MODIFICATION
A -- Integrated Command & Control
- Notice Date
- 7/23/2012
- Notice Type
- Modification/Amendment
- NAICS
- 541712
— Research and Development in the Physical, Engineering, and Life Sciences (except Biotechnology)
- Contracting Office
- Department of the Air Force, Air Force Materiel Command, AFRL - Rome Research Site, AFRL/Information Directorate, 26 Electronic Parkway, Rome, New York, 13441-4514
- ZIP Code
- 13441-4514
- Solicitation Number
- BAA-10-01-RIKA
- Point of Contact
- Lynn G. White, Phone: (315) 330-4996
- E-Mail Address
-
Lynn.White@rl.af.mil
(Lynn.White@rl.af.mil)
- Small Business Set-Aside
- N/A
- Description
- The purpose of this modification is to include the following changes: (1) Section I Funding Opportunity Description: Add specific focus areas for FY13. No other changes have been made. (1) Insert the following under Section I: FUNDING OPPORTUNITY DESCRIPTION: Focus Areas for FY13 : The Machine Intelligence for Mission-Focused Autonomy (MIMFA) program will research technologies that enable distributed autonomous assets to make intelligent coordinated adaptations to plans/policies that optimize mission performance in dynamic and realistically complex domains. Emphasis is placed upon autonomous techniques which enable faster, more efficient understanding for complex, multi-modal military data. Our FY13 Focus Areas for MIMFA, with award details, are: Collaborative Agency for Shared Awareness : The objective of this effort is to advance the state of the art related to the tasking, coordination, and negotiation of distributed, heterogeneous agents in complex and/or communication-denied environments. Our domains of interest are high-tempo, data-rich military decision-making situations where the collection, planning, processing, analysis and dissemination of military information leads to decision speed advantage. Target capabilities include the ability to assign software agents to information collection/analysis tasks, share information and conclusions among agents to build team understanding, and self-direct efforts to meet overall mission goals. More specifically, we are interested in answering the following questions: 1. What is the proper way of representing sub-tasks for agents to effectively self-assign to them while ensuring that overall task complexity is properly addressed? 2. What is an effective feedback mechanism to influence autonomy in a positive way? How do agents learn better task selection behavior based on user feedback? 3. What if a user does not agree with a given set of results? 4. What is an effective presentation to a user that will convey a sense of understanding of how an autonomous system is reaching a decision? 5. Can we provide a user with a capability that both increases user effectiveness and increases trust in the autonomous system? White papers for this topic only will be due by: 20 Aug 2012. It is anticipated that awards for this particular topic will range from 9 to 24 months with dollar amounts nominally up to $500,000 per award. Please email your white papers to: staskevg@rl.af.mil. Classification and State Based Reasoning : The objective of this effort is to develop advanced techniques to focus human attention and machine reasoning on the most important aspects of massive, heterogeneous, or partially observed data sources. This is particularly important for high-speed decision-making environments, such as military intelligence, command and control, planning, and operational scenarios. Our goal is to aid human and machine reasoners to1) Identify and reason over the most significant and discriminating features in that data; 2) Recognize trends and correlations, 3) Robustly handle uncertainty and present information to the user intuitively; 4) Account for changes over time; 5) Present diverse perspectives and interpretations of the data, and 6) Derive dynamic abstractions of state and action spaces while learning a solution to an overall problem. The purpose of this research is to improve the robustness of human understanding and enable more intelligent and faster mission-focused decisions; currently made in a "fog of information," under varying degrees of uncertainty and trust, and with unquantified risk. Some of the approaches of significant interest include: multi-agent approaches to data mining, evolutionary and bio-inspired approaches, information theoretic techniques, supervised and unsupervised learning, reinforcement learning, dynamic Bayesian networks, analyzing competing hypothesis from agent perspectives, and the subsequent evaluation of cost functions which are derived from the consideration of multiple approaches for processing the data simultaneously. White papers for this topic only will be due by: 20 Aug 2012. It is anticipated that awards for this particular topic will range from 12 to 36 months with dollar amounts nominally up to $500,000 per award. Please email your white papers to: Misty.Blowers@rl.af.mil. Allother information remains the same.
- Web Link
-
FBO.gov Permalink
(https://www.fbo.gov/spg/USAF/AFMC/AFRLRRS/BAA-10-01-RIKA/listing.html)
- Record
- SN02812388-W 20120725/120724000044-7310eb28f6713505301953440d0791f6 (fbodaily.com)
- Source
-
FedBizOpps Link to This Notice
(may not be valid after Archive Date)
| FSG Index | This Issue's Index | Today's FBO Daily Index Page |