Detail

Probabilistic Constraints and Applications

Uncertainty and nonlinearity play a major role in modeling most real-world continuous systems. The probabilistic constraint approach combines a stochastic representation of uncertainty on the parameter values with a reliable constraint framework robust to nonlinearity. The approach computes conditional probability distributions of the model parameters, given the underlying uncertainty and the model constraints. This talk provides a short overview of the probabilistic constraint framework and illustrates its potential on real-world applications, namely, ocean color remote sensing, localization and mapping of autonomous robots, reliability based design, and biomedical models. This work was developed in the context of project PROCURE – Probabilistic Constraints for Uncertainty Reasoning in Science and Engineering Applications.