No description available.

"This thesis presents an effective approach to study tactile based mobile robot navigation. A Matlab simulator, which can simulate the properties of the tactile sensors, the environment, and the motion of the robot, is developed. The simulator uses an abstraction model of a compliant tactile sensor to represent an array of sensors covering the robot. The tactile sensor can detect normal and shear forces. The simulator has been used by a set of human subjects to drive a robot in an indoor environment to capture data. The details of the implementation and the data collected are presented in this thesis. From the data, some contact features can be extracted. Regarding the features, this thesis uses the Gaussian classifier and Gaussian mixture model to classify the data and build the feature classification model. Comparing the classification results of these two methods, the Gaussian mixture model has better performance. Applying the feature classification model, some contact objects can be detected, such as wall and corner. Based on this classification tool, a simple navigation problem can be solved successfully."

No description available.

The aim of this project is to enable robots to recognise objects and object categories by combining vision and touch. In this thesis, a novel inexpensive tactile sensor design is presented, together with a complete, probabilistic sensor-fusion model. The potential of the model is demonstrated in four areas: (i) Shape Recognition, here the sensor outperforms its most similar rival, (ii) Single-touch Object Recognition, where state-of-the-art results are produced, (iii) Visuo-tactile object recognition, demonstrating the benefits of multi-sensory object representations, and (iv) Object Classification, which has not been reported in the literature to date. Both the sensor design and the novel database were made available. Tactile data collection is performed by a robot. An extensive analysis of data encodings, data processing, and classification methods is presented. The conclusions reached are: (i) the inexpensive tactile sensor can be used for basic shape and object recognition, (ii) object recognition combining vision and touch in a probabilistic manner provides an improvement in accuracy over either modality alone, (iii) when both vision and touch perform poorly independently, the sensor-fusion model proposed provides faster learning, i.e. fewer training samples are required to achieve similar accuracy, and (iv) such a sensor-fusion model is more accurate than either modality alone when attempting to classify unseen objects, as well as when attempting to recognise individual objects from amongst similar other objects of the same class. (v) The preliminary potential is identified for real-life applications: underwater object classification. (vi) The sensor fusion model providesimprovements in classification even for award-winning deep-learning basedcomputer vision models.

This thesis explores two novel ways of reducing the data complexity of tactile sensing. The thesis begins by examining the state-of-the art in tactile sensing, not only examining the sensor construction and interpretation of data but also the motivation for these designs. The thesis then proposes two methods for reducing the complexity of data in tactile sensing. The first is a low-power tactile sensing array exploiting a novel application of a pressure-sensitive material called quantum tunnelling composite. The properties of this material in this array form are shown to be beneficial in robotics. The electrical characteristics of the material are also explored. A bit-based structure for representing tactile data called Bitworld is then defined and its computational performance is characterised. It is shown that this bit-based structure outperforms floating-point arrays by orders of magnitude. This structure is then shown to allow high-resolution images to be produced by combining low resolution sensor arrays with equivalent functional performance to a floating-point array, but with the advantages of computational efficiency. Finally, an investigation into making Bitworld robust in the presence of positional noise is described with simulations to verify that such robustness can be achieved. Overall, the sensor and data structure described in this thesis allow simple, but effective tactile systems to be deployed in robotics without requiring a significant commitment of computational or power resources on the part of a robot designer.

The manipulation contact forces convey substantial information about the manipulation state. This paper address the fundamental problem of interpreting the force signals without any additional manipulation context. Techniques based on forms of the generalized sequential likelihood ratio test are used to segment individual strain signals into statistically equivalent pieces. We report on our experimental development of the segmentation algorithm and on its results for contact states. The sequential likelihood ratio test is reviewed and some of its special cases and optimal properties are discussed. Finally, we conclude by discussing extensions to the techniques and a contact interpretation framework.

Grasping and manipulation of objects is an integral part of a robot’s physical interaction with the environment. In order to cope with real-world situations, sensor based grasping of objects and grasp stability estimation is an important skill. This thesis addresses the problem of predicting the stability of a grasp from the perceptions available to a robot once fingers close around the object before attempting to lift it. A regrasping step can be triggered if an unstable grasp is identified. The percepts considered consist of object features (visual), gripper configurations (proprioceptive) and tactile imprints (haptic) when fingers contact the object. This thesis studies tactile based stability estimation by applying machine learning methods such as Hidden Markov Models. An approach to integrate visual and tactile feedback is also introduced to further improve the predictions of grasp stability, using Kernel Logistic Regression models. Like humans, robots are expected to grasp and manipulate objects in a goal-oriented manner. In other words, objects should be grasped so to afford subsequent actions: if I am to hammer a nail, the hammer should be grasped so to afford hammering. Most of the work on grasping commonly addresses only the problem of finding a stable grasp without considering the task/action a robot is supposed to fulfill with an object. This thesis also studies grasp stability assessment in a task-oriented way based on a generative approach using probabilistic graphical models, Bayesian Networks. We integrate high-level task information introduced by a teacher in a supervised setting with low-level stability requirements acquired through a robot’s exploration. The graphical model is used to encode probabilistic relationships between tasks and sensory data (visual, tactile and proprioceptive). The generative modeling approach enables inference of appropriate grasping configurations, as well as prediction of grasp stability. Overall, results indicate that the idea of exploiting learning approaches for grasp stability assessment is applicable in realistic scenarios. / <p>QC 20121026</p>

Robots can move, see, and navigate in the real world outside carefully structured factories, but they cannot yet grasp and manipulate objects without human intervention. Two key barriers are the complexity of current approaches, which require complicated hardware or precise perception to function effectively, and the challenge of understanding system performance in a tractable manner given the wide range of factors that impact successful grasping. This thesis presents sensors and simple control algorithms that relax the requirements on robot hardware, and a framework to understand the capabilities and limitations of grasping systems. / Engineering and Applied Sciences

Tactile sensors are the last frontier to robots that can handle everyday objects and interact with humans through contact. Robots are expected to recognize the properties of objects in order to handle them safely and efficiently in a variety of applications, such as health- and elder care, manufacturing, or high-risk environments. To be effective, such sensors have to sense the geometry of touched surfaces and objects, as well as any other relevant information for their tasks, such as forces, vibrations, and temperature, that allow them to safely and securely interact within an environment. Given the capability of humans to easily capture and interpret tactile data, one promising direction in order to produce enhanced robotic tactile sensors is to explore and imitate human tactile sensing capabilities. In this context, this thesis presents the design and hardware implementation issues related to the construction of a novel multimodal bio-inspired skin module for dynamic and static tactile surface characterization. Drawing inspiration from the type, functionality, and organization of cutaneous tactile elements in the human skin, the proposed solution determines the placement of two shallow sensors (a tactile array and a nine DOF magnetic, angular rate, and gravity system) and a deep pressure sensor within a flexible compliant structure, similar to the receptive field of the Pacinian mechanoreceptor. The benefit of using a compliant structure is tri-folded. First, the module has the capability of performing touch tasks on unknown surfaces, tackling the tactile inversion problem. The compliant structure guides deforming forces from its surface to the deep pressure sensor, while keeping track of the deformation of the structure using advantageously placed shallow sensors. Second, the module’s compliant structure and its embedded sensor placement provide useful data to overcome the problem of estimating non-normal forces, a significant challenge for the current generation of tactile sensing technologies. This capability allows accommodating sensing modalities essential for acquiring tactile images and classifying surfaces by vibrations and accelerations. Third, the compliant structure of the module also contributes to the relaxation of orientation constraints of end-effectors or other robotic parts carrying the module to contact surfaces of unknown objects. Issues related to the module calibration, its sensing capabilities and possible real-world applications are also presented.

No description available.