J.L. Pedreno-Molina

Hyper RBF model for accurate reaching in redundant robotic systems

In this paper, a solution based on hyper radial basis functions networks (HRBF) for learning inverse kinematics in redundant robots is presented. This model has been implemented in two different visuo-motor robotic platforms for reaching and grasping applications. The obtained results allow to verify the robustness and accuracy capabilities of this neural model for reaching and tracking objects as well as to give a solution when redundant robots are considered. Therefore, the invariance of the proposed visuo-motor architecture for different arm-head relative configurations is demonstrated.

A Neural Tactile Architecture Applied to Real-time Stiffness Estimation for a Large Scale of Robotic Grasping Systems

This paper presents a model for solving the problem of real-time neural estimation of stiffness characteristics for unknown objects. For that, an original neural architecture is proposed for a large scale robotic grasping systems applied for unknown object with unspecified stiffness characteristics. The force acquisition is based on tactile information from force sensors in robotic manipulator. The proposed model has been implemented on a robotic gripper with two parallel fingers and on a one d.o.f. robotic finger with opponent artificial muscles and angular displacements. This self-organized model is inspired of human biological system, and is carried out by means of Topographic Maps and Vector Associative Maps. Experimental results demonstrate the efficiency of this new approach.

Multimode cavity efficiency optimization by optimum load location-experimental approach

In this paper, a novel load-matching procedure for microwave-heating applicators is presented and tested. In order to accomplish the optimization procedure, an optimization method based on the use of the Lebenverg-Marquardt technique has been specifically developed and tested on two different microwave ovens. The proposed procedure allows an efficient optimization of three-dimensional microwave applicators by means of the dielectric sample relocation as a function of its complex permittivity, size, and operating frequency. Experimental measurements of the reflection coefficient are presented and analyzed over several samples and multimode cavities. Results indicate that high power efficiencies can be obtained provided that operating frequency is not just below TM-mode cutoff frequencies for the transverse dimensions of the oven.

A neural model for visual-tactile-motor integration in robotic reaching and grasping tasks

This paper presents a neural model to solve the visual-tactile-motor coordination problem in robotic applications. The proposed neural controller is based on the VAMC (Vector Associative Map) model. This algorithm is based on the human biological system and has the ability of learning the mapping that establishes the relationship between the spatial and the motor coordinates. These spatial inputs are composed of visual and force parameters. The LINCE stereohead carries out a visual detection process, detecting the positions of the object and of the manipulator. The artificial tactile skins placed over the two fingers of the gripper measure the force distribution when an object is touched. The neural controller has been implemented for robotic operations of reaching and object grasping. The reaching process is fed back in order to minimize the Difference Vector (DV) between the visual projections of the object and the manipulator. The stable grasping task processes the force distribution maps detected in the contact with the two surfaces of the gripper, in order to direct the object into the robotic fingers. Experimental results have demonstrated the robustness of the model and the accuracy of the final pick-and-place process.

A neural controller for a robotic hand with artificial tactile skins in grasping tasks

In this paper, artificial tactile skins have been applied to a grasping task which require a certain precision in the determination of the object contact position with the surfaces and the pressure exercised in each point of the same. This design allows to process the force distribution maps in order to do precise maneuvers of grasping.

Precise Evaluation of Coaxial to Waveguide Transitions by Means of Inverse Techniques

In this paper, a new two-tier inverse characterization technique for coaxial to waveguide transition evaluation is presented and properly validated. The transition is characterized by estimating its scattering parameters and a cascade procedure is employed in order to compare simulations and measurements during the unterminating procedure. In contrast to other unterminating methods there are no restrictions concerning the number and type of standards and two transitions are simultaneously characterized. Additionally, genetic algorithms and the gradient descent method are used for error minimization during the unterminating stage. The accuracy of this two-tier inverse technique is evaluated as a function of the employed standards and the obtained results are compared to those provided by different well-known calibration algorithms. Results show that it is possible to properly characterize the coaxial to waveguide transition in a very flexible and accurate way.

A modular neural network linking Hyper RBF and AVITE models for reaching moving objects

In this paper, the problem of precision reaching applications in robotic systems for scenarios with static and non-static objects has been considered and a solution based on a modular neural architecture has been proposed and implemented. The goal of this solution is to combine robustness and capability mapping trajectories from two biologically plausible neural network sub-modules: Hyper RBF and AVITE. The Hyper Basis Radial Function (HypRBF) neural network solves the inverse kinematic in redundant robotic systems, while the Adaptive Vector Integration to End-Point (AVITE) visuo-motor neural model quickly maps the difference vector between current and desired position in both spatial (visual information) and motor coordinates (propioceptive information). The anthropomorphic behaviour of the proposed architecture for reaching and tracking tasks in presence of spatial perturbations has been validated over a real arm-head robotic platform.

Emulation of the animal muscular actuation system in an experimental platform

This research work involves the design and implementation of an efficient biomechanical model of the animal muscular actuation system. In order to build the biomechanical system to have mechanical properties as close as possible to the human or animal arm, auto-reversible DC motors with appropriate planetary gearboxes and multi-radial flexible couplings (in order to pull and to be pushed), force and position sensors, and tendons are integrated in the system. In this system the implementation of mathematical models of muscle in a whole skeletal muscle force generation on DC motors was carried out. Experimental results show the actuation system has the basic properties of the animal musculoskeletal system. This properties are the force-length and force-velocity relationships.

A new methodology for in situ calibration of a neural network-based software sensor for S-parameter prediction in six-port reflectometers

In this work, a neural network-based software sensor is proposed for determining the reflection coefficient from measurements obtained by a six-port reflectometer. The proposed software sensor is able to cope with the nonlinearities and noise inherent to the measurement electronics, without needing additional calibration. To extract data for the calibration, a new method that allows in situ calibration is applied. Experimental evidence of the feasibility of the proposed method is given using a simulation testbench. r 2006 Published by Elsevier B.V.

Microwave heating modelling of a green smoothie: Effects on glucoraphanin, sulforaphane and S-methyl cysteine sulfoxide changes during storage

BACKGROUND The heating of a green smoothie during an innovative semi-continuous microwave treatment (MW; 9 kW for 15 s) was modelled. Thermal and dielectric properties of the samples were previously determined. Furthermore, the heating effect on the main chemopreventive compounds of the smoothie and during its subsequent storage up to 30 days at 5 or 15 °C were studied. Such results were compared to conventional pasteurisation (CP; 90 °C for 45 s) while unheated fresh blended samples were used as the control. RESULTS A procedure was developed to predict the temperature distribution in samples inside the MW oven with the help of numerical tools. MW-treated samples showed the highest sulforaphane formation after 20 days, regardless of the storage temperature, while its content was two-fold reduced in CP samples. Storage of the smoothie at 5 °C is crucial for maximising the levels of the bioactive compound S-methyl cysteine sulfoxide. CONCLUSION The proposed MW treatment can be used by the food industry to obtain an excellent homogeneous heating of a green smoothie product retaining high levels of bioactive compounds during subsequent retail/domestic storage up to 1 month at 5 °C.