Computational Methods for Decision Making Program

The Office of Naval Research Computational Methods for Decision Making Applied Research Program is composed of three thrusts—Large-scale Distributed Decision-making, Automated Image Understanding and Resource Optimization.

  • Large-scale Distributed Decision-making: The amount of data that the decision makers are facing today is much larger than any time before in human history. In addition, the data is much more complex, heterogeneous and fast changing. Analysis of such large and complex datasets is beyond the cognitive abilities of any single decision maker. The aim of this thrust is to develop new methods for extraction and analysis of relevant information from large-scale datasets, and to develop new tools for distributed information sharing and decision-making. To achieve this aim, it is required to advance fundamental understanding of networks (such as social and organizational networks), and to integrate rigorous methods from mathematical and computational sciences with methods from social sciences.

    Some of the topics of interest include, but are not limited to:

    Coordination and integration: Methods for aggregation of individual preferences, optimal allocation and matching mechanisms; methods for collaborative problem solving; methods for formalizing information content and communication rules.

    Knowledge acquisition, assessment and dissemination: Methods for adaptive learning on individual and group levels; methods for large-scale assessment and evaluation of distributed information (such as peer reviewing and deliberation); techniques for information representation and dissemination.

    Network structure: Design of the optimal network structure for a given task complexity; analysis of network dynamics; structure formation, evolution, and adaptation over time.

    POC information:
    Name: Dr. Predrag Neskovic
    Email: predrag.neskovic@navy.mil
    Title: Program Officer
    Division: ONR-311, Mathematics, Computers and Information Sciences

  • Automated Image Understanding: The objective of Automated Image Understanding thrust is to further develop promising computational methods based on principled approaches for building reliable vision systems. The primary focus is on high-level vision, namely, recognizing objects and activities, and inferring intentions and threats in surveillance imagery, as well as for semantic search of large image and video databases. Suggested research topics of interest include the following. (a) Methods for integration of high-level knowledge and image data, in particular hierarchical and compositional models for representation and processing, and reasoning. (b) Learning complex visual concepts, in particular learning relationships among objects, activities involving interactions of people and objects/spaces, etc. (c) Using non-visual information to provide additional context for recognition and inference. (d) Reconstruction of “scenes and events” from ad hoc networks of heterogeneous cameras, where cameras may be still or video, stationary or mobile, with different resolutions and image quality, and with images taken from widely different views. (e) Methods for analyzing images from other modalities and fusion of multimodal imagery for enhanced recognition.

    POC information:
    Name: Dr. Behzad Kamgar-Parsi
    Email: behzad.kamgarparsi@navy.mil
    Title: Program Officer
    Division: ONR-311, Mathematics, Computers and Information Sciences

  • Resource Optimization: The Resource Optimization thrust supports applied research in mathematical optimization, such as linear, nonlinear, integer and combinatorial optimization. This thrust aims to develop innovative models and optimization-based solution techniques for Navy-relevant problems in resource allocation, such as those arising in mission planning, command and control, and logistics. Current application areas of interest are maritime mission planning and unmanned sensor management and allocation. In particular, in the area of unmanned sensor management and allocation, a specific area of emphasis is the development of techniques based on decentralized optimization.

    POC information:
    Name: Dr. Don Wagner
    Email: don.wagner@navy.mil
    Title: Program Officer
    Division: ONR-311, Mathematics, Computers and Information Sciences

Note: Proposers are encouraged to contact the program officer to discuss their research interest prior to the submission of formal proposals.

Program Contact Information

Name: Dr. Donald Wagner

Title: Program Officer

Department: Code 31

Division: Mathematics Computer and Information Sciences

Email: don.wagner@navy.mil

Address
Office of Naval Research
875 N. Randolph Street, Suite 1425
Arlington, Va. 22203

* Some pages on this website provide links which require a plug in to view.