Sequential nonlinear estimation with nonaugmented priors (Q1094800): Difference between revisions

How can the basic compatibility of theory and observations be investigated for nonlinear processes without requiring stochastic characterizations for residual error terms? The present paper proposes a flexible least-cost approach. For each possible estimate x for the sequence of process states, let \(c_ D(x)\) and \(c_ M(x)\) denote the costs incurred for deviations away from the prior dynamic specifications and prior measurement specifications, respectively. Define the cost-efficiency frontier to be the greatest lower bound for the set of all possible cost pairs \((c_ D(x),c_ M(x))\), conditional on the given observations. State sequence estimates x which attain the cost-efficiency frontier indicate the possible ways the actual process could have developed over time in a manner minimally incompatible with the prior dynamic and measurement specifications. An algorithm is developed for the exact sequential updating of the cost- efficient state sequence estimates as the duration of the process increases and additional observations are obtained.