Search

This work proposes a discrete-time non-linear neural observer based on a recurrent high order neural network in parallel model trained with an algorithm based on the extended Kalman filter for discrete-time multiple input multiple output non-linear systems with unknown dynamics and unknown time-delay. To prove the semi-globally uniformly ultimately boundedness of the proposed neural observer the stability analysis based on the Lyapunov approach is included. Applicability of the proposed observer is shown via simulation and experimental results. [ABSTRACT FROM AUTHOR]

This work presents a parallelization method for the Clifford support vector machines, based in two characteristics of the Gaussian Kernel. The pure real-valued result and its commutativity allows us to separate the multivector data in its defining subspaces. These subspaces are independent from each other, so we can solve the problem using parallelism. The motivation is to present an easy approach that can be explained using the more common known concepts of complex numbers and quaternions, because in general there exists a lack of familiarity with geometric algebra. [ABSTRACT FROM AUTHOR]

This work proposes a discrete-time nonlinear neural identifier based on a recurrent high-order neural network trained with an extended Kalman filter-based algorithm for discrete-time deterministic multiple-input multiple-output systems with unknown dynamics and time-delay. To prove the semi-globally uniformly ultimately boundedness of the proposed neural identifier, the stability analysis based on the Lyapunov approach is included. Applicability of the proposed identifier is shown via simulation and experimental results, all of them performed under the presence of unknown external and internal disturbances as well as unknown time-delays. [ABSTRACT FROM AUTHOR]

This paper deals with a visual servoing scheme, which uses a paracatadioptric sensor as visual input. The paracatadioptric sensor provides a wide field of view while maintaining the single center of projection, which is a desirable property of these sensors. The projection induced by this sensor is nonlinear. In this paper a linear model of this projection is presented, the model is developed using the conformal geometric algebra framework which allows to represent nonlinear conformal transformations using a special type of multivectors called versors. With this model we relate the feature time variation with the camera velocity to design a velocity controller used in a visual servoing task. [ABSTRACT FROM AUTHOR]