You are here

Multiple Hypothesis Management

Description:

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Trusted AI and Autonomy

 

The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.

 

OBJECTIVE: Develop methodology and prototype software to enable autonomous hypothesis management and resolution of potential courses of action based on available data.

 

DESCRIPTION: As technology advances, services and capabilities become computerized, and an increasing number of processes are conducted electronically, there as an increasing need for real-time decision-making systems with many capabilities in various decision spaces. With intelligence gathering rapidly growing in size and sensors producing increasing amounts of data, manual inspection of the data quickly becomes infeasible. A common mantra in information fusion is that "analysts are drowning in data but starving for information," and this is readily apparent across several domains. The focus of this effort will be to develop a method to manage large decision spaces where several hypotheses must be considered and analyzed both spatially and temporally. Owing to the decision space of different types of situational awareness, such decision support systems must concentrate on and nominate specific decision tracks or rank multiple tracks representing the hypothesis. A commander's options during a mission span a large decision space, requiring understanding possible courses of action (COAs) for both red and blue forces and domain and problem complexities.

 

A scalable method is sought to assist decision makers through various analysis and modeling techniques that automate the evaluation of options to take at any given state while presenting the best alternatives clearly and concisely. A key aspect is to manage a decision space that could grow exponentially, while maintaining the most plausible and impactful COAs over the life of the mission.

 

PHASE I: Develop methodology for hypothesis management. Conduct analysis of alternatives and develop architecture for proposed solution. Develop use case in one or more domains and identify available and required data to support hypothesis management. GFE will not be provided.

 

PHASE II: Develop prototype software solution that implements chosen methodology for chosen use case. Integrate available data types and sources and output metrics that rank or score the likelihood of each plausible hypothesis. Test performance using real-world data. GFE will not be provided.

 

PHASE III DUAL USE APPLICATIONS: The Phase III effort may include implementation of the prototype software in operational environments for assessment by analysts against real-world, real-time data. Solution performance may be evaluated against the current state of the art. Military uses include enemy course of action determination across multiple domains. Expected TRL at Phase III entry is 5.

 

REFERENCES:

  1. Haberlin, Richard, da Costa, Paulo, Laskey, Kathryn, "Hypothesis Management in Support of Inferential Reasoning", Fifteenth International Command and Control Research and Technology Symposium, May, 2010. https://apps.dtic.mil/sti/citations/ADA525233;
  2. Gordon, J., Shortliffe, E.H. (2008). A Method for Managing Evidential Reasoning in a Hierarchical Hypothesis Space. In: Yager, R.R., Liu, L. (eds) Classic Works of the Dempster-Shafer Theory of Belief Functions. Studies in Fuzziness and Soft Computing, vol 219. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-44792-4_12;

 

KEYWORDS: hypothesis management; hypothesis resolution; courses of action; domain awareness; situational awareness

US Flag An Official Website of the United States Government