Advanced Computational Algorithms for Nonlinear Filtering for Real Time Environment

The techniques of linear filtering have contributed tremendously in missile guidance and modern radar technology. However, they can only serve as a first order approximation to the infinite-dimensional nonlinear filtering problem. Solutions to theseproblems are known in theory, and with the explosive growth of high performance computing, they have also increasingly become available in terms of practical algorithms. The objective of the proposed effort is to critically examine, categorize andevaluate existing nonlinear filtering algorithms, and develop new, hybrid algorithms that judiciously combine different algorithms for particular applications. The focus area will be on tracking, and we will develop suitable benchmark problems thatavoid many of the pitfalls involved when comparing algorithms using benchmarks. The proposed team consists of Scientific Systems Company Inc. (SSCI), Professor Amarjit Budhiraja at University of North Carolina at Chapel Hill, and Dr. Ronald Mahler atLockheed Martin Tactical Systems. SSCI has extensive expertise in control and signal processing and in algorithm/software development. Professor Budhiraja is one of the leaders in the study of stochastic filtering theory, and Dr. Mahler is a renownedexpert in multi-sensor multi-target tracking. The Phase I tasks are: (1) Literature survey of general nonlinear filtering problems; (2) Identification of the filtering problem in tracking; (3) Development of criteria to measure the performance of variousfiltering algorithms; (4) Development of a set of benchmark problems for the testing and comparison of algorithms; (5) Final report and Phase II recommendations. Nonlinear filtering is a very important area of research for both military and commercialapplications. The integrated, real time, hybrid computational algorithms and software developed under this project will enable more accurate and faster detections and/or estimations of signals in the noisy and nonlinear real world environments, and hencewill significantly improve current commercial and military radar technologies and communications systems.