Loren Data's FBO Daily™

Home Today's FBO Search Archives Numbered Notes CBD Archives Subscribe

A -- Reasoning, Comprehension, Perception and Anticipation in Multi-Domain Environments

Notice Date
Notice Type
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
Solicitation Number
Point of Contact
Lynn G. White, Phone: (315) 330-4996
E-Mail Address
Small Business Set-Aside
The purpose of this modification is to republish the original announcement, incorporating all previous modifications, pursuant to FAR 35.016(c). This republishing also includes the following changes: (a) Section III.3 and III.4, Eligibility Information: Added information concerning CCR and Executive Compensation and First-Tier Sub-contract/Sub-recipient Awards; (b) Section IV.3, Submission Dates and Times: Added sentence to indicate the closing date of the BAA; (c) Section VI.3, Award Administration Information : Added more detailed reporting instructions; and (d) Section VII, Agency Contacts: Updated clause date and telephone number of the AFRL Ombudsman. No other changes have been made. NAICS CODE: 541712 FEDERAL AGENCY NAME: Department of the Air Force, Air Force Materiel Command, AFRL - Rome Research Site, AFRL/Information Directorate, 26 Electronic Parkway, Rome, NY, 13441-4514 TITLE: Reasoning, Comprehension, Perception and Anticipation in Multi-Domain Environments ANNOUNCEMENT TYPE: Initial announcement FUNDING OPPORTUNITY NUMBER: BAA 10-03 - RIKA CFDA Number: 12.800 I. FUNDING OPPORTUNITY DESCRIPTION: The Air Force Research Laboratory's Information Fusion and Understanding (IFU) Core Technical Competency (CTC) is defined as the continuous process that provides world-wide situational awareness in order to enable decision superiority. The focus area of this BAA is to research, develop, demonstrate, integrate and test innovative technologies in support of the IFU CTC which enable continuous assessment of global conditions and events; establish and maintain battle space situational awareness (including an understanding of adversarial capabilities and intent); and that locate, identify, and track red, blue, and gray forces anywhere, anytime in near real-time. This BAA is comprised of the following focus areas of which an offeror may respond to one or more areas: 1.0 REASONING AND LEARNING Most automated reasoning and learning techniques rely heavily on well-defined models of the domain of interest. Development of these models is often a manual process requiring input from both experts and knowledge engineers to ensure the model is both expressive and functional. We seek new methods for building and extending models from data and providing a mapping of new information to existing models. 1.1 Targeted Perception With the large amount of data available from a wide range of sources it is infeasible to map all collected information to concepts that have been modeled in a structured format. Because domain models often contain concepts that are fixed, new information must be mapped to these concepts to be used for reasoning. Additionally, there may be constraints on resources, such as limited collection windows or storage limits that require targeted collection of information that would best support the goals of the reasoning process. The intent is to support collection, refinement, storage and presentation of information in a form that supports reasoning over a model of a domain. Challenges include but are not limited to: • Extracting and retrieving information that is relevant to provided models. • Mapping extracted concepts to existing knowledge structures. Tracking the state of concepts over time. • Generalizing concepts, relations and instances. • Satisficing of information collection under dynamic constraints We seek new algorithms for information extraction, mapping and generalization driven by the models provided to the system. 1.2 Model Elicitation Domain models are often developed by an expert or community of interest but will not necessarily be sufficient for all tasks in that domain. It's likely that information will exist that can not be mapped to defined concepts. Additionally, the domain itself may change over time and require constant updates. Small changes to a model can often have serious impact on the reasoning process. Models can not be exhaustive and, as a result, they could potentially lack the necessary information to be sufficiently expressive. Challenges include but are not limited to: • Creating and evolving models from iterative inputs. • Validating and verifying models based on expert review, user input, and data confirmation. • Representing uncertainty. A distinction should be made between uncertainty about the correctness of the values, and uncertainty regarding the correctness of the model itself. • Detecting and negotiating inconsistencies, to allow for differing values within the same model and allowing for intentional inconsistency. • Ensuring changes to a model do not invalidate past assertions. • Providing clear and concise explanations of the effects of changes to the structure of the model. We seek algorithms for mixed-initiative development, manipulation, and maintenance of computational models to support reasoning. These technologies will aid in the discovery of the structure and parameters of new or incomplete models. In addition to providing support for uncertainty and inconsistency, solutions should include support for describing rationale, provenance, and trust. 2.0 COMPREHENSION Comprehension technologies seek to develop capabilities for quantitative evaluation of events that enhance a decision maker's ability to judge, appraise, and determine the relevance of emerging situations. 2.1 Link and Group Discovery (LGD) This area is focused on techniques for analyzing large collections of data to discover valuable knowledge that may be present as hidden patterns or links among seemingly unrelated items. LGD will discover the hidden structure of organizations, relate groups, identify fraudulent behavior, model group activity, connect bits of information into patterns that can be evaluated and analyzed, learn what patterns discriminate between legitimate and suspicious behavior, and provide early detection of emerging threats. Specific areas of interest include, but are not limited to the following areas: 2.1.1 Dynamic Networks Over Time Most networks of entities and relationships change over time. Computers connect and disconnect from the internet. Web pages and hyperlinks appear and disappear from the worldwide web. People enter and leave social networks. Leaders emerge and then disappear. Many approaches have been developed to detect patterns in static snapshots of these networks, but discovering patterns in the dynamics of these networks can provide new understanding of how they evolve and new ways to categorize networks based on their dynamics. There is growing evidence that networks influence both individual and collective group activity. Networks play a key role in determining how information is disseminated and how organizations evolve (e.g., how new members are recruited and how they leave). Additionally, these networks have a significant impact on the choices an individual makes. These observations apply not only to social, but also to geospatial, information and technological networks. Despite growing interest in social network analysis (SNA) and related fields, an understanding of how these networks influence individuals and groups is still very limited. The objective of this technology area is to research and develop: - Methods for combining the effects of multiple, heterogeneous networks within a single model as well as mathematical methods and formalisms for modeling dynamic networks and their influence on the individual and group dynamics. - Methods for combining different sources of evidence, how to include spatio-temporal data, and how the community structure changes over time. - Enhanced techniques for social network modeling beyond static models. Develop techniques capable of handling dynamic models that account for relationships that drift over time and tractable to learn such models from data, even as the number of entities gets large. - Metrics to assess and identify change within and across networks. - Techniques to determine whether differences observed over time in networks are due simply to different samples from a distribution of links and nodes or due to changes over time in the underlying distribution of links and nodes. The end goal is to understand the entire problem space well enough to predict/forecast change in existing networks. Managing the pedigree of the information must be addressed in order to accurately combine information from multiple sources. 2.1.2 Abnormality Detection in Counter Terrorism Evidence Anomaly detection looks for entities whose characteristics, behaviors or connections to other individuals are in some way abnormal. Particular patterns of abnormality are not typically available, and therefore must be derived from data which is normal, by identifying deviations from "normal" patterns. Often it is the combination of several seemingly normal things that is abnormal. Much of today's evidence consists of networks of entities and their interrelationships. However, most approaches for detecting abnormalities in this evidence consider only the attributes of the entities, or focus on the presence or absence of specific relationships, without considering the context of the abnormality. For example, in the case of fraud, the perpetrator attempts to mimic normal behavior in order to avoid detection. That is, abnormality only makes sense in the context of what is normal. In the case of networks, normal behavior can be represented by recurring normative patterns in the structure of the network, and abnormalities can be defined as unexpected deviations to these normative patterns, not just unexpected deviations within the network as a whole. In addition to methods for detecting outlier attributes and relationships, we also need methods for detecting anomalies to the prevalent, normal behavior reflected in the transactions among entities in the domain of interest. Such methods will provide several benefits, including the description of abnormalities within the context of the normal behavior they defy and the ability to detect these abnormalities without prior training in possible abnormalities; thus, providing the ability to detect previously unforeseen abnormalities. Combining these methods with the above methods on detecting patterns in dynamic networks will provide the ability to detect anomalies in both the structure and the dynamics of networks. Single anomalies are often the result of noise, data mistakes, or other one-time-only phenomena and do not have significant practical interest. Identifying a collection of records that are each anomalous, but have some pattern of self-similarity, may make them indicative of a larger event. For example, a single strange case in the hospital emergency department is probably nothing more than that, but several of these across a city are indicative of a disease outbreak, or potential malicious activity. Research and development is needed to extend traditional anomaly detection methods to link data to discover linked groups of anomalous records along with efficient methods to scale this up to millions of links. This will enable discovery of linked groups of individuals engaged in anomalous activity, even if none are previously known to be dangerous, or the method of attack they are pursuing is novel. Many times there are simply too many unique or rare events to make it useful to identify them all (not to mention having to determine how rare an event needs to be before it is reported). Sherlock Holmes stories typically see the detective observe a multitude of things that seem perfectly ordinary until he puts their significance together to solve the crime. Research and develop techniques to recognize situations of potential interest, and to tell a story that explains why the situations are of potential interest, without those situations having been predefined in detail. Develop models of relevancy. An abnormality that can be explained away through a simple non-threatening story should not be reported. Conversely, an abnormality that cannot be explained with a non-threatening story, or supports a threatening or opportunistic story should be reported. Develop capability to recognize situations of potential interest and explain why the situations are of interest, without those situations having been predefined in detail. 2.1.3 Layered Multi-Modal Network Analysis The intent is to seek new and innovative ideas for experimental and theoretical development of technologies to fill Department of Defense (DoD) requirements for the development of a layered multi-modal network analysis (LMMNA) approach. Understanding the structure and dynamics of networks are of vital importance to winning the global war on terror. Current analysis of network data occurs primarily within one or two particular domains (e.g. derived from communications intelligence (COMINT) or human intelligence (HUMINT)). However, to fully understand the network environment, analysts must be able to investigate interconnected relationships of many diverse network types simultaneously as they evolve spatially and temporally. No single network exists in a vacuum as networks are interconnected through space and time. The emphasis of this focus area is to research and develop a layered multi-modal networking approach that the user can interrogate and shape for their mission. A layered multi-modal network analysis (LMMNA) approach will be able to assemble previously disconnected networks (e.g. information derived from COMINT, open source intelligence (OSINT), imagery intelligence (IMINT), etc.) in a common battle space picture providing the user with timely situation awareness, understanding and anticipation of threats, and support for effective decision-making in diverse environments. Combining numerous networks will require various data transformation techniques such as standardization, normalization, as well as entity resolution. Emphasis will be on the development of an approach to apply network analysis methods (e.g. eigenvector centrality, group detection) and visualization technology to the collective network. This will allow an analyst to have all network data in a layered network application where they can correlate and analyze activity and time occurrence in related networks to understand and potentially predict when a major event of interest is about to happen and where to expect it. The software developed is envisioned to be at the Technology Readiness Level (TRL) 6, system/subsystem model or prototype demonstration and validation in a relevant environment. This work must be completed on site at AFRL/RI. The recommended date for submittal of FY 11 white papers for the topic area above, 2.1.3, is until 8 October 2010. 2.2 Situation Analysis (SA). The objective of the SA area is to research and develop capabilities for comprehensive, integrated and continuous awareness of activities, systems and the environment across Air, Space and Cyber domains. This includes developing software tools that provide computational techniques to support the analysis of identities, behaviors, intentions, capability, capacity, kinematics, activity level, and saliences. 2.2.1 Space Situation Awareness. Space Situation Awareness includes perception, comprehension and anticipation of threats against blue (including coalition) space assets (satellites and their ground stations). Space threats encompass non-kinetic and kinetic attacks. Examples of non-kinetic threats include laser dazzling, RF jamming and cyber attacks against satellites and/or their command & control ground stations. Examples of kinetic threats include Direct Assent Anti-Satellite Ballistic Missile (DA-ASAT) and Co-Orbital ASAT kinetic kill vehicles (KKV) in Low Earth Orbits (LEO), Medium Earth Orbits (MEO) and Geostationary Orbits (GEO). Space threats may be executed by multiple adversaries through simultaneous, coordinated attacks against multiple ground stations and satellites in the constellation (eg, a DA-ASAT attack against Satellite X by country A teamed with country B who is concurrently attacking Satellite Y by laser dazzling & RF jamming). The objective of this technology area is to research and develop: - Dynamic automated adversary modeling and alerting techniques which are needed to provide watch agencies', analysts and operators with enough advanced warning of coordinated attacks against multiple DoD (Department of Defense), National and commercial space assets in sufficient time for successful Defensive Counterspace (DCS) actions. - Automated learning and reasoning approaches mentioned in 1.0 can be applied to the space domain. Automated space asset attack assessment indicates the probability and type of space asset attack, which coalition (air, ground, maritime, cyber) assets are vulnerable, the vulnerability period, and the confidence levels associated with the assessment. The impact of an attack needs to be understood as well as the effect asset degradation/failure has on coalition (air, ground, maritime, and cyber) operations so as to ensure unhindered integrated Command and Control (C2) of coalition forces. Space Tracking and Object Characterization is an area of research to include, but not limited to, novel algorithms for automatic tracking of satellites to minimize the number of uncorrelated tracks on space objects, and decipher between debris and satellites. - Novel techniques are needed in multi-source data (radar, optical and other) exploitation, analysis and fusion capabilities for timely, accurate and complete characterization of space objects, physical and functional analysis, events and situation assessment, threat determination and appropriate course of action development. - High fidelity tools to fit into RI simulation environment are needed for satellite modeling, assessment of satellite vulnerabilities related to particular threats, automated classification of unknown or wrongly labeled space objects and corresponding probable mission. Research and development methods include physics based modeling and analysis of photometric and multispectral satellite signatures, improved detection, tracking, enhanced orbital cataloging, and characterization of satellite threats. 2.2.2 Assessment of Adversary Capability and Capacity The intent is to seek new and innovative ideas for experimental and theoretical development of technologies to fill DOD requirements for development of a decision support system (DSS) that gathers/fuses data from various intelligence sources to streamline the assessment of a potential adversary's Capability & Capacity. This includes advanced technology development software tools that provide computational techniques to support the analysis of capability and capacity, and machine learning approaches to capability/capacity model development. The software developed is envisioned to be at the Technology Readiness Level (TRL) 5, system/subsystem/component validation in a relevant environment. The recommended date for submittal of FY 11 white papers for the topic area above, 2.2.2, is until 02 July 2010. 3.0 ANTICIPATION The intent of this area is to develop technologies which provide a detailed understanding of probable intent and future strategy in order to identify the set of potential courses of action (COAs) that both our adversaries and other entities' commanders have to consider while taking actions. Determine their most likely COAs, their COAs which have the greatest detrimental impact, and their most likely reactions to our COAs. The vision is to provide the Decision Maker (DM) and their staff greater awareness into the range of alternate futures (state & non-state actors); and to assist them in exploring the realm of the plausible in order to support: greater understanding of current conditions and possible outcomes (impact and plausibility); more robust/targeted courses of actions; better insight into potential ramifications of planned blue actions; greater variance in training scenarios for blue forces, minimizing surprise, while bounding the realm of the possible (better preparing our forces); better utilization of limited ISR resources; and an increased insight into what the adversary can/is doing against various blue assets/missions (to support fight through). This area cuts across and supports all Air Force domains (Air, Space, & Cyber). 3.1 Understanding the Operational Environment (Nation-state) The intent is to provide a Strategic Analysis/Assessment Tool that provides insight into the complex state space that is today's modern operational environment. In other words, given the current state of affairs within a specific region (or nation-state), what are the short, mid and long-term forecasts of its security, social, physical, and government support mechanisms and (stability) behavior. Technology challenges include the ability to completely model complex regional and national environmental states (to include all factors and their inter-relationships) and to support the Blue Commander's ability to interact/investigate multiple options of achieving his "objectives." This is not to develop the blue COA but to support its development. The development is a Command and Control (C2) responsibility; large-scale multi-dimensional heuristics capable of identifying decision/leverage points; visualization methods that allow understanding of highly complex and multi-dimensional models; multi-constraint objective analysis; social-cultural modeling; behavioral modeling; integrated analysis tools that support rapid modeling and simulation of plausible futures based on continuous assessment of behavioral and environmental conditions; and methods to integrate discrete near and far term forecasting capabilities into a single service architecture application with near-real time analysis capability. 3.2 Understanding Adversary Behavior The intent is to develop an operational/tactical analysis and assessment tool that forecasts potential adversaries' actions and events based on indications of known evidence and projected known and/or anticipated threat(s). Technology challenges include: the integration of broad-spectrum adversarial modeling (individual to societal behaviors, infrastructure, and cyber); advancement of predictive sciences (constructive simulation, analytical methods); analysis of implications of the adversary's actions (based on capability, intent and opportunity) to identify potential threat(s); capabilities to project adversary courses of action; and ability to rank order potential actions as part of an adversary's COA as well as support to collection requirements. 3.3 Determine Adversary Opportunities The intent is to seek new and innovative ideas for experimental and theoretical development of technologies to fill DOD requirements for determining adversary opportunities. The focus is on applied research and advanced technology development objectives for understanding adversarial opportunities to fit within the existing Situation Identification and Threat Assessment (SITA) framework. Given opportunities exists based on "our" vulnerabilities, this research focuses on the development of algorithms that will automatically identify the opportunities that an adversary might have in accomplishing their intent or goals. Focus should initially be on the cyber domain, but should be extensible to additional domains (cross domain) such as air, and space. 3.4 Identify Adversary Intent The intent is to seek new and innovative ideas for experimental and theoretical development of technologies to fill DOD requirements to identify adversary intent. The focus is on applied research and advanced technology development objectives for identification of adversary intent to fit within the existing Situation Identification and Threat Assessment (SITA) framework. Current research will apply innovative techniques that will identify adversarial intent or goals. Focus should initially be on the cyber domain, but should be extensible to additional domains (cross domain) such as air, and space. The recommended date for submittal of FY 11 white papers for the two topic areas above, 3.3 and 3.4, is 17 June 2010. 4.0: PERCEPTION The intent of this area is to develop technologies which fuse multiple intelligence sources to provide awareness of all elements of the current battle space situation, including single entities, groups, and activities. Accurate perception of the battle space is a key enabler for both comprehension of the current situation and anticipation of future enemy actions, thus enabling a commander to make better decisions. A major focus of the area is the ability to locate, identify, track and observe/monitor friendly, enemy, non-friendly, and non-aligned forces/actors anywhere/anytime in near real-time. Another concentration is on the development of forensic capabilities to analyze historical multi-INT data to enable more accurate perception of the current situation. This includes automated motion and behavioral pattern analysis, correlation of multi-INT data with social networks, and utilization of forensic data for sensor cueing. A final focus is on text extraction and understanding to determine entity profiles, define relationships, and identify events. Technology research and development in these areas include but are not limited to: 4.1: Network Centric Multi-INT Fusion: The major focuses in this area include Multi-INT feature aided tracking (FAT), knowledge and reasoning based association, algorithm based association, non-linear tracking, track/sensor management, and onboard processing. 4.1.1: Multi-INT FAT: The intent is to develop new algorithms that utilize multi-INT features to overcome the lack of persistent surveillance, large collection gap times, and dense target environments (>3 targets per sensor resolution cell) that result in ambiguous association conditions in Multi-INT tracking and fusion algorithms that utilize kinematics only. Examples of features include, but are not limited to, advanced radar features such as high range-resolution radar (HRR), synthetic aperture radar (SAR) imagery and inverse synthetic aperture radar (ISAR), video imagery features such as color, shape and size, hyperspectral imagery features such as color and texture, ID features from SIGINT, and features obtained from HUMINT reports. FAT algorithms may utilize the features in combination with, or to augment the kinematic track state or to stitch pure kinematic tracklets after periods of kinematic confusion or extended sensor gaps. Algorithms which combine features into models such that cross-domain association (e.g. correlation of video with hyperspectral features) can occur are also sought. Algorithms are also sought for the specific case of extracting and combining multiple-features from multiple, homogeneous and heterogeneous video sensors in dense target environments to obtain longer, more accurate tracks. The key to this type of fusion is interoperability between the video sensors and sensors from other tracking sources such as non-imagery derived information sources. It is the current practice for the user to click on an object/pixel for manual nomination. The user is essentially telling the computer to track the selected object. The goal of the feature aided tracking portion of the effort would be to eliminate this bottleneck by devising algorithms that automatically perform this process and combine the results with other intelligence sources, such as MOVINT data. 4.1.2: Knowledge and Reasoning Based Association: The objective is to develop new methods and algorithms to overcome the factors discussed in 4.1.1 that limit Multi-INT tracking and fusion performance. Previous research has shown that augmenting traditional association methods with knowledge and reasoning based association algorithms shows great promise to increase tracking performance in difficult conditions. Technologies of interest include, but are not limited to knowledge based reasoning and learning, adductive and deductive reasoning, context based association and other heuristic techniques. Of specific interest are context based techniques which utilize information such as geospatial features, traffic models, cultural data, and forensically derived motion and behavioral patterns to aid the association problem. 4.1.3: Non-linear tracking: In this area of research, measures of nonlinearity have been explored to determine which non-linear tracking filter to use under various conditions. In fact, a filter swapping suite has been tried, and significant improvements were demonstrated. However, there is a much broader spectrum of nonlinear filters that can be employed, and advanced computing resources to exploit. The work in nonlinear filters needs to be expanded to consider vehicle dynamic models and new ways of predicting the performance of particle filters, Unscented Kalman Filters, and Extended Kalman Filters and other nonlinear tracking filters when used in conjunction with each other. 4.1.4: Track/Sensor Management: The objective is to develop algorithms to manage sensor resources to maintain track on all targets in the battle space and maintain a consistent track picture. Sensor management techniques may be developed to manage multiple modes on a single sensor or multiple modes and sensor modalities across multiple platforms. For the latter case, centralized or distributed techniques may be utilized, but either must ensure that track pedigree information is maintained and a consistent track numbering scheme for outputting tracks is developed. Also of specific interest are sensor resource management techniques that balance the requirements between forensics and high value target tracking (i.e. short pure tracklets on all surveillance tracks vice extended-duration track on a smaller subset of targets). 4.1.5: Onboard processing: High resolution sensor platforms suchas Constant Hawk, Angel Fire and proposed sensor platforms such as Gorgon Stare and Argus produce large amounts of data that can cause latency and information availability issues due to bandwidth limitations. The intent is to develop algorithms that can be implemented onboard the sensor platform and produce relevant information, requiring minimal bandwidth, so that this information can be distributed to a wide variety of users with minimal latency. 4.2: Moving Target Indicator (MTI) Analysis: Ground Moving Target Indicator (GMTI) and Video: Automated Adaptive Pattern Recognition. The objective of this topic is to explore, identify, and prototype innovative approaches that process multiple movement based event streams to detect patterns and trends in real time or near real time. The ability to detect patterns in the flow of events will allow a proactive use of previously observed activity. The challenge is to provide these indicators and warnings for continually emerging tactics. Innovative algorithms are desired that will monitor all potential MOVINT data sources (S/GMTI, geospatial and temporal event info, coalition traffic patterns from Blue Force data, maritime data like Automatic Identification System (AIS), etc) to generate alerts in an autonomous or semi-autonomous manner. 4.2.1: Low Flying Targets: One of the greatest challenges in the analysis of MTI data is accounting for low flying targets that appear in MTI data. The capability to extract the low flying targets from certain GMTI databases is desired. Also, ground looking radars and video sensors are used to track and classify air vehicles and surface vehicles. Many of these systems rely on the intervention of an analyst to track and classify air vehicles and surface vehicles. Automation of this process through the development of knowledge based heuristics to distinguish between ground targets and low-flying targets within these GMTI databases would greatly improve the state of the art. In addition, the use of Air Moving Target (AMTI) templates at the beam clutter edges of a side-looking airborne radar when combined with GMTI information would greatly enhance the capability to extract low fliers from MTI data. 4.3: IED Forensics: The major focuses in this area include leveraging historical-temporal agility, geospatial reasoning and cued exploitation, and social/MTI network correlation. Of specific interest are the following areas: 4.3.1: Movement Augmented Network Analysis: The objective is to develop automated tools to reciprocally influence both derived movement information and social network analysis (SNA) to define and exploit the structure and behavior of the enemy. The intent is to develop movement derived link analysis capabilities to establish probabilistic linkages between people, places, other entities, and events. The movement derived linkages would then be utilized as an additional information source for SNA. The intent is also to develop automated tools for improved group detection (i.e. terrorist cells) by incorporating MTI or SIGINT derived linkages and more traditional transactional and soft data. Additionally of interest are automated tools that can exploit and fuse the data and intelligence products cited above as context for GMTI analyses. 4.3.2: Activity Analysis: The objective of this effort is to establish the nature and intent of meeting events by combining kinematic analysis with behavior analysis and SNA for enhanced and timely situational analysis (SA). It will provide actionable information on activities (or lack of) based upon GMTI and SIGINT data thus enabling timely situational analysis updates. Approaches must develop activity level detection/kinematic analysis tools that incorporate and exploit geospatial and temporal data, develop meeting analyst/behavior analyst software tool(s) to establish the type of meeting, phase of operation and potential participants, and develop an approach for this domain to accrue evidence of the nature and intent of meeting, phase of operation, participants and update SA. Technologies of interest include, but are not limited to, automatic tracking, spatial scan statistics, and Bayesian Networks and Dempster-Shafer evidence accrual. 4.4: Text Understanding: The major focus of this area is to help analysts more effectively exploit the information in unstructured and semi-structured textual data, such as Intelligence message traffic (e.g., Human Intelligence reports (HUMINT)), open source intelligence (OSINT), chat, and Significant Activity Reports (SIGACTs). The goal is to help analysts find potentially relevant information within large collections of documents faster, and to put it in a structured form enabling the use of automated analysis and visualization (A&V) tools. Information of interest to analysts includes entities ("things", such as people, locations, organizations, weapons, facilities, etc.), entity attributes, relationships between entities, and events. 4.4.1 Specific user capabilities of interest include enabling automated link analysis and visualization from information in unstructured text, enabling automated analysis and visualization of events on timelines and maps, the creation and update of cross-document entity profiles that consolidate all the information extracted on a given real-world entity from 1,000s of documents ("electronic dossiers"), and the creation of cross-document event profiles that consolidate all the information extracted on a given real-world event from 1,000s of documents. Multilingual extraction and translation is also of keen interest to end users. In addition, exploiting the information in certain types of textual data (e.g., chat) is of high interest to users. 4.4.2 A number of research areas need to be pursued to mature text extraction technology to support the aforementioned user capabilities. These include, but are not limited to, entity extraction technology gaps, within-document co-reference resolution, cross-document co-reference resolution, temporal analysis of events (time-stamping), location-stamping of events (geo-coding), discourse analysis, subjective information extraction, inferring non-explicit information from text, rapid domain porting/customization with minimal training data and user interaction, multilingual text extraction, and high-accuracy extraction of information from certain text types of high interest to our users, such as chat and SIGACTs. II. AWARD INFORMATION: Total funding for this BAA is approximately $24.9M. The anticipated funding to be obligated under this BAA is broken out by fiscal year as follows: FY 10 - $4M; FY 11 - $5.3M; FY 12 - $5.3M; FY 13 - $5.3M; and FY14 -$5.0M. Individual awards will not normally exceed 36 months with dollar amounts normally ranging between $150K - $750K per year. There is also the potential to make awards up to any dollar value. Awards of efforts as a result of this announcement will be in the form of contracts, grants, or cooperative agreements depending upon the nature of the work proposed. III. ELIGIBILITY INFORMATION: 1. ELIGIBLE APPLICANTS: All foreign allied participation is excluded at the prime contractor level. 2. COST SHARING OR MATCHING: Cost sharing is not a requirement, but may be considered in making awards. 3. CCR Registration: Unless exempted by 2 CFR 25.110 all offerors must: (a) Be registered in the Central Contractor Registration (CCR) prior to submitting an application or proposal; (b) Maintain an active CCR registration with current information at all times during which it has an active Federal award or an application or proposal under consideration by an agency; and (c) Provide its DUNS number in each application or proposal it submits to the agency. 4. Executive Compensation and First-Tier Sub-contract/Sub-recipient Awards: Any contract award resulting from this announcement may contain the clause at FAR 52.204-10 - Reporting Executive Compensation and First-Tier Subcontract Awards. Any grant or agreement award resulting from this announcement may contain the award term set forth in 2 CFR, Appendix A to Part 25 http://ecfr.gpoaccess.gov/cgi/t/text/text-idx?c=ecfr&sid=c55a4687d6faa13b137a26d0eb436edb&rgn=div5&view=text&node=2: IV. APPLICATION AND SUBMISSION INFORMATION: 1. APPLICATION PACKAGE: THIS ANNOUNCEMENT CONSTITUTES THE ONLY SOLICITATION. WE ARE SOLICITING WHITE PAPERS ONLY. DO NOT SUBMIT A FORMAL PROPOSAL AT THIS TIME. Those white papers found to be consistent with the intent of this BAA may be invited to submit a technical and cost proposal, see Section VI of this announcement for further details. For additional information, a copy of the AFRL/Rome Research Sites "Broad Agency Announcement (BAA): A Guide for Industry," April 2007, may be accessed at: http://www.fbo.gov/spg/USAF/AFMC/AFRLRRS/Reference%2DNumber%2DBAAGUIDE/listing.html 2. CONTENT AND FORM OF SUBMISSION: Offerors are required to submit 3 copies of a 3 to 5 page white paper summarizing their proposed approach/solution. The purpose of the white paper is to preclude unwarranted effort on the part of an offeror whose proposed work is not of interest to the Government. The white paper will be formatted as follows: Section A: Title, Period of Performance, Estimated Cost, Name/Address of Company, Technical and Contracting Points of Contact (phone, fax and email)(this section is NOT included in the page count); Section B: Task Objective; and Section C: Technical Summary and Proposed Deliverables. Multiple white papers within the purview of this announcement may be submitted by each offeror. If the offeror wishes to restrict its white papers/proposals, they must be marked with the restrictive language stated in FAR 15.609(a) and (b). All white papers/proposals shall be double spaced with a font no smaller than 12 pitch. In addition, respondents are requested to provide their Commercial and Government Entity (CAGE) number, their Dun & Bradstreet (D&B) Data Universal Numbering System (DUNS) number, a fax number, an e-mail address, and reference BAA 10-03-RIKA with their submission. All responses to this announcement must be addressed to the technical POC, as discussed in paragraph six of this section. 3. SUBMISSION DATES AND TIMES: White papers may be submitted at any time during the life of this BAA. However, it is recommended that white papers be received by the following dates to maximize the possibility of award: FY 10 should be submitted by 15 Mar 2010, FY11 by 3 May 2010, FY 12 by 2 May 2011; FY 13 by 1 May 2012; FY 14 by 1 May 2013. White papers will be accepted until 2pm Eastern time on 30 Sep 2014, but it is less likely that funding will be available in each respective fiscal year after the dates cited. The closing date for this BAA is 30 Sep 2014. FORMAL PROPOSALS ARE NOT BEING REQUESTED AT THIS TIME. 4. FUNDING RESTRICTIONS: The cost of preparing white papers/proposals in response to this announcement is not considered an allowable direct charge to any resulting contract or any other contract, but may be an allowable expense to the normal bid and proposal indirect cost specified in FAR 31.205-18. Incurring pre-award costs for ASSISTANCE INSTRUMENTS ONLY, are regulated by the DoD Grant and Agreements Regulations (DODGARS). 5. All Proposers should review the NATIONAL INDUSTRIAL SECURITY PROGRAM OPERATING MANUAL, (NISPOM), dated February 28, 2006 as it provides baseline standards for the protection of classified information and prescribes the requirements concerning Contractor Developed Information under paragraph 4-105. Defense Security Service (DSS) Site for the NISPOM is: https://www.dss.mil/portal/ShowBinary/BEA%20Repository/new_dss_internet//isp/fac_clear/download_nispom.html. 6. OTHER SUBMISSION REQUIREMENTS: DO NOT send white papers to the Contracting Officer. All responses to this announcement must be addressed to the attention of the appropriate technical Point of Contact listed in Section VII. Electronic submission will also be accepted. All White Papers must identify the Area that the white paper addresses, i.e. "This whitepaper addresses Area 2.0 Link and Group Discovery (LGD)." Failure to identify the technical area may result in the paper not being evaluated or considered. V. APPLICATION REVIEW INFORMATION: 1. CRITERIA: The following criteria, which are listed in descending order of importance, will be used to determine whether white papers and proposals submitted are consistent with the intent of this BAA and of interest to the Government: (1) Overall Scientific and Technical Merit - Including the approach for the development and/or enhancement of the proposed technology; (2) Technology Related Experience - The extent to which the offeror demonstrates relevant technology and domain knowledge; (3) Openness/Maturity of Solution - The extent to which existing capabilities and standards are leveraged and the relative maturity of the proposed technology in terms of reliability and robustness; and (4) Reasonableness and realism of proposed costs and fees (if any). No further evaluation criteria will be used in selecting white papers/proposals. Individual white paper/proposal evaluations will be evaluated against the evaluation criteria without regard to other white papers and proposals submitted under this BAA. White papers and proposals submitted will be evaluated as they are received. 2. REVIEW AND SELECTION PROCESS: Only Government employees will evaluate the white papers/proposals for selection. The Air Force Research Laboratory's Information Directorate has contracted for various business and staff support services, some of which require contractors to obtain administrative access to proprietary information submitted by other contractors. Administrative access is defined as "handling or having physical control over information for the sole purpose of accomplishing the administrative functions specified in the administrative support contract, which do not require the review, reading and comprehension of the content of the information on the part of non-technical professionals assigned to accomplish the specified administrative tasks." These contractors have signed general non-disclosure agreements and organizational conflict of interest statements. The required administrative access will be granted to non-technical professionals. Examples of the administrative tasks performed include: a. Assembling and organizing information for R&D case files; b. Accessing library files for use by government personnel; and c. Handling and administration of proposals, contracts, contract funding and queries. Any objection to administrative access must be in writing to the Contracting Officer and shall include a detailed statement of the basis for the objection. VI. AWARD ADMINISTRATION INFORMATION: 1. AWARD NOTICES: Those white papers found to be consistent with the intent of this BAA may be invited to submit a technical and cost proposal. Notification by email or letter will be sent by the technical POC. Such invitation does not assure that the submitting organization will be awarded a contract. Those white papers not selected to submit a proposal will be notified in the same manner. Prospective offerors are advised that only Contracting Officers are legally authorized to commit the Government. All offerors submitting white papers will be contacted by the technical POC, referenced in Section VII of this announcement. Offerors can email the technical POC for status of their white paper/proposal no earlier than 45 days after submission. 2. ADMINISTRATIVE AND NATIONAL POLICY REQUIREMENTS: Depending on the work to be performed, the offeror may require a TS-SCI facility clearance and safeguarding capability; therefore, personnel identified for assignment to a classified effort must be cleared for access to TS-SCI information at the time of award. In addition, the offeror may be required to have, or have access to, a certified and Government-approved facility to support work under this BAA. Data subject to export control constraints may be involved and only firms holding certification under the US/Canada Joint Certification Program (JCP) (www.dlis.dla.mil/jcp) are allowed access to such data. 3. REPORTING: Once a proposal has been selected for award, offerors will be required to submit their reporting requirement through one of our web-based, reporting systems known as JIFFY or TFIMS. Prior to award, the offeror will be notified which reporting system they are to use, and will be given complete instructions regarding its use. Please note that use of the JIFFY or TFIMS application requires customers outside of the.mil domain to purchase an approved External Certificate Authority certificate to facilitate a secured log on process. It is necessary to obtain an ECA certificate BEFORE obtaining a JIFFY or TFIMS user account. Additional information on obtaining an ECA is available at: http://iase.disa.mil/pki/eca/index.html. VII. AGENCY CONTACTS: Questions of a technical nature shall be directed to the cognizant technical point of contact, as specified below: Section 1: Reasoning and Learning: Mr. Jeff Hudack, 315-330-4488, Jeffrey.Hudack@rl.af.mil Section 2.1: Link and Group Discovery (LGD): Mr. Peter Lamonica, 315-330-4088, Peter.Lamonica@rl.af.mil Section 2.2: Situation Analysis: Mr. Michael Hinman, 315-330-3175, Michael.Hinman@rl.af.mil Section 3: Anticipation: Dr. John Salerno, 315-330-3667, John.Salerno@rl.af.mil Section 4: Perception: Tracking: Mr. Brian OHern, 315-330-3995, Brian.Ohern@rl.af.mil, Text Understanding: Ms. Carrie Pine, 315-330-2473, Carrie.Pine@rl.af.mil Questions of a contractual/business nature shall be directed to the cognizant contracting officer, as specified below: Lynn White Telephone (315) 330-4996 Email: Lynn.White@rl.af.mil The email must reference the solicitation (BAA) number and title of the acquisition. In accordance with AFFARS 5301.91, an Ombudsman has been appointed to hear and facilitate the resolution of concerns from offerors, potential offerors, and others for this acquisition announcement. Before consulting with an ombudsman, interested parties must first address their concerns, issues, disagreements, and/or recommendations to the contracting officer for resolution. AFFARS Clause 5352.201-9101 Ombudsman (Apr 2010) will be incorporated into all contracts awarded under this BAA. The AFRL Ombudsman is as follows: Susan Hunter Building 15, Room 225 1864 Fourth Street Wright-Patterson AFB OH 45433-7130 FAX: (937) 225-5036; Comm: (937) 904-4407 All responsible organizations may submit a white paper which shall be considered.
Web Link
FBO.gov Permalink
SN02477459-W 20110622/110620235037-ce7f946444c0f7bad6b0980b8e72e2aa (fbodaily.com)
FedBizOpps Link to This Notice
(may not be valid after Archive Date)

FSG Index  |  This Issue's Index  |  Today's FBO Daily Index Page |
ECGrid: EDI VAN Interconnect ECGridOS: EDI Web Services Interconnect API Government Data Publications CBDDisk Subscribers
 Privacy Policy  © 1994-2016, Loren Data Corp.