AFRL posts new BAA for Agent Based Systems
On September 19, the U.S. Air Force Research Laboratory posted a broad agency announcement for Agent Based Systems (ABS) (BAA NUMBER: FA8750-17-S-7014). For best consideration for FY18 funding, the agency recommends that white papers be submitted by November 30.
The Air Force Research Laboratory, Information Directorate is seeking innovative research, development, integration, test and evaluation of technologies/techniques to rapidly design, build, and field autonomous systems.
The Department of Defense (DoD) and the Intelligence Community (IC) intend to meet future customer intelligence needs through agent-based systems that are open, model-based, and adaptable to diverse use cases. Focus areas for this BAA include robotic and content production systems that use or produce Geospatial Intelligence (GEOINT), which encompasses all aspects of imagery and geo-positioning. To improve the legacy analytic workflows and capabilities of robotic and content production systems, the DoD & IC stakeholders will require the development of new agent-based techniques and technologies. At the core of this research will be the development of agents and agent-based information frameworks that can quickly integrate new technologies and advanced geospatial sensor data to enable more sophisticated and faster information products and services. The intent is to take advantage of both traditional and non-traditional data sources. Potential solutions must adhere to applicable DoD and IC cybersecurity and information assurance directives while addressing enterprise-wide stakeholder requirements specific to GEOINT accuracy, quality control, timeliness, and safety metrics.
Developing innovative, open, model-based, and adaptable agent-based technologies and services will enable the delivery of cost-efficient and flexible solutions that can have broad positive impacts on the diverse missions of the DoD and IC. This BAA seeks significant advances in agent-based systems to support DoD, IC, and other government agency’s GEOINT-related missions across the following sub-disciplines:
– Open model-based standards
– Model-based and semi-autonomous development and integration tools
– Open dynamic and pragmatic interoperability frameworks
– Open embedded computing systems (hardware and software)
– Open hypergraph-based data stores
– Open advanced geo-temporal query languages
– Open Natural Language processing systems
– Semi-autonomous ontology model construction and management tools
– Advanced modeling of ontological expressiveness and complex relationships
– Semi-autonomous error detection, classification, and correction techniques and systems
– Agent-based Machine Learning and Neural Networks (Convolution Neural Networks, Bayesian Networks, etc.)
– Semi-autonomous complexity management systems
– Computer vision systems (hardware and software)
– Language translation systems
– Model-based cyber-security and information assurance analysis systems
– 3-D printed payloads for robotic systems
Additionally, with the Intelligence Community’s transition to the Intelligence Community Information Technology Enterprise (IC ITE), additional consideration must be given to Assured Cloud Computing. Security risks related to the technologies, software, and systems under development and the eventual deployment environment should be considered. Investigate assured computing architectures and associated technologies that will address the 1) transition and 2) mission shortfalls of the DoD and IC.
The BAA technologies supporting the sub-disciplines above may require the planning and conducting of field tests to demonstrate advancements in specific technology areas. This includes preparing test plans; acquiring, transporting, deploying, and operating all equipment; operating and measuring ground truth sources; evaluating and monitoring test execution; and documenting all test results.
The innovative technologies, applications, and techniques being pursued under this BAA will address significant shortfalls in agent-based systems. Candidate technologies will be evaluated against current requirements for open standards, adaptability, latency, quality, and scalability/affordability. Successful candidate technologies will be nominated for transition where appropriate.
Full information is available here.