<p> Traditionally, models of a robot's kinematics and sensors have been provided by designers through manual processes. Such models are used for sensorimotor tasks, such as manipulation and stereo vision. However, these techniques often yield static models based on one-time calibrations or ideal engineering drawings; models that often fail to represent the actual hardware, or in which individual unimodal models, such as those describing kinematics and vision, may disagree with each other.</p><p> Humans, on the other hand, are not so limited. One of the earliest forms of self-knowledge learned during infancy is knowledge of the body and senses. Infants learn about their bodies and senses through the experience of using them in conjunction with each other. Inspired by this early form of self-awareness, the research presented in this thesis attempts to enable robots to learn unified models of themselves through data sampled during operation. In the presented experiments, an upper torso humanoid robot, Nico, creates a highly-accurate self-representation through data sampled by its sensors while it operates. The power of this model is demonstrated through a novel robot vision task in which the robot infers the visual perspective representing reflections in a mirror by watching its own motion reflected therein.</p><p> In order to construct this self-model, the robot first infers the kinematic parameters describing its arm. This is first demonstrated using an external motion capture system, then implemented in the robot's stereo vision system. In a process inspired by infant development, the robot then mutually refines its kinematic and stereo vision calibrations, using its kinematic structure as the invariant against which the system is calibrated. The product of this procedure is a very precise mutual calibration between these two, traditionally separate, models, producing a single, unified self-model.</p><p> The robot then uses this self-model to perform a unique vision task. Knowledge of its body and senses enable the robot to infer the position of a mirror placed in its environment. From this, an estimate of the visual perspective describing reflections in the mirror is computed, which is subsequently refined over the expected position of images of the robot's end-effector as reflected in the mirror, and their real-world, imaged counterparts. The computed visual perspective enables the robot to use the mirror as an instrument for spacial reasoning, by viewing the world from its perspective. This test utilizes knowledge that the robot has inferred about itself through experience, and approximates tests of mirror use that are used as a benchmark of self-awareness in human infants and animals.</p>

A concatenation framework for time-domain concatenative speech synthesis (TDCSS) is presented and evaluated. In this framework, speech segments are extracted from CV, VC, CVC and CC waveforms, and abutted. Speech rhythm is controlled via a single duration parameter, which specifies the initial portion of each stored waveform to be output. An appropriate choice of segmental durations reduces spectral discontinuity problems at points of concatenation, thus reducing reliance upon smoothing procedures. For text-to-speech considerations, a segmental timing system is described, which predicts segmental durations at the word level, using a timing database and a pattern matching look-up algorithm. The timing database contains segmented words with associated duration values, and is specific to an actual inventory of concatenative units. Segmental duration prediction accuracy improves as the timing database size increases. The problem of incomplete timing data has been addressed by using `default duration' entries in the database, which are created by re-categorising existing timing data according to articulation manner. If segmental duration data are incomplete, a default duration procedure automatically categorises the missing speech segments according to segment class. The look-up algorithm then searches the timing database for duration data corresponding to these re-categorised segments. The timing database is constructed using an iterative synthesis/adjustment technique, in which a `judge' listens to synthetic speech and adjusts segmental durations to improve naturalness. This manual technique for constructing the timing database has been evaluated. Since the timing data is linked to an expert judge's perception, an investigation examined whether the expert judge's perception of speech naturalness is representative of people in general. Listening experiments revealed marked similarities between an expert judge's perception of naturalness and that of the experimental subjects. It was also found that the expert judge's perception remains stable over time. A synthesis/adjustment experiment found a positive linear correlation between segmental durations chosen by an experienced expert judge and duration values chosen by subjects acting as expert judges. A listening test confirmed that between 70% and 100% intelligibility can be achieved with words synthesised using TDCSS. In a further test, a TDCSS synthesiser was compared with five well-known text-to-speech synthesisers, and was ranked fifth most natural out of six. An alternative concatenation framework (TDCSS2) was also evaluated, in which duration parameters specify both the start point and the end point of the speech to be extracted from a stored waveform and concatenated. In a similar listening experiment, TDCSS2 stimuli were compared with five well-known text-tospeech synthesisers, and were ranked fifth most natural out of six.

This thesis documents research undertaken into the design and evaluation of a computer tool (Colour Concept Generator) to produce colour schemes for products from verbal descriptors depicting a required aesthetic image or style. The system was designed to translate between descriptive words and colour combinations and aims to provide a form of ideas stimulus for a product designer at the initial stages of the design process. The computer system uses elements of artificial intelligence (AI) to `learn' colour and descriptor semiotic relations from a product designer based upon a proposed objective criteria or to reflect a designers personal style. Colour concepts for products can then be generated from descriptors based upon these semiotic relations. The philosophy of the research is based upon the idea of computing colour aesthetics at the front end of the design process and the design of an Al software mechanism to facilitate this. The problem was analysed with respect to the available literature on colour and a set of detail requirements for the system were presented. The system was then designed and code based upon the requirements and evaluated in terms of the overall philosophy, system methodology and application of computer media. The research is a contribution to the field of computer aided design regarding colour aesthetics and demonstrates the possibility of using an artificial intelligent machine to inspire and stimulate creative human thought. The Al software mechanism of the Colour Concept Generator is presented as an application of Al to aesthetic design. 11

This thesis describes an investigation into a proposed theory of AI. The theory postulates that a machine can be programmed to predict aspects of human behaviour by selecting and processing stored, concrete examples of previously experienced patterns of behaviour. Validity is tested in the domain of natural language. Externalisations that model the resulting theory of NLP entail fuzzy components. Fuzzy formalisms may exhibit inaccuracy and/or over productivity. A research strategy is developed, designed to investigate this aspect of the theory. The strategy includes two experimental hypotheses designed to test, 1) whether the model can process simple language interaction, and 2) the effect of fuzzy processes on such language interaction. Experimental design requires three implementations, each with progressive degrees of fuzziness in their processes. They are respectively named: Nonfuzz Babe, CorrBab and FuzzBabe. Nonfuzz Babe is used to test the first hypothesis and all three implementations are used to test the second hypothesis. A system description is presented for Nonfuzz Babe. Testing the first hypothesis provides results that show NonfuzzBabe is able to process simple language interaction. A system description for CorrBabe and FuzzBabe is presented. Testing the second hypothesis, provides results that show a positive correlation between degree of fuzzy processes and improved simple language performance. FuzzBabe's ability to process more complex language interaction is then investigated and model-intrinsic limitations are found. Research to overcome this problem is designed to illustrate the potential of externalisation of the theory and is conducted less rigorously than previous part of this investigation. Augmenting FuzzBabe to include fuzzy evaluation of non-pattern elements of interaction is hypothesised as a possible solution. The term FuzzyBaby was coined for augmented implementation. Results of a pilot study designed to measure FuzzyBaby's reading comprehension are given. Little research has been conducted that investigates NLP by the fuzzy processing of concrete patterns in language. Consequently, it is proposed that this research contributes to the intellectual disciplines of NLP and AI in general.

Thesis (M.S.)--Youngstown State University, 2008. / Includes bibliographical references (leaves 50-52). Also available via the World Wide Web in PDF format.

Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2008. / Source: Dissertation Abstracts International, Volume: 69-05, Section: B, page: 3100. Adviser: Minh N. Do. Includes bibliographical references (leaves 117-124) Available on microfilm from Pro Quest Information and Learning.

Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2008. / Source: Dissertation Abstracts International, Volume: 69-11, Section: B, page: 6922. Adviser: Jean Ponce. Includes bibliographical references (leaves 127-134) Available on microfilm from Pro Quest Information and Learning.

Thesis (Ph. D.)--University of Toronto, 2008. / Includes bibliographical references.

Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2008. / Source: Dissertation Abstracts International, Volume: 69-11, Section: B, page: 6947. Adviser: Thomas S. Huang. Includes bibliographical references (leaves 117-126) Available on microfilm from Pro Quest Information and Learning.

Thesis (Ph.D.)--Syracuse University, 2008. / "Publication number: AAT 3323077."