In order to better capture empirical phenomena, research on option price and implied volatility modeling increasingly advocates the use of nonparametric methods over simple functional forms. This, however, comes at a price, since they require dense observations to yield sensible results. Calibration is therefore typically performed using aggregate data. Ironically, the use of time-series data i...

This paper presents a discrete-time robust control for electrically driven robot manipulators in the task space. A novel discrete-time model-free control law is proposed by employing an adaptive fuzzy estimator for the compensation of the uncertainty including model uncertainty, external disturbances and discretization error. Parameters of the fuzzy estimator are adapted to minimize the estimat...

Optimal solutions to Markov Decision Problems (MDPs) are very sensitive with respect to the state transition probabilities. In many practical problems, the estimation of those probabilities is far from accurate. Hence, estimation errors are limiting factors in applying MDPs to realworld problems. We propose an algorithm for solving finite-state and finite-action MDPs, where the solution is guar...

There has been a rapid increase in the use of unmanned aerial vehicles (UAVs). On UAVs, autopilots are fundamental components that use a variety of sensors to estimate vehicle’s state and perform actuation, ultimately allowing to perform the assigned tasks. Modern UAVs are often being powered by electric motors which provide a number of advantages over internal combustion engines, in terms of w...

This paper deals with the robust filtering problem for uncertain bilinear stochastic discrete-time systems with estimation error variance constraints. The uncertainties are allowed to be norm-bounded and enter into both the state and measurement matrices. We focus on the design of linear filters, such that for all admissible parameter uncertainties, the error state of the bilinear stochastic sy...

In this paper, the concept of command-tostate/output mapping is introduced for robust estimation under output feedback. Speci£cally, robust estimation is achieved if a command-to-state mapping of the plant converges to that of an uncertainty-free observer. It is shown using the Lyapunov direct method that, for a command-to-state mapping to be convergent, the Jacobian system corresponding to the...

A nonlinear geometric observer is developed, which infers the distillate and residue compositions in a highly-nonlinear binary distillation column from temperature measurements. The estimator performance is evaluated by imposing severe step changes to the input variables. In particular, the capability of the observer reconstruction is assessed with regard to ill-conditioning of the observabilit...

The idea of applying H1 estimation techniques to the \array uncertainties problem" is motivated by the fact that H1 estimation is robust to model uncertainties and lack of statistical information with respect to noise. In this paper, a new state space model for the received signal of a general array of sensors is developed which, in contrast to existing models, is capable of handling the simult...

We provide a new computationally-efficient class of estimators for risk minimization. We show that these estimators are robust for general statistical models: in the classical Huber ǫ-contamination model and in heavy-tailed settings. Our workhorse is a novel robust variant of gradient descent, and we provide conditions under which our gradient descent variant provides accurate estimators in a g...

To handle the state estimation of a nonlinear system perturbed by a scalar disturbance distributed by a known nonlinear vector, we incorporate a sliding mode term into a nonlinear observer to realise a robust nonlinear observer. By linking the observability of the unknown input to the output measurement, the so-called matching condition is avoided. The measurable output estimation error is the ...