AFRL posts new funding opportunity for resilient autonomous systems
On February 19, the Air Force Research Laboratory issued a broad agency announcement for Resilient Autonomous Systems (RAS) (BAA NUMBER: BAA AFRL-RIK-2016-0005). The agency recommends that white papers be submitted by March 30 for best consideration for an award in FY16.
The Information Directorate of the Air Force Research Laboratory (AFRL), Rome Research Site, is seeking innovative research proposals in the area of resilient distributed autonomous systems. The objective of this project is to develop and demonstrate improved resiliency of autonomous assets in a simulated Intelligence Surveillance and Reconnaissance (ISR) mission with degraded communications. Resiliency in the context of this project is defined as a system’s ability to operate at an acceptable level of normalcy despite disturbances. This definition encompasses the system’s agility, adaptive capacity and insufficiency, and robustness. A robust autonomous system can provide increased resiliency with capabilities to assess, recover, learn, and adapt from adverse events, both benign and hostile. These capabilities will allow deployed systems in contested domains, such as Anti-Access Area Denial (A2/AD) environments, to complete mission objectives with minimal impact.
Proposed research should investigate innovative approaches that enable increased resiliency through and ability to learn and adapt over repeated engagements. The following is a non-comprehensive list of technologies that can potentially contribute to the desired solution. It is not expected that a proposed solution will have elements from all the technology areas listed.
– Distributed Planning and Constraint Optimization
– Multi-Agent Coordination
– Distributed Information Management
– Representation and Feature Learning
– Reinforcement Learning
– Transfer Learning
– Case Based Reasoning
– Game Theory and Opponent Modeling
Full information is available here.