Help Desk Outage
The SBA Help Desk is closed and will re-open on Monday, April 20th. All requests submitted to sba.sbir.support@reisystems.com will be responded to on Monday, April 20th in the order received.
Company
Portfolio Data
Back to Company SearchMACHINA COGNITA TECHNOLOGIES, INC.
UEI: MP37XZUHS7C3
Number of Employees: 15
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
SBIR/STTR Involvement
Year of first award: 2020
6
Phase I Awards
5
Phase II Awards
83.33%
Conversion Rate
$1,031,289
Phase I Dollars
$8,237,124
Phase II Dollars
$9,268,413
Total Awarded
Awards
State-based Machine Aided Real Time Strategy (SMARTS)
Amount: $1,999,955 Topic: N201-077
Military operations require fast, decisive, and accurate decision making to accomplish missions with optimal performance and minimization of exposure to risk. Military leaders are forced to make these decisions in high-pressure situations with changing circumstances, incomplete information, very short time frames, and minimal margin for error. Advancements in Artificial Intelligence (AI), specifically Reinforcement Learning (RL) and Deep Learning (DL), are enabling computers to accomplish tasks under similar conditions by recognizing patterns across massive data streams. However, the lack of transparency and explainability of AI systems has made it unfeasible for these decision makers to put lives at risk based on black-box algorithms. In addition, the integration of AI systems into existing military operations presents challenges in how military personnel communicate with autonomous systems. There is a direct need for a system that can understand both the underlying machinations of autonomous systems and the doctrine-based communication patterns of military operations. To solve these shortcomings, the Machina Cognita Technologies (MCT) team is developing the State-based Machine Aided Real Time Strategy (SMARTS) system and the SMARTS Translation Engine. The SMARTS engine provides users with the ability to analyze an array of potential sequences of actions (or decision tracks), the risks associated with each of these actions, and the required capabilities and effectiveness for units to execute the actions. The SMARTS Translation Engine allows autonomous systems and humans to communicate without requiring military personnel to modify existing processes, procedures, and training. In particular, the SMARTS Translation Engine will enable the two-way conversion between military doctrine-based and formatted communication and machine-understandable messages and control. Machina Cognita Technologies (MCT), in partnership with Covan Group and Unitary Labs, proposes to enhance the SMARTS systemÆs of military doctrine and operations. To accomplish this goal, the MCT team will improve the SMARTS systemÆs Natural Language Processing (NLP) pipeline and Semantic Reasoning capability built upon Bidirectional Encoder Representations from Transformer (BERT) models, develop an Unstated Knowledge Model including support for speaker personality/military role models, and generate a Socio-Pragmatic Knowledge Repository based on military operations. Through these components, the SMARTS system will have the added functionality of extrapolating unstated tasks, conditions, and criteria based on human-generated operations and communications, ensuring that the translations are fully described and based upon military doctrine and governing documentation.
Tagged as:
SBIR
Phase II
2024
DOD
NAVY
Spatial-Temporal Agent-based Motion Prediction and Evasion Decision Engine (STAMPEDE)
Amount: $1,249,886 Topic: AF221-0013
The Personnel Recovery (PR) mission is vital to effectively plan and conduct military operations in overseas theaters. The military effort to prepare for and successfully execute the recovery of isolated personnel (IPs) is essential to maintaining force readiness, denying enemy critical intelligence, and protecting the lives of U.S. service members. The USAF is often a leader among services in integrating new PR resources and adopting new innovative technologies. Cutting-edge developments in Machine Learning (ML) and Artificial Intelligence (AI) have created an opportunity to advance current PR planning resources and operational PR support products. Deep Learning (DL) approaches are highly effective at identifying temporal and spatial patterns in geospatial data. Reinforcement Learning (RL) can discover successful behaviors and decisions in realistic military simulations. If harnessed effectively, AI and ML technologies can equip PR planners, coordinators, and IPs with a significant technological advantage over their adversaries. However, new technologies are often tough to deploy at scale. Broad-based adoption is difficult across large military and government organizations. Human behavior is challenging to model. To meet these challenges, Machina Cognita Technologies (MCT) proposes the Spatial-Temporal Agent-based Motion Prediction and Evasion Decision Engine (STAMPEDE). STAMPEDE will be designed to provide users at each level of the joint PR C2 architecture with guidance through an enhanced suite of DL-powered planning and coordination aids. The STAMPEDE system will ingest a wide array of data sources that characterize PR scenarios. STAMPEDE will be compatible with LandSAR mobility model plugin data and incorporate new dynamic data sources. STAMPEDE will return IP location probability maps at sequenced time intervals back to decision support tools. Accompanied by easily interpreted explanations, recommended evasion decisions that avoid capture will be output directly to PR planners and coordinators. STAMPEDE will enable PR planners and coordinators to identify exclusion zones that reduce SAR search areas and drive more efficient searches through spatial-temporal human motion pattern discovery. STAMPEDE’s IP evasion movement recommendations will guide AOR evasion plans of action (EPAs) and theater wide PR guidance using ML-powered prediction and recommendation tools. STAMPEDE will generate customized evasion planning and decision guidance tailored to specific threat scenarios, real-world geographically bounded locations, and individual IP mobility behaviors and circumstances. STAMPEDE’s evasion decision explanations will instill PR user trust in and drive greater PR user adoption of the system using intuitive ML explainability models. STAMPEDE will empower PR users to reduce operational costs and increase the likelihood of successful evasion, survival and recovery through ML model location predictions and evasion decisions recommendations.
Tagged as:
SBIR
Phase II
2024
DOD
USAF
Statistical Characterization and Operation Readiness assessment of ELINT/SIGINT Deep learning (SCORED)
Amount: $1,237,464 Topic: AF221-0022
The application of advances in Machine Learning and in particular Deep Learning (DL) to complex RF applications provides a great opportunity to advance DoD system capabilities. However, the black box nature of DL models requires additional advances in Exp
Tagged as:
SBIR
Phase II
2023
DOD
USAF
Autonomous Vehicle Audio Translation for Airfield Readiness (AVATAR)
Amount: $139,969 Topic: N231-025
Machina Cognita Technologies (MCT) proposes the Autonomous Vehicle Audio Translation for Airfield Readiness (AVATAR) system for facilitating communications between airfield control authorities and Foreign Object Debris (FOD) removal vehicles. The system will provide a full conversational loop consisting of human-to-machine statement translation and a corresponding machine-to-human message- generation system. AVATAR will monitor continuous airfield radio signals and identify discrete speech segments despite challenges typical of airfield communications, including overlapping speakers, a variety of accents, and background noise. We will parse, classify, and filter the statements, relaying only those containing Air Traffic Control (ATC) instructions and questions for the relevant FOD-removal vehicles. When responding to ATC or negotiating permission for airfield navigation, the FOD-removal vehicle will have the ability to speak through AVATAR’s statement-generation module. Machine-generated messages will follow all airfield rules and regulations. Statements will be optimized for succinctness and directness to ensure a safe operating environment. The streamlined system will allow ATC to communicate with FOD-removal vehicles without unnecessary delay. In contrast to popular dialogue systems, AVATAR will maintain informational accuracy across conversations. The system will create a repository of situational information, including representations of ongoing movements of other airfield entities, histories of previous ATC statements, and details from daily operations plans. Relevant context from the repository will bolster the human-machine communication loop so that every ATC statement is understood accurately and every FOD-generated message is unambiguous. The system will incorporate geographic coordinates to provide spatial context for each translated statement and assist the FOD robot in averting potential collisions and airfield hazards. Each component of AVATAR will support an open interface with system users to promote compatibility. The system will provide processed data in any format necessary to ensure efficient communication. AVATAR-enabled FOD removal will increase airfield readiness and provide a much safer environment for naval aviation operations.
Tagged as:
SBIR
Phase I
2023
DOD
NAVY
Multi-modal Evidential Deduction for Upgraded Situational Awareness (MEDUSA)
Amount: $1,749,912 Topic: N211-079
In military operations, it is vital that commanders have a high-level of situational awareness to manage risk and make effective decisions. Historically, the limitation of situational awareness has been the availability of data. However, in today's data-saturated battlefield, the challenge has shifted to efficiently harnessing the torrent of source data to construct an accurate picture of the battlespace. For a typical Maritime Operations Center (MOC), the Common Operational Picture (COP) is the visual representation of the collective situational awareness. As the Navy develops the Maritime Tactical Command and Control (MTC2) system, the NavyÆs next generation command and control platform, it is paramount that the underlying data management and analytics can effectively leverage the deluge of multi-modal geospatial and non-geospatial data. To meet these challenges, the Machina Cognita Technologies (MCT) team (MCT, University at Buffalo, and Voyager Search) proposes to develop the Multi-modal Evidential Deduction for Upgraded Situational Awareness (MEDUSA) engine. The system will streamline the data management pipeline, leverage Machine Learning (ML) algorithms to drive accurate and targeted analytics, and create and integrate enhanced data layers and geospatial visualizations. Overall, the MEDUSA system will lead to increased situational awareness and enhanced geospatial analytics to accelerate and support kill chain requirements. The MEDUSA system will be designed to be an end-to-end data enhancement and visualization system supporting analysis for kill chain requirements. It will ingest multi-model COP source data, generate enhanced predictive data layers, and output real-time geographic visualizations to aid in threat analysis and environmental assessment. The efficiencies gained from a streamlined prediction analysis will lead to a clear and rapidly understandable operational picture providing increased situational awareness. MEDUSA will be composed of four primary components: a data correlation and entity disambiguation engine, semantic state space and entity embedding models, geospatial analytics algorithms, and an enhanced visualization tool. MEDUSA will expand and expedite the available data behind each entity displayed on the COP through an entity disambiguation step. By providing a single correlated view of the known information pertaining to each entity, MEDUSA will be able to help expedite the kill chain process. MEDUSA will then utilize semantic embedding space algorithms to encapsulate both the world state information as well as entity state information to enable analysis of the entire situation by deep learning-powered geospatial analytics algorithms. Next, MEDUSA will provide a collection of geospatial analytics algorithms to empower visualizations providing commanders with rapid, enhanced situational awareness. Finally, the MEDUSA system will provide semantically filterable and mission-specific data layers and visualizations.
Tagged as:
SBIR
Phase II
2023
DOD
NAVY
Statistical Characterization and Operation Readiness assessment of ELINT/SIGINT Deep learning (SCORED)
Amount: $149,990 Topic: AF221-0022
The application of advances in Machine Learning and in particular Deep Learning (DL) to complex RF applications provides a great opportunity to advance DoD system capabilities. However, the black box nature of DL models requires additional advances in Explainable AI (XAI) to ensure that the output of the black box DL models can be justified and understood by warfighters. In particular, the application of XAI along with automated Test and Evaluation (T&E) is needed to validate both performance and reliability of DoD RF systems, particularly SIGINT and ELINT collection sensors. While recent investments including DARPA’s Radio Frequency Machine Learning Software (RFMLS) and the Air Force ISR Modernization and Automation Development (IMAD) program increase the utility of fielded systems, the transition target Programs of Record require a stringent and rigorous level of validation and reliability prior to fielding a system. These lengthy validation and verification activities require even more rigorous testing to ensure the automated functions are operating as intended, with no adverse consequences. Thus, new XAI methods for DoD-specific applications are required that statistically: (1) quantify performance in an operationally relevant environment: and (2) quantify reliability (and thus availability). However, the historically extensive and expensive field testing associated with gathering all of the relevant statistics is unsustainable. To overcome these issues and provide the required statistical analysis of Radio Frequency (RF) systems, the Machina Cognita Technologies (MCT) and Epsilon team propose to develop the Statistical Characterization and Operation Readiness assessment of ELINT/SIGINT Deep learning (SCORED) system. The SCORED system will provide a Modular, Open Systems Approach (MOSA) to T&E of RF systems. SCORED will be a combination of the Test Automation Framework (TAF), an automated testing and scenario execution framework, and an AI/DL powered RF analysis and recommendation engine. The system will be able to statistically quantify performance across a range of operational conditions and quantify the reliability of the RF System Under Test (SUT). The output of the SCORED system will be a clear, concise explanation of the capabilities of the SUT including both text-based summarizations and visual representations of the statistical analysis. Users will then be able to further drill into these summarizations to explore the underlying statistical and raw data generated by the SCORED system during the T&E process.
Tagged as:
SBIR
Phase I
2022
DOD
USAF
State-based Machine Aided Real Time Strategy (SMARTS)
Amount: $1,999,907 Topic: N201-077
Military operations require fast, decisive, and accurate decision making to accomplish missions with optimal performance and minimization of exposure to risk.Ā Military leaders are forced to make these decisions under constant pressure, changing circumstances, incomplete information, and very short time frames with minimal margin for error.Ā Advancements in Artificial Intelligence (AI) and, specifically, Deep Learning (DL) are helping train computers to accomplish tasks under these same conditions by recognizing patterns across massive data streams.Ā Research in competitive gaming, especially Real-Time Strategy (RTS) games, have shared an interesting symbiosis with the advancement of AI approaches to complex decision-making and hierarchical planning. RTS games are characterized by their imperfect information, large state and action spaces, and necessary balancing of high and low-level planning. The conceptual underpinnings of these game dynamics are highly relevant to problems that are familiar to the military intelligence community, such as knowing how to parameterize plans and when to execute them. Partial observability of environments compounds these difficulties by adding a degree of uncertainty to the mix.Ā However, a question that remains to be answered is how well recent accomplishments in gaming agents, can improve real-world decision-making aids that require situational awareness over high-dimensional observations. ĀDL approaches are making it possible for machines to learn from experiences, adapt to new data, and provide recommendations on optimal behavior. Insights from these models can be communicated to users and analytics providing an intelligence and command advantage. However, the lack of transparency and explainability have made it impossible for these decision makers to put lives at risk based on a black box opinion on the best path forward.Ā In addition, current AI and DL solutions focus on individual decisions based on the current situation with minimal concern for longer term strategic impacts.Ā To solve these two shortcomings, the Machina Cognita Technologies team proposes to develop the State-based Machine Aided Real Time Strategy (SMARTS) engine.Ā The SMARTS engine will provide the ability to analyze an array of potential sequences of actions (or decision tracks), the risks associated with each of these actions, and the required capabilities and effectiveness for units to execute the actions.Ā In addition, the SMARTS engine will provide clear explanations as to the reasoning behind the recommended actions, the impact on mission effectivities, and the possible outcomes for the recommended actions and alternative paths.Ā Specifically, we seek to create a machine learning framework for distilling mission plans into interpretable strategic and tactical decision tracks using a combination of behavioral cloning, unsupervised learning, and attention networks.
Tagged as:
SBIR
Phase II
2022
DOD
NAVY
Spatial Temporal Agent-based Motion Prediction and Evasion Decision Engine (STAMPEDE)
Amount: $149,984 Topic: AF221-0013
The Personnel Recovery (PR) mission is vital to effectively plan and conduct military operations in overseas theaters. The military effort to prepare for and successfully execute the recovery of isolated personnel (IPs) is essential to maintaining force readiness, denying enemy critical intelligence, and protecting the lives of U.S. service members. The USAF is often a leader among services in integrating new PR resources and adopting new innovative technologies. Cutting-edge developments in Machine Learning (ML) and Artificial Intelligence (AI) have created an opportunity to advance current PR planning resources and operational PR support products. Deep Learning (DL) approaches are highly effective at identifying temporal and spatial patterns in geospatial data. Reinforcement Learning (RL) can discover successful behaviors and decisions in realistic military simulations. If harnessed effectively, AI and ML technologies can equip PR planners, coordinators, and IPs with a significant technological advantage over their adversaries. However, new technologies are often tough to deploy at scale. Broad-based adoption is difficult across large military and government organizations. Human behavior is challenging to model. To meet these challenges, Machina Cognita Technologies (MCT) proposes the Spatial-Temporal Agent-based Motion Prediction and Evasion Decision Engine (STAMPEDE). STAMPEDE will be designed to provide users at each level of the joint PR C2 architecture with guidance through an enhanced suite of DL-powered planning and coordination aids. The STAMPEDE system will ingest a wide array of data sources that characterize PR scenarios. STAMPEDE will be compatible with LandSAR mobility model plugin data and incorporate new dynamic data sources. STAMPEDE will return IP location probability maps at sequenced time intervals back to decision support tools. Accompanied by easily interpreted explanations, recommended evasion decisions that avoid capture will be output directly to PR planners and coordinators. STAMPEDE will enable PR planners and coordinators to identify exclusion zones that reduce SAR search areas and drive more efficient searches through spatial-temporal human motion pattern discovery. STAMPEDE’s IP evasion movement recommendations will guide AOR evasion plans of action (EPAs) and theater wide PR guidance using ML-powered prediction and recommendation tools. STAMPEDE will generate customized evasion planning and decision guidance tailored to specific threat scenarios, real-world geographically bounded locations, and individual IP mobility behaviors and circumstances. STAMPEDE’s evasion decision explanations will instill PR user trust in and drive greater PR user adoption of the system using intuitive ML explainability models. STAMPEDE will empower PR users to reduce operational costs and increase the likelihood of successful evasion, survival and recovery through ML model location predictions and evasion decisions recommendations.
Tagged as:
SBIR
Phase I
2022
DOD
USAF
Multi-modal Evidential Deduction for Upgraded Situational Awareness (MEDUSA)
Amount: $239,943 Topic: N211-079
In military operations, it is vital that commanders have a high-level of situational awareness to manage risk and make effective decisions. Historically, the limitation of situational awareness has been the availability of data. However, in today's data-saturated battlefield, the challenge has shifted to efficiently harnessing the torrent of source data to construct an accurate picture of the battlespace. For a typical Maritime Operations Center (MOC), the Common Operational Picture (COP) is the visual representation of the collective situational awareness. As the Navy develops the Maritime Tactical Command and Control (MTC2) system, the Navy’s next generation command and control platform, it is paramount that the underlying data management and analytics can effectively leverage the deluge of multi-modal geospatial and non-geospatial data. To meet these challenges, the Machina Cognita Technologies (MCT) team (MCT, University at Buffalo, and Voyager Search) proposes to develop the Multi-modal Evidential Deduction for Upgraded Situational Awareness (MEDUSA) engine. The system will streamline the data management pipeline, leverage Machine Learning (ML) algorithms to drive accurate and targeted analytics, and create and integrate enhanced data layers and geospatial visualizations. Overall, the MEDUSA system will lead to increased situational awareness and enhanced geospatial analytics to accelerate and support kill chain requirements. The MEDUSA system will be designed to be an end-to-end data enhancement and visualization system supporting analysis for kill chain requirements. It will ingest multi-model COP source data, generate enhanced predictive data layers, and output real-time geographic visualizations to aid in threat analysis and environmental assessment. The efficiencies gained from a streamlined prediction analysis will lead to a clear and rapidly understandable operational picture providing increased situational awareness. MEDUSA will be composed of four primary components: a data correlation and entity disambiguation engine, semantic state space and entity embedding models, geospatial analytics algorithms, and an enhanced visualization tool. MEDUSA will expand and expedite the available data behind each entity displayed on the COP through an entity disambiguation step. By providing a single correlated view of the known information pertaining to each entity, MEDUSA will be able to help expedite the kill chain process. MEDUSA will then utilize semantic embedding space algorithms to encapsulate both the world state information as well as entity state information to enable analysis of the entire situation by deep learning-powered geospatial analytics algorithms. Next, MEDUSA will provide a collection of geospatial analytics algorithms to empower visualizations providing commanders with rapid, enhanced situational awareness. Finally, the MEDUSA system will provide semantically filterable and mission-specific data layers and visualizations.
Tagged as:
SBIR
Phase I
2021
DOD
NAVY
Testing Routines using AI for Communication Evaluation and Recommendations (TRACER)
Amount: $111,451 Topic: A20-033
Communication networks provide Command and Control with the necessary information and connections to their soldiers in the field required to execute their missions. Ensuring these networks are available and optimized for the mission at hand is crucial to mission success. However, the monitoring, testing, and design of these networks is a tedious, manual, and costly effort when performed but can be catastrophic if neglected. Advancements in the areas of Artificial Intelligence (AI) and Deep Learning (DL) offer an opportunity to apply these capabilities to network analysis including traffic engineering, dynamic path planning, and topology optimization. Therefore, the Machina Cognita Technologies (MCT) and Epsilon team propose to lower the overall burden and cost of network analysis while also improving the accuracy of the analytics, optimization of the network design, and minimization of the impact of localized network outages and component failures. To accomplish these goals, we propose to develop the AI and DL powered Testing Routines using AI for Communication Evaluation and Recommendations (TRACER) system. The TRACER system will provide a Modular, Open Systems Approach (MOSA) to Test and Evaluation (T&E) of Command, Control, Communications, and Intelligence (C3I) systems. The system will be a combination of the Test Automation Framework (TAF), an automated testing and scenario execution framework, and an AI/DL powered network analysis and recommendation engine. The system will be able to provide descriptions of how the network is performing under test, forecasts of how the network will behave under various scenarios, and recommendations on how to improve the network to meet specific goals. The TRACER system will be composed of three major components and will connect to the network of interest (or System Under Test (SUT)) and provide results in an intuitive, easy-to-use interface. The three major components are the TAF, the Analysis Engine, and the Recommendation Engine. TAF will enable the automated testing and evaluation of the network through data injection, scenario management, simulation, and metric/data collection. TAF will send the results of the automated testing along with the network metrics and topology to the Analysis Engine. The Analysis Engine will utilize DL technologies to understand the performance of the network with regard to temporal fluctuations and the impact of the network topology and equipment on performance. These results will then be passed to the Recommendation Engine that will generate specific, actionable, and understandable recommendations for modifications to the network along with expected impacts on performance.
Tagged as:
SBIR
Phase I
2020
DOD
ARMY