In this paper, we propose a system architecture for decision-making support on ISR (i.e., Intelligence, Surveil­lance, Reconnaissance) missions via optimizing resource allocation. We model a mission as a graph of tasks, each of which often requires exclusive access to some resources. Our system guides users through refinement of their needs through an interactive interface. To maximize the chances of executing new missions, the system searches for pre-existent information collected on the field that best fit the needs. If this search fails, a set of new requests representing users' requirements is considered to maximize the overall benefit constrained by limited resources. If an ISR request cannot be satisfied, feedback is generated to help the commander further refine or adjust their information requests in order to still provide support to the mission. In our work, we model both demands for resources and the importance of the information retrieved realistically in that they are not fully known at the time a mission is submitted and may change overtime during execution. The amount of resources consumed by a mission may not be deterministic; e.g., a mission may last slightly longer or shorter than expected, or more of a resource may be required to complete a task. Furthermore, the benefits received from the mission, which we call profits, may also be non-deterministic; e.g., successfully localizing a vehicle might be more important than expected for accomplishing the entire operation. Therefore, when satisfying ISR requirements we take into account both constraints on the underlying resources and uncertainty of demands and profits.

Date Published: 22 May 2013
PDF: 8 pages
Proc. SPIE 8742, Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR IV, 874203 (22 May 2013); doi: 10.1117/12.2018047

Published in SPIE Proceedings Vol. 8742:
Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR IV
Tien Pham; Michael A. Kolodny; Kevin L. Priddy, Editor(s)