To develop algorithms, software, and/or hardware necessary to collect, process, and fuse information from multiple sensors based on multiple platforms (XBR, SBIRS, EKV, UEWR) in real time in order to improve acquisition, tracking and discrimination of threat objects in a cluttered environment, advanced sensor fusion techniques will be investigated. Automated abductive inference (best-explanation reasoning) will be used to create a changing, "best interpretation" representation of the situation from incoming data. Modeling and simulation will be used by the abductive inference software for automatic generation of predictions from hypotheses, enabling the continual generation of predictions to support: hypothesis evaluation, sensor tasking, planning, and detection of anomalies that may be valuable indications of deception, modeling errors, or sensor failure. Abductive inference will work tightly with predictive inference to provide a reliable, self-correcting representation of the situation, based on current evidence, using domain knowledge encoded as causal-model fragments. Aetion will work with Teledyne Brown Engineering to agree upon a specific test which will begin the process of creating capabilities beyond anything currently available. During phase I we will work on models to use them to solve that problem. Anticipated Benefits/Commercial Applications: Aetion's technology will enable people to make better decisions, build more useable models and use computers to explain data. People will have a greater understanding of the range of alternatives and the value tradeoffs. Potential commercial applications include: rapid route re-planning and sensor tasking for the Air Force and Navy; other military planning, re-planning and simulation; civilian planning, re-planning and simulation; military and civilian engineering design; and infrastructure vulnerability analysis (anti-terrorism, Homeland Defense, targeting).
Keywords: MCDM, decision, simulation, planning, sensor Pareto, replanning, optimization
