This paper proposes an exponential interpolation to merge a part-of-speech-based language model and a word-based$n$-gram language model to accomplish word prediction tasks. In order to find a set of mathematical equations to properly describe the language modeling, a model based on partial differential equations is proposed. With the appropriate initial conditions, it was found an interpolation model similar to the traditional maximum entropy language model. Improvements in keystroke saved and perplexity over the word-based$n$-gram language model and two other traditional interpolation models is obtained, considering three different languages. The proposed interpolation model also provides additional improvement in hit rate parameter.

This paper proposes a solution to the problem of path-following by a formation of mobile robots (three robots are considered, forming a triangle on the ground). The proposed solution allows planning the motion of the desired formation without needing specifying how each robot should move. The proposed strategy is based on the cluster space approach, and embeds a reactive method to give the formation the capability of avoiding obstacles during the path-following. Theoretical analysis and experimental results are presented, which demonstrate the effectiveness of the proposed control system to guide the multi-robot formation to accomplish a path-following task.

Recently, we have successfully exploited and applied the new and powerful non-parametric Integrated Nested Laplace Approximation (INLA) Bayesian inference method to the problem of Superresolution (SR) image reconstruction, generating the INLA SR algorithm. Such approach achieved superior image reconstruction results in comparison to other state-of-the-art methods. In this paper we propose a modification in the mathematical model of the INLA SR, generating the new DFT INLA SR algorithm. It is shown that the new approach reduces the computation cost of the INLA SR algorithm (from O(n4) to O(n log(n))), as well as the dimension of the matrices handled (from n2× n2to n × n, the size of the HR image), at the cost of a slight reduction of the HR image quality.

This paper proposes a new reactive method to avoid obstacles during trajectory tracking, considering unicycle mobile robots navigating in semi-structured environments, which can be used in association with any trajectory tracking controller. A meaningful improvement in the obstacle avoidance process is achieved analyzing the layout of the obstacles in relation to the planned trajectory. Experimental results show that the evasion algorithm is fairly efficient, reducing the time spent to avoid obstacles and shortening the path traveled by the robot during such procedure as well.

Superresolution are techniques to enhance the resolution of an image without changing the camera resolution, through using software algorithms. In this context, this paper proposes a fully automatic Superresolution algorithm, using a recent non-parametric Bayesian inference method based on numerical integration, known in the statistical literature as Integrated Nested Laplace Approximation. By applying such inference method to the Superresolution problem, this paper shows that all the equations needed to implement this technique can be written in closed form. Moreover, the results of several simulations (three of them are here presented) show that the proposed algorithm performs better than other Superresolution algorithms recently proposed. As far as the authors know, this is the first time that the Integrated Nested Laplace Approximation is used in the area of image processing, which is a meaningful contribution of this paper.

This paper presents a new fuzzy controller for trajectory tracking for unicycle-like mobile robots, represented by a Takagi-Sugeno fuzzy model. Such controller allows setting different gains for the controller, according to the values of the velocity of the trajectory and the values of the tracking error. The noise inherent to the robot odometry is treated by the fuzzy controller itself, not requiring the use of filters. The stability of the developed controller is proven based on the theory of Lyapunov. Experimental results are also presented, and show that the proposed controller is effectively able to guide the robot during a trajectory tracking task.

This paper presents the classification of three mental tasks, using the electroencephalographic signal and simulating a real-time process, that is, the pseudo-online technique. Linear Discriminant Analysis is used to recognize the mental tasks, and the feature extraction uses the Power Spectral Density. The choice of EEG channel and frequency uses the Kullback-Leibler symmetric divergence and a reclassification model is proposed to stabilize the classifier. Finally, it is expected that the proposed method can be implemented in a Brain-Computer Interface associated with a robotic wheelchair.

This work presents a strategy to control a mobile robot navigating along a corridor. The proposed control system is based on the fusion of the control signals generated by two redundant controllers. Redundancy here means that both controllers have the same objective, which is to keep the mobile robot in the middle of the corridor. The two control signals being fused are generated by a controller based on the optical flow technique and by a controller based on distance measures provided by ultrasonic sensors.

This work presents a new approach to calculate the optical flow, which uses the decentralized information filter to accomplish a data fusion step. The proposal consists in taking some least mean square estimates of the optical flow vector associated to a certain region of the image considered and to fuse them in order to get a more accurate final estimate of such a vector. Besides this, the way the initial least mean square estimates are obtained is also modified, by reducing the number of observations used to get each one of them, in order to make the overall algorithm faster. The idea is that such initial estimates can be rougher, once the fusion engine improves the accuracy of the final estimate, in the sense that the decentralized information filter generates a final estimate whose variance is lower than the smallest variance associated to the initial estimates.

This paper proposes an alternative approach to address the problem of coordinating behaviors in mobile robot navigation: fusion of control signals. Such approach is based on a set of two decentralized information filters, which accomplish the data fusion involved. Besides these two fusion engines, control architectures designed according to this approach also embed a set of different controllers that generate reference signals for the robot linear and angular speeds. Such signals are delivered to the two decentralized information filters, which estimate suitable overall reference signals for the robot linear and angular speeds, respectively. Thus, the background for designing such control architectures is provided by the nonlinear systems theory, which makes this approach different from any other yet proposed. This background also allows checking control architectures designed according to the proposed approach for stability. Such analysis is carried out in the paper, and shows that the robot always reaches its final destination, in spite of either obstacles along its path or the environment layout. As an example, a control architecture is designed to guide a mobile robot in an experiment, whose results allows checking the good performance of the control architecture and validating the design approach proposed as well.