No description available.

No description available.

No description available.

Le toucher est considéré comme l’un des sens primordiaux à modéliser chez un robot afin de lui permettre de générer des comportements plus souples et plus agiles comme attraper un objet, toucher (ou être touché par) une personne. Même si les capteurs tactiles actuels sont encore très limités en comparaison à la peau humaine, combinés à la vision et à la proprioception, le développement de nouveaux capteurs proches de la peau humaine pourrait démultiplier les capacités d’interactions d’un robot afin d’interagir directement avec une personne en toute sécurité et de partager avec lui son environnement physique et social. A la différence de la peau humaine, les principaux capteurs tactiles utilisés en robotique actuellement ne sont capables de détecter des variations de pression et de poids que sur de petites surfaces uniquement. De plus, ceux-ci sont souvent très rigides et n’ont pas les propriétés élastiques de déformation de la peau humaine. Les travaux de cette thèse se basent sur le développement d’une interface tactile proche d’une "peau artificielle" en terme de surface de recouvrement (qui peuvent atteindre plusieurs dizaines de centimètres carrés) et de localisation des points de contact de quelques dizaines de millinewtons. Deux aspects principaux sont développés : (i) aspect d’ingénierie comprenant le développement d’un prototype de peau artificielle conçue pour un robot humanoïde afin de lui conférer une perception tactile, et (ii) aspect cognitifs qui s’appuient sur l’intégration de multiples rétroactions sensorielles (tactile, visuelle, proprioceptive) dans le but d’avoir un robot qui puisse interagir physiquement avec des personnes.Le prototype tactile développé est basé sur la reconstruction du champ électrique à la surface d’un matériau conducteur, suivant le principe de la Tomographie par Impédance Électrique (TIE). Notre innovation principale a été d’implémenter des techniques d’apprentissage par réseau de neurones artificiels afin de reconstruire l’information sans utiliser les techniques analytiques d’inversion de matrice coûteuse en temps de calcul. De plus, nous montrons que l’utilisation de réseaux de neurones artificiels permet d’avoir un système beaucoup plus biomimétique, indispensable pour comprendre la perception du toucher chez l’être humain.Nous avons ensuite abordé le problème de l’intégration des informations tactiles et motrices. Après avoir recouvert un bras manipulateur avec la peau artificielle, nous avons fait apprendre un réseau de neurones son schéma corporel et adapter sa compliance par retour tactile. Le fonctionnement du moteur est basé sur le contrôle par admittance du bras robotique. Des expériences montrent que les réseaux de neurones peuvent contrôler l’interaction adaptative entre le bras du robot avec une personne grâce à l’estimation du couple appris selon la position où la force tactile avait été appliquée lors de la phase d’apprentissage.Enfin, nous nous sommes intéressées à la problématique de la représentation du corps au niveau neuronal, comment les êtres humains perçoivent leur propre corps à travers tous les sens (visuel, tactile et proprioceptif). Nous avons proposé un modèle biologique au niveau du cortex pariétal qui s’appuie sur l’intégration de multiples rétroactions sensorielles du corps du robot (son bras) et sur la synchronisation des rétroactions visuelles et proprioceptives. Nos résultats montrent l’apprentissage d’une image corporelle et l’espace péri-personnel avec l’émergence de neurones qui codent une information spatiale visuo-tactile relative au déplacement du bras et centrée soit sur le bras robotique soit centrée sur l’objet. / The touch perception is considered as one of the crucial senses to be recreated in a robot so that it could generate a more flexible and agile behavior. For instance, grasping an object, as well as touch or be touched by a person. Although modern touch sensors are still very limited compared to the human skin, combined with vision and proprioception, the development of new sensors similar to human skin could multiply the robot’s capacity to interact directly and safely with a person, as well as to share his or her physical and social environment.Unlike human skin, the main touch sensors used in modern robotics are only capable of detecting the pressure and weight variations on small batches of surface. Moreover, they are often quite stiff and do not have the elastic deformation capacity intrinsic to the human skin. The purpose of this thesis is to develop a touch interface close to "artificial skin" in terms of the covered area (which can reach several square decimeters) and localization of the contact points (several dozen millinewtons). Two main aspects have been developed: (i) the engineering aspect including the development of an artificial skin prototype for a humanoid robot designed to impart a tactile perception, and (ii) the cognitive aspect that is based on the integration of multiple sensory feedbacks (tactile, visual, proprioceptive) in order to conceive a robot that can physically interact with people.The developed tactile prototype is based on the reconstruction of the electric field on the surface of a conductive material, following the principle of Electrical Impedance Tomography (EIT). Our main innovation was to implement the neural network learning techniques to reconstruct the information without using the inverse matrix analytical techniques which imply time consuming computation. Moreover, we show that the application of artificial neural networks allows to obtain a much more biomimetic system, essential to understand the perception of the human touch.Then, we addressed the issue of integrating tactile and motor information. After having covered a manipulator arm with artificial skin, we have learn a neural network its body schema and enables it to adjust its compliance with tactile feedback. The functioning of the motor is based on the admittance control of the robot arm. Experiments show that neural networks can control the adaptive interaction between the robot arm and a human being by estimating the torque perceived according to the position where the touch force had been applied during the learning phase.Finally, we turned our attention to the issue of the body representation at the neuronal level, namely, how human beings perceive their own body through all their senses (visual, tactile, and proprioceptive). We have proposed a biological model in the parietal cortex, which is based on the integration of multiple sensory feedbacks from the robot’s body (its arm) and on the synchronization of visual and proprioceptive feedback. Our results show the capacity to perceive the body image with the emergence of neurons that encode a spatial visual-tactile information of the arm movement and is centered on either the robotic arm or on the object.

<p>Tactile sensing is an essential human ability for understanding their surroundings. It allows humans to detect and manipulate objects that are concealed or difficult to see in low-light settings. Further, tactile sensing enables people to comprehend object and surface properties that cannot be obtained through visual feedback alone. This is achieved with gentle touches, enabling tactile exploration of fragile, sensitive objects, or living organisms. This capability could be transferred to robots through suitable hardware and algorithms. Nevertheless, current tactile sensors and skills for robotics are not comparable to the tactile sense of humans, thus resulting in inferior characterization of scenes and a risk of altering object states.</p> <p><br></p> <p>To address these limitations, this dissertation proposes a novel framework for robot active tactile exploration and object characterization. The framework combines bioinspired soft sensors and minimally invasive tactile exploration strategies to minimize perturbations to objects. This framework was achieved by: (1) an ultrasensitive whisker sensor that enables object characterization with minimal interaction forces; (2) autonomous tactile exploration skills to localize objects and then characterize their shape and surface properties; and (3) machine learning techniques to analyze contact information gathered by our tactile sensors, enabling the understanding of object attributes by tactile sensing alone. </p> <p><br></p> <p>Experiments were conducted to validate the effectiveness of the framework. In terms of object localization efficiency, informative path planners and contour exploration patterns outperformed baseline methods. Furthermore, the whisker sensor was successfully employed to characterize object surface and liquid properties. Finally, the features found through the characterization process allowed for successful classification by machine learning techniques. These results indicate that the proposed framework can effectively gather multimodal features from environments while maintaining the safety of objects. </p>

Touch (or tactile) sensors are gaining renewed interest as the level of sophistication in the application of minimally invasive surgery and humanoid robots increases. The spatial resolution of current large-area tactile sensors (greater than 1 cm2) lag human fingers by over an order of magnitude. Using metal and semiconducting nanoparticles, a ~100 nm thick, large area thin-film device working on the principles of electron tunneling is self-assembled, such that the change in current density through the film and the electroluminescence light intensity are linearly proportional to the local stress. By pressing a United States 1 cent coin (and also a copper grid) on the device a well resolved stress image by focusing the electroluminescence light directly on CCD is obtained. Both the lateral and height resolution of texture are comparable to human finger at similar stress levels of ~10 KPa. The fabrication of the film is based on self-assembly of polyelectrolytes, and metal and semiconducting nanoparticles in a layered architecture. The polyelectrolyte layer functions as the dielectric tunneling barrier and the nanoparticles function as the base for tunneling electrons. The assembly of the device can be simplified by incorporating the functionality of the polyelectrolyte and the nanoparticles in a single composite medium. A non-micellar mineralization process for the synthesis of multifunctional nanocomposite materials is also reported as a possible building block for the assembly of tactile sensor. The non-micellar method results in the synthesis of monodisperse semi-conducting nanoparticles templated on polymer chains dissolved in solution at high yield. The monodispersity is achieved due to the beaded necklace morphology of the polyelectrolyte chains in solution where the beads are nanometer-scale nodules in the polymer chain and the nanoparticles are confined to the beads. The resultant structure is a nanoparticle studded necklace where the particles are imbedded in the beads. Multiple cycles of the synthesis on the polymer template yield nanoparticles of identical size, resulting in a nanocomposite with high particle fraction. The resultant nanocomposite has beaded-fibrilar morphology with imbedded nanoparticles, and can be solution cast to make electroluminescent thin film devices. The concept is further modified for synthesis of metal nanoparticles on polyelectrolyte templates with isolated beaded morphology. / Ph. D.

This thesis contains introduction to the principles of dynamic plantography and it´s clinical application. Afterwards it is described feet anatomy, types of feet arch and human walking process. Next part describes principles of various types of tactile sensors and electrical platform Arduino. Most important part of this thesis is focused on teoretical design of device and it’s practical realization. The last part of diploma thesis is devoted to discussion of parameters of the device and to results of measuring of group of volunteers.

No description available.

Exploring surfaces is an essential ability for humans, allowing them to interact with a large variety of objects within their environment. This ability to explore surfaces is also of a major interest in the development of a new generation of humanoid robots, which requires the development of more efficient artificial tactile sensing techniques. The details perceived by statically touching different surfaces of objects not only improve robotic hand performance in force-controlled grasping tasks but also enables the feeling of vibrations on touched surfaces. This thesis presents an extensive experimental study of object surface exploration using biologically-Inspired tactile-enabled robotic fingers. A new multi-modal tactile sensor, embedded in both versions of the robotic fingertips (similar to the human distal phalanx) is capable of measuring the heart rate with a mean absolute error of 1.47 bpm through static explorations of the human skin. A two-phalanx articulated robotic finger with a new miniaturized tactile sensor embedded into the fingertip was developed in order to detect and classify surface textures. This classification is performed by the dynamic exploration of touched object surfaces. Two types of movements were studied: one-dimensional (1D) and two-dimensional (2D) movements. The machine learning techniques - Support Vector Machine (SVM), Multilayer Perceptron (MLP), Random Forest, Extra Trees, and k-Nearest Neighbors (kNN) - were tested in order to find the most efficient one for the classification of the recovered textured surfaces. A 95% precision was achieved when using the Extra Trees technique for the classification of the 1D recovered texture patterns. Experimental results confirmed that the 2D textured surface exploration using a hemispheric tactile-enabled finger was superior to the 1D exploration. Three exploratory velocities were used for the 2D exploration: 30 mm/s, 35 mm/s, and 40 mm/s. The best classification accuracy of the 2D recovered texture patterns was 99.1% and 99.3%, using the SVM classifier, for the two lower exploratory velocities (30 mm/s and 35mm/s), respectively. For the 40 mm/s velocity, the Extra Trees classifier provided a classification accuracy of 99.4%. The results of the experimental research presented in this thesis could be suitable candidates for future development.