Abstract
A kernel regressor to estimate a six-degree-of-fredoom non linear model of an autonomous underwater vehicle is proposed. Although this estimator assumes that the model coefficients are linear combinations of basis functions, it circumvents the problem of specifying the basis functions by using the kernel trick. The Gaussian radial basis function is the chosen kernel, with the Kernel matrix being regularized by its principal components. The variance of the Gaussian radial basis function and the number of principal components are hyper-parameters to be determined by the minimisation of a final prediction error criterion and using the training data. A simulated autonomous underwater vehicle is proposed was used as case study.

Abstract

Abstract
Associated with the exploitation of metallic minerals in Europe during the 20th century, several mining areas were abandoned without adequate environmental intervention. Furthermore, these areas lack studies to characterize the impact of pollution on the hydrogeological system. The area surrounding the tungsten mine of Regoufe, in northern Portugal, is one such area exploited during the Second World War. The accumulation of sulfide-rich tailings may have caused an acid mine drainage (AMD), where the leaching processes caused by seepage water led to soil contamination, evidenced by its acid character and anomalous concentrations of some Potentially Toxic Elements (PTE) reported in previous studies. The present research proposes an innovative approach that seeks the integration of different geophysical techniques to characterize the impact of mining activity on the subsurface. Electrical resistivity (ER) and electromagnetic (EM) were used to measure subsurface electrical properties. In addition, seismic refraction and Multichannel Analysis of Surface Waves (MASW) were performed to characterize the geometry, depth, and geomechanical behavior of the soil and rock bodies. The integration of these techniques allowed the interpretation of hydrogeological sections and a 3D resistivity volume to gain insight into the distribution of potentially contaminating fluids and tailings material present in the mining valley.

Abstract
Special care must be taken when considering robots designed to operate collaboratively, such as a swarm, to prevent these agents from being damaged due to unwanted collisions. This work proposes integrating techniques used to move robots, using the Robot Operating System (ROS) and Python's Scikit-Fuzzy module. Thus, this work developed a fuzzy-controlled collaborative obstacle avoidance system for a type of robot whose dynamics are based on motors' vibration. Thus, these robots were designed to participate in a swarm, and the collision must be avoided. In the search for navigation stability, optimal values were sought for the engines' pulse width modulation (PWM).

Abstract

Abstract