Robust Bayesian Estimation

Robust Bayesian Estimation

The AVL dedicates a significant portion of its resources to developing new state-of-the-art state estimation methods. Among the areas of interest, the AVL’s main aim is to develop online robust estimators for hardware implementations. Effectively, the AVL seeks to develop estimators with a reasonably high level of robustness to nonlinearities and uncertainties while maintaining algorithms complexity level at a minimum.

AVL’s recent results include the development of Kalman-based filters that have a very convenient implementation and are more resilient to failure than a conventional Kalman formulation, even when the estimator faces numerical instability. This last characteristic is significant because many of the developments of the AVL are taken as launchpads by the U.S. Air Force Research Laboratory. Thus, most of our research comes with proof-of-concept hardware implementations, where numerical issues may arise more easily.


Ramos, J. Humberto, Kevin Brink, Prashant Ganesh, and John E. Hurtado. “Factorized Partial-Update Schmidt–Kalman Filter” Journal of Guidance, Control, and Dynamics, vol. 45, issue 9, pp. 1567-1582 (2022).

Ramos, J. Humberto, Kevin Brink, Prashant Ganesh, and John E. Hurtado. “A summary on the UD Kalman Filter.” arXiv preprint arXiv:2203.06105 (2022).

Ramos, J. Humberto, Davis W. Adams, Kevin M. Brink, and Manoranjan Majji. “Observability Informed Partial-Update Schmidt Kalman Filter.” In 2021 IEEE 24th International Conference on Information Fusion (FUSION), pp. 1-8. IEEE, 2021.