AI/ML-Enabled Voice-Commanded Autonomous Maneuver for Ground Combat Vehicles
Operating, maneuvering, engaging, defending, and commanding the Combat Vehicles on the modern battlefield requires a significant level of crew communication, systems management, and situational awareness. As a result, it imperative to reduce the cognitive burden on vehicle crews and enable rapid decision-making, especially during combat. To support this, the US Army is seeking innovative solutions that will enable autonomous maneuvers in response to crew commands issued with natural language.
Automated Course of Action Generation
Several approaches to CoA generation for military applications currently exist. These methods leverage large language models (LLM) applied to Doctrine or deep learning/hierarchical modeling applied to wargaming. Each existing LLM approach is inadequate for CoA generation at BN due to lack of proper consideration of Tactics, Techniques and Procedures (TTPs) and Standard Operating Procedures (SOPs) for both friendly and enemy forces. The existing learned/hierarchical approaches that depend on wargaming are also inadequate due to a lack of fully automated wargaming capability at the BN echelon and/or due to CoA outcomes that are not aligned with best practices (TTPs and SOPs). Proposals submitted under this topic will leverage state-of-the-art Artificial Intelligence (AI) approaches to create a CoA recommendation module narrowly tailored to the BN echelon. This capability will expand to encompass higher echelons in later phases.
Cold Regions Research and Engineering Laboratory CSO
The U.S. Army Engineer Research and Development Center's Cold Regions Research and Engineering Laboratory is looking to obtain innovative solutions or potential new capabilities in the following categories: Building Cold Region Domain Awareness, Enhancing Mobility and Maneuver in Cold Region Environments, Integrated Ice Operations, Advanced Materials Development and Applications in Extreme Cold Environments, and Resilient Cold Region Energy Systems.
Language Models for Veteran Suicide Prevention (LM4VSP)
On September 22, 2021, the US House Veterans Affairs Committee held a hearing entitled, “Veteran Suicide Prevention: Innovative Research and Expanded Public Health Efforts” [1]. The hearing followed the release of annual data from the US Department of Veterans Affairs showing that the disproportionate rate of veteran suicide is a public health crisis [2]. Although there is no single reason why veterans commit suicide, evidence suggests that stable housing, financial security, access to healthcare, addressing social isolation and loneliness, and treating the effects of trauma are important components of a comprehensive suicide prevention strategy; all of which require coordination and cooperation across families, communities, and at all levels of government. Recent advances in AI, and specifically LMs, have the potential to help lessen the effects of social isolation/loneliness and trauma. According to a 2019 report on “Sleep and timing of death by suicide among US Veterans 2006-2015” [McCarthy, et al. 2019], the raw proportion of veteran suicides peaks between the hours of 1000 and 1200; however, the peak prevalence of suicide, after accounting for the population being awake, is between the hours of 0000 and 0300 (p < 0.00001, F = 0.88). The highest Standardized Incidence Ratio (SIR) is at midnight; US Veterans are eight times more likely to die by suicide than expected given the population awake (SIR = 8.17; 95% Confidence Interval = 7.45-8.94). In other words, when clinical help is likely unavailable or difficult to access, technology has the potential to provide critical assistance. Recent advances in the field of natural language processing have allowed LMs (for example, Chat GPT (Generative Pre-trained Transformer)) to be fine-tuned using reinforcement learning based on human feedback [3]. Prior efforts have shown that it is possible to create a highly conversational model based on 40,000 pieces of feedback [4]. Other recent research work in the field suggests promising results in prompt engineering [5], using memory-based machine learning with dramatic improvements in the LM’s ability to stay on task, and return more accurate and precise results. [6] LM4VSP seeks to develop a clinical co-pilot based on LMs specific to the mental health subdomain, and in close collaboration with mental health subject matter experts (SMEs). The goal is for the LM4VSP clinical co-pilot to enable caregivers to offer around-the-clock assistance and accelerate their understanding and assessments and improve the effectiveness of intervention.
Large Language Models for System Security Engineering Analysis
The primary problem this topic addresses is the growing complexity of traditional and AI/ML-based cybersecurity threats to DoD weapon systems, increasingly connected and automated weapon systems architectures, and the need for advanced tools to enhance development-phase cyber resiliency efforts and exploit modeling. This topic is essential because it will improve US DoD aviation and missile platforms’ resilience, survivability, and lethality through the enhanced identification and exploitation modeling of system vulnerabilities during system development. This will achieve significant impact in the most cost-effective phase of the system lifecycle. The proposed approach leverages state-of-the-art LLMs to develop a specialized tool for system security engineering risk reduction efforts (blue team and AAMCATs) and provides critical exploitation inputs to DoD-approved red team operations. This topic innovates on existing technology by fine-tuning a foundational LLM built to analyze complex weapon system codebases, identify vulnerabilities, and generate proof-of-concept exploits. This approach combines natural language processing and code analysis capabilities, creating a powerful tool that surpasses current manual and automated analysis methods. The proposed LLM will be trained on the large amounts of relevant data available to DEVCOM AvMC including code, network traffic, static and dynamic analysis results, external software code bases and malicious software examples, and threat intelligence from partner US Government organizations. The LLM will be integrated with AvMC software and hardware integration labs to provide further tuning and address the issue of run-time analysis when software code is unavailable to the cyber resiliency team.
Naval Special Warfare Command CSO
Naval Special Warfare Command (NSWC) seeks to accelerate the development, procurement and integration of unique capabilities into deployable warfighting capabilities in support of the Joint Force and our allied Special Operations Forces (SOF).
Request for Information (RFI) - Strategic Technology Office (STO)
This RFI is to provide a mechanism to inform the office of new capabilities and concepts and the potential performers who will provide them. DARPA will use this information to determine the companies and individuals that STO would invite to have further substantive discussions to inform future projects and programs in appropriately classified settings when necessary.
TurboFCL
The Department of Defense (DOD) aims to increase small business participation within the industrial base and has boosted its involvement in providing goods, services, and research and technology to support national defense. However, significant obstacles persist that dissuade non-traditional vendors from entering the defense ecosystem of contracting and acquisition. Prominent among them is the complex industrial facility security clearance (FCL) process. The FCL process is instrumental in vetting businesses for their capability to handle classified information and bid on classified contracts. However, this process can be daunting for small businesses and non-traditional vendors due to fragmented information, heavy reliance on “government speak”, and the significant time and resources required to complete the process.DARPA’s Bringing classified Innovation to Defense and Government Systems (BRIDGES) has sought to connect innovation from small and nontraditional companies to classified Department of Defense (DoD) research and development (R&D) efforts, specifically by sponsoring innovative companies for facility clearances so that they can directly interact with DoD customers at classified levels. During execution of the BRIDGES program, DARPA observed firsthand the challenges that these small companies faced while going through the FCL process, most notably:• Misunderstanding what information was required on the required forms• Filling out forms incorrectly• Not fully understanding submission timelinesThis resulted in additional workload on DARPA security to answer questions and provide guidance, delays in processing for FCLs, and some FCL packages being rejected by DCSA.To address these challenges, DARPA is looking to develop a software application, leveraging recent advancements in language model technology, that can assist small and nontraditional companies apply for their FCLs, as well as their associated personnel clearances (PCLs). Information on the FCL and PCL processes, while disaggregated, is publicly available. A targeted language model can be trained on the processes, forms, and other related information, and distill this information into more easily understandable wording. Then, just like the popular and commercially available TurboTax software, this model can provide appropriate prompts to users to gather the required information, and then autocomplete the required forms. Additionally, it could provide insights into the deadlines and timelines, and provide a “chat bot” feature to answer questions about the processes.In this SBIR, the proposer will develop a prototype system ready to be tested by representatives from the target audience (small businesses and nontraditional contractors who are not familiar with the FCL and/or PCL processes) during the base effort. If successful, they will then oversee test and evaluation of the prototype by end users, ideally performers on DARPA’s BRIDGES program. During this test and evaluation period, the proposer will verify both the inputs and outputs of the application, collect feedback from users, and incorporate appropriate updates. The end goal will be a system that removes errors from FCL packages, improves processing timelines by removing delays/extension requests, while also improving the user experience and reducing the time and effort required by the end user.
