N112-131 TITLE: Data Fusion for USW Common Tactical Picture

TECHNOLOGY AREAS: Information Systems, Battlespace

ACQUISITION PROGRAM: Program Executive Office, Integrated Warfare Systems (PEO IWS) 5E

OBJECTIVE: The objective of this research topic is to develop a real-time decision-aid that can compute multi-sensor threat assessment analysis for USW decision support systems and aid the user in the decision-making process.

DESCRIPTION: The Navy USW community has a significant need for decision support tools that support the operator in making decisions about fusing multiple targets and managing uncertainty in the challenging environment of undersea warfare. Current fusion engines focus on automated processes that combine contacts into tracks. The operator is presented with the results of the fusion process with no understanding of why some tracks were combined while others were not. Without knowledge of the process behind the fusion the operator is unable to accurately assess the outcome of the fusion process. These black box systems reduce the operator�s situation awareness (SA) by reducing their knowledge of the tracks in their area. The fusion system should include the operator in the decisions and give them a method to continually identify confidence and uncertainty in the information being used in the fusion process.

After many years of research, the vast majority of work in data fusion has focused primarily at Level 0 and 1 of the JDL fusion model, which deals primarily with the characteristics of single objects (Ref 1,2) such as track fusion. Although there is significant interest and need for computer models incorporating fusion at the higher levels of the JDL model (to include object meaning and relationships, mission impact and projected future states), currently there is very little work that has accomplished this objective (Ref 3).

Endsley�s model of SA provides a foundation for developing computer models that include these higher levels of data fusion (Ref 4,5). This work provides insight into the characteristics that computational models of SA would need to embody, and provides tools and methodologies that can be utilized to develop fusion engines and algorithms that focus on the higher levels of data fusion by mimicking the human processes of perception, comprehension, and projection (Ref 6). Principled processes for information presentation also provide guidance on how to present the results of this data fusion to the operator in a manner that allows for data checking and verification, to insure that the operator understands the confidence and reliability of the fused information (Ref 7,8).

The goal of this research program is to develop a decision aiding tool that effectively fuses track and other pertinent information into needed assessments of enemy threats and presents the data fusion results to the user. It should also provide confidence and uncertainty information to the user. This tool should not only combine relevant contact information together into meaningful tracks, but it should also allow the user to assess the data fusion process. The tool should provide:

1. Perception. Enabling technologies should be capable of assimilating, filtering, and displaying relevant info to the user. This includes being able to compute relevance, confidence, and uncertainty about each track.
2. Comprehension. Enabling technologies should be capable of integrating low-level information into higher cognitive "bits of information" to reduce information clutter, but still provide access to low-level data for the user. Enabling technologies should be capable of quantifying threat assessment and ranking existing threats across multiple goals, and displaying it to the user in a way that allows users to understand the reliability of the assessments.
3. Projection. This includes projecting future locations and threat characteristics of the fused track at future points in time based on past data points, track capabilities, and other intel on the situation.

PHASE I: Provide a preliminary concept for a decision support tool that can support SA and decision-making for fusing multiple contacts into tracks. Identify information requirements and algorithmic approaches that will be used to compute track fusion, threat assessment, and threat projection. Develop prototype UI concepts that will allow the operator to assess the fusion outputs and modify as needed.

PHASE II: Develop a prototype of the decision support tool. Determine feasibility and assess performance of this preliminary model for a test case. Essential human performance metrics should be included for assessing efficacy of the tool. An integration plan should be provided to detail how the prototype will be integrated within existing Navy systems.

PHASE III: The firm shall work with IWS 5 to transition the decision support tool to USW Decision Support acquisition programs. The decision support tool development methods and algorithms should also have transition potential to other branches of the military.

PRIVATE SECTOR COMMERCIAL POTENTIAL/DUAL-USE APPLICATIONS: 1. Training for operators of systems requiring cognitive situational awareness such as Air traffic Control. 2. Training for professionals with complex cognitive decisions using decision aids for information seeking such as Medical Doctors making diagnosis and course of treatment decisions.

REFERENCES:
1. Hall, D. L., Llinas, J. (1997) An introduction to multisensory data fusion. Proceedings of the IEEE, 85 (1), p. 6-23.

2. Kokar, M. , Matheus C. J., Letkowski, J.,Baclawski, K. and Kogut, P. (2003) Association in Level 2 Fusion. Ft. Belvoir Defense Technical Information Center JAN 2004.

3. Toth, G. (2011). Keynote presentation to the CogSIMA 2011 Conference on Cognitive Methods in Situation Awareness and Decision Support. Miami, IEEE.

4. Endsley, M. R. (1995). Toward a theory of situation awareness in dynamic systems. Human Factors, 37(1), pp. 32-64.

5. Endsley, M. R. (2011) Building Models of Situation Awareness: From Humans to Computers. Conference on Cognitive Methods in Situation Awareness and Decision Support. Miami, IEEE.

6. Jones, R. E., Connors, E. S., & Endsley, M. R. (2009). Incorporating the Human Analyst into the Data Fusion Process by Modeling Situation Awareness Using Fuzzy Cognitive Maps. 12th International Conference on Information Fusion. Mountain View, CA: ISIF.

7. Hall, D. L., Shaw, T.S., Garga, A. K., and Rottoff, E.S. (2002). Human-Centered Remote Information Fusion. Proceedings of the MSS National Symposium on Sensor and Data Fusion, San Diego, CA.

8. Endsley, M. R., Bolte, B., & Jones, D. G. (2003). Designing for situation awareness: An approach to human-centered design. (London: Taylor & Francis).

KEYWORDS: Anti-Submarine Warfare; Situational Awareness; Undersea Warfare; data fusion; adaptive user interface; threat assessment

** TOPIC AUTHOR (TPOC) **

DoD Notice:   Between April 26 and May 25, 2011, you may talk directly with the Topic Authors to ask technical questions about the topics. Their contact information is listed above. For reasons of competitive fairness, direct communication between proposers and topic authors is not allowed starting May 26, 2011, when DoD begins accepting proposals for this solicitation.

However, proposers may still submit written questions about solicitation topics through the DoD's SBIR/STTR Interactive Topic Information System (SITIS), in which the questioner and respondent remain anonymous and all questions and answers are posted electronically for general viewing until the solicitation closes. All proposers are advised to monitor SITIS (11.2 Q&A) during the solicitation period for questions and answers, and other significant information, relevant to the SBIR 11.2 topic under which they are proposing.

If you have general questions about DoD SBIR program, please contact the DoD SBIR Help Desk at (866) 724-7457 or email weblink.