DON26TZ01-NV016 TITLE: Nudging Behaviors for Better Sleep
OUSW (R&E) CRITICAL TECHNOLOGY AREA(S): Applied Artificial Intelligence (AAI)
COMPONENT TECHNOLOGY PRIORITY AREA(S): Human-Machine Interfaces;Trusted AI and Autonomy
PROJECTED CMMC LEVEL REQUIREMENT: Level 2 (Self)
OBJECTIVE: Develop software for personalized and adaptive behavioral interventions (i.e., nudges) using commercial off-the-shelf (COTS) wearable hardware devices to promote and improve sleep outcomes and human performance in dynamic environments.
DESCRIPTION: Despite extensive research on the mechanisms of sleep and behavioral modifications to improve sleep, relatively little is known about how context-sensitive behavioral nudging systems—those that dynamically suggest small, adaptive changes based on real-time data—can improve sleep quality and overall performance outcomes in complex, high-stakes settings. Fatigue caused by inadequate sleep negatively affects service members' performance and has contributed to accidents—resulting in deaths and hundreds of millions of dollars in damage to ships, vehicles, and aircraft [Ref 1]. "Nudging" refers to subtle interventions that steer behavior without restricting choices [Ref 2]. For example, non-obvious changes in how options are presented (e.g., ordering, timing, framing) have been shown to significantly affect sleep behaviors and dietary choices [Ref 3]. Recent advances in wearable sensor technology (e.g., smartwatches, rings, sleep trackers, etc.) allow for continuous collection of physiological and behavioral data. Many hardware devices are coupled with software that provide notifications, advice, and suggestions, but these are often canned, static statements that are simply pushed to the user (i.e., a one-way notification) and are not personalized to the user and/or their data.
Delivering adaptive behavioral nudges that learn and track the user’s state and responses, evolve over time, and promote sustained positive behavior change is also critical for mitigating the impact of sleep on operations. The objective of this STTR topic is to develop personalized and adaptive behavioral interventions (i.e., nudges) using COTS wearable devices to promote and improve sleep outcomes and human performance in dynamic environments. Achieving this objective requires: (1) research into integrated theoretical frameworks for personalized behavior change, grounded in cognitive, physiological, and contextual variables, and informed by mathematical tools such as dynamical systems modeling; (2) the development of adaptive algorithms that leverage Machine Learning (ML) and Artificial Intelligence (AI) to integrate with existing wearable and embedded sensors to identify optimal timing, modality, and content for real-time, minimally-intrusive, adherence-supporting behavioral nudges across diverse user states and operational contexts; (3) the exploration of human-centered communication strategies for delivering behavioral insights and recommendations, ensuring interventions are not only well-timed but also subtle and capable of supporting an ongoing user-system relationship built on trust and voluntary engagement; and (4) empirical testing in ecologically valid environments, including experiments that collect sleep and performance metrics to evaluate effectiveness, generalizability, and long-term behavioral impact.
Equal emphasis will be placed on (1) advancing theoretical models of behavior change, sleep regulation, and performance adaptation and (2) developing AI/ML systems and communication strategies for delivering behavioral nudges.
This topic focuses on sleep behavior due to its broad applicability to the general population, its foundational role in human performance, and the relative ease and reliability of measurement. Proposed efforts should aim to develop generalizable algorithms that integrate complex mathematical modeling and ML with cognitive-behavioral theory to drive adaptive behavioral interventions. These interventions must be compatible with existing wearable and embedded sensor ecosystems – this topic explicitly does not aim to develop new hardware, but instead to maximize the utility of currently available commercial sensors as inputs to a personalized, adaptive nudging system.
PHASE I: Develop early research plans, concepts/prototypes, and requirements for investigations into: (1) theoretical models of real-time behavioral change, intervention receptiveness, and nudging effectiveness that combines psychology (e.g., behavioral, cognitive, decision sciences), mathematics (e.g., dynamical systems), computer science (e.g., AI/ML, human-computer interaction), physiology (e.g., sleep science, chronobiology), and communications (e.g., persuasive communication, dialogic interaction systems; (2) develop a system that integrates AI/ML decision engines that dynamically adapts nudge timing, content, and delivery method based on physiological, cognitive, and contextual data and measures nudge compliance and effectiveness all in service of positively impact sleep behavior.
Tasks and environments should reflect the unique operational demands of the naval context, including irregular sleep schedules, sustained attention during extended operations, and decision-making under fatigue. Critical elements of the Phase I effort are to describe the research and engineering plans that would be executed during a potential Phase II and provide evidence of the feasibility of the approach, emphasizing the current state of the research and how the approach is both innovative and achievable.
Prepare Phase II plans that should include key component technological milestones and plans for at least one operational test and evaluation to include user testing.
Due to the potential for long review times involved, formal human subject research is prohibited during Phase I.
PHASE II: Conduct and implement interdisciplinary research in the fields of psychology, physiology, mathematics, and computer science to develop and evaluate a prototype system with sailors (coordination aided by ONR) outlined during the Phase I. Include parallel but interrelated research and engineering tracks that will deliver iterative prototypes that will undergo design and testing reviews, to include usability assessment and effectiveness evaluations where appropriate. Collect both subjective and objective metrics regarding nudge usefulness, compliance, sleep quantity and quality through the development process. Perform all appropriate engineering tests and reviews, including a critical design review to finalize the system design. Produce the following deliverables: (1) additional research into development, adaptation, and delivery of behavioral nudges with a particular emphasis on sleep and fatigue; (2) a working prototype of the system that leverages existing COTS sensors, wearables, and hardware; (3) evaluation of system usability and compliance regarding effectiveness of nudges; (4) a system effectiveness evaluation of system capabilities to produce improved sleep quantity and/or quality.
DON will provide Phase II awardees with the appropriate guidance required for human research protocols. Institutional Review Board (IRB) determination as well as processing, submission, and review of all paperwork required for human subject use can be a lengthy process. As such, no human research will be allowed until Phase II and work will not be authorized until approval has been obtained, typically as an Option to be exercised during Phase II.
PHASE III DUAL USE APPLICATIONS: Support the Navy in transitioning the technology for fielding. Develop the software for evaluation to determine its effectiveness in operational settings. As appropriate, focus on broadening capabilities and commercialization plans. Development of affordable, scalable, non-proprietary technologies are needed to take data generated by COTS hardware and sensors into actionable information that can be delivered as personalized nudges.
The commercial sector is developing some of these AI-enabled sleep technologies, but they often do not deal with critical issues regarding complex environments and dynamic contexts, do not address encryption and classification requirements, and often come with prohibitive licensing and usage fees. This technology will have broad application in the commercial sector.
REFERENCES:
KEYWORDS: behavior change; adaptive systems; human performance; sleep and fatigue; dynamical systems modeling
TPOC 1
Peter Squire
peter.n.squire.civ@us.navy.milTPOC 2
Jason Wong
jason.h.wong.civ@us.navy.mil
** TOPIC NOTICE ** |
The Navy Topic above is an "unofficial" copy from the Navy Topics in the DoW FY-26 Release 1 SBIR BAA. Please see the official DoW Topic website at www.dodsbirsttr.mil/submissions/solicitation-documents/active-solicitations for any updates. The DoW issued its Navy FY-26 Release 1 SBIR Topics pre-release on April 13, 2026 which opens to receive proposals on May 6, 2026, and closes June 3, 2026 (12:00pm ET). Direct Contact with Topic Authors: During the pre-release period (April 13, through May 5, 2026) proposing firms have an opportunity to directly contact the Technical Point of Contact (TPOC) to ask technical questions about the specific BAA topic. The TPOC contact information is listed in each topic description. Once DoW begins accepting proposals on May 6, 2026 no further direct contact between proposers and topic authors is allowed unless the Topic Author is responding to a question submitted during the Pre-release period. DoD On-line Q&A System: After the pre-release period, until May 20, 2026, at 12:00 PM ET, proposers may submit written questions through the DoW On-line Topic Q&A at https://www.dodsbirsttr.mil/submissions/login/ by logging in and following instructions. In the Topic Q&A system, the questioner and respondent remain anonymous but all questions and answers are posted for general viewing. DoW Topics Search Tool: Visit the DoW Topic Search Tool at www.dodsbirsttr.mil/topics-app/ to find topics by keyword across all DoW Components participating in this BAA.
|