limitations, and cargo compartment capabilities are available in U.S. Department of the Army, “Operator's Manual: Army Model UH-1H/V Helicopters [2]. Load and unload time should be comparable to expected times for manual cargo handling for similar cargo delivery sizes in manned conditions.

PHASE I: During Phase I, the small business will define and develop a concept for the Autonomous Cargo Handling System (ACHS). The company will develop the testing and validation methodology for the ACHS, along with performance parameter goals, not limited to speed of loading/unloading and load capacity, size, weight, volume, interface, and power requirements. The system should be able to be modular and designed to be rapidly removed from the host aircraft in less than 8 hours (threshold) and 4 hours (objective). Full interfacing functionality with the UH-1H cargo access door is required [2]. Highlight the design choices that ensure future interoperability with other platforms including the UH-1Y and H-60. Key deliverables in Phase I would be documentation of conceptual design that would lay the framework for prototyping in Phase II.

PHASE II: Develop an Autonomous Cargo Handling System prototype based on the Phase I efforts. Validate performance parameters and technical goals expressed in Phase I final report through an iterative test schedule. Demonstrate the performance capabilities of the autonomous cargo handling system and architecture that includes the following activities: