No description available.

No description available.

An investigation is conducted into the cognitive effects of using different computer based instructions media in acquisition of specific novel human skills. With recent rapid advances in computing and multimedia instructional delivery, several contemporary research have focussed on the best practices for training and learning delivered via computer based multimedia simulations. More often than not, the aim has been cost minimisation through an optimisation of the instructional delivery process for efficient knowledge acquisition. The outcome of such research effort in general have been largely divergent and inconclusive. The work reported in this thesis utilises a dual prong methodology to provide a novel perspective on the moderating effects of computer based instructional visualisations with a focus on the interaction of interface dynamism with target knowledge domains and trainee cognitive characteristics. The first part of the methodology involves a series of empirical experiments that incrementally measures/compares the cognitive benefits of different levels of instructional interface dynamism for efficient task representation and post-acquisition skilled performance. The first of these experiments utilised a mechanical disassembly task to investigate novel acquisition of procedural motor skills by comparing task comprehension and performance. The other experiments expanded the initial findings to other knowledge domains as well as controlled for potential confounding variables. The integral outcome of these experiments helped to define a novel framework for describing multimodal perception of different computer based instruction types and its moderating effect on post-learning task performance. A parallel computational cognitive modelling effort provided the complementary methodology to investigate cognitive processing associated with different instructional interfaces at a lower level of detail than possible through empirical observations. Novel circumventions of some existing limitations of the selected ACT-R 6.0 cognitive modelling architecture were proposed to achieve the precision required. The ACT-R modifications afforded the representation of human motor movements at an atomic level of detail and with a constant velocity profile as opposed to what is possible with the default manual module. Additional extensions to ACT-R 6.0 also allowed accurate representation of the noise inherent in the recall of spatial locations from declarative memory. The method used for this representation is potentially extendable for application to 3-D spatial representation in ACT-R. These novel propositions are piloted in a proof-of-concept effort followed by application to a more complete, naturally occurring task sequence. The modelling methodology is validated with established human data of skilled task performances. The combination of empirical observations and detailed cognitive modelling afforded novel insights to the hitherto controversial findings on the cognitive benefits of different multimodal instructional presentations. The outcome has implications for training research and development involving computer based simulations.

This thesis evaluates several aspects of the cognitive modeling tools, using a questionnaire as the survey method. We try to assess the the suitability for cognitive modeling task of the cognitive modeling tools, from the perspective of international community of cognitive modeling tool users. Part of this assessment is done with respect to general usability of software and the rest is specialized for the cognitive modeling issues. Frequency and correlation analyses reveal that there is a significant relationship between suitability as a software product and suitability as a cognitive modeling tool. Specifically, there are correlations between the features of the tool involving flexibility, presentation of input and output and the process of design, implementation and evaluation of a cognitive modeling tool, while these processes are negatively related to adversely effecting features of the tool, such as having to do extra tasks that are not related to the actual task. Our study confirms that a cognitive modeling tool can also be evaluated from the perspective of a general purpose software product, and also gives clues about directions for improvement to tool developers.

abstract: Building computational models of human problem solving has been a longstanding goal in Artificial Intelligence research. The theories of cognitive architectures addressed this issue by embedding models of problem solving within them. This thesis presents an extended account of human problem solving and describes its implementation within one such theory of cognitive architecture--ICARUS. The document begins by reviewing the standard theory of problem solving, along with how previous versions of ICARUS have incorporated and expanded on it. Next it discusses some limitations of the existing mechanism and proposes four extensions that eliminate these limitations, elaborate the framework along interesting dimensions, and bring it into closer alignment with human problem-solving abilities. After this, it presents evaluations on four domains that establish the benefits of these extensions. The results demonstrate the system's ability to solve problems in various domains and its generality. In closing, it outlines related work and notes promising directions for additional research. / Dissertation/Thesis / M.S. Computer Science 2011

No description available.

There is a need to have an automated system that can read family history books or other historical texts and extract as many genealogy facts as possible from them. Embley and others have applied traditional information extraction techniques to this problem in a system called OntoES with a reasonable amount of success. In parallel much linguistic theory has been developed in the past decades, and Lonsdale and others have built computational embodiments of some of these theories using Soar. In this thesis we introduce a system called OntoSoar which combines the Link Grammar Parser using a grammar customized for family history texts with an innovative semantic analyzer inspired by construction grammars to extract genealogical facts from family history books and use them to populate a conceptual model compatible with OntoES with facts derived from the text. The system produces good results on the texts tested so far, and shows promise of being able to do even better with further development.

No description available.

Building general purpose autonomous robots that suit a wide range of user-specified applications, requires a leap from today's task-specific machines to more flexible and general ones. To achieve this goal, one should move from traditional preprogrammed robots to learning robots that easily can acquire new skills. Learning from Demonstration (LfD) and Imitation Learning (IL), in which the robot learns by observing a human or robot tutor, are among the most popular learning techniques. Showing the robot how to perform a task is often more natural and intuitive than figuring out how to modify a complex control program. However, teaching robots new skills such that they can reproduce the acquired skills under any circumstances, on the right time and in an appropriate way, require good understanding of all challenges in the field. Studies of imitation learning in humans and animals show that several cognitive abilities are engaged to learn new skills correctly. The most remarkable ones are the ability to direct attention to important aspects of demonstrations, and adapting observed actions to the agents own body. Moreover, a clear understanding of the demonstrator's intentions and an ability to generalize to new situations are essential. Once learning is accomplished, various stimuli may trigger the cognitive system to execute new skills that have become part of the robot's repertoire. The goal of this thesis is to develop methods for learning from demonstration that mainly focus on understanding the tutor's intentions, and recognizing which elements of a demonstration need the robot's attention. An architecture containing required cognitive functions for learning and reproduction of high-level aspects of demonstrations is proposed. Several learning methods for directing the robot's attention and identifying relevant information are introduced. The architecture integrates motor actions with concepts, objects and environmental states to ensure correct reproduction of skills. Another major contribution of this thesis is methods to resolve ambiguities in demonstrations where the tutor's intentions are not clearly expressed and several demonstrations are required to infer intentions correctly. The provided solution is inspired by human memory models and priming mechanisms that give the robot clues that increase the probability of inferring intentions correctly. In addition to robot learning, the developed techniques are applied to a shared control system based on visual servoing guided behaviors and priming mechanisms. The architecture and learning methods are applied and evaluated in several real world scenarios that require clear understanding of intentions in the demonstrations. Finally, the developed learning methods are compared, and conditions where each of them has better applicability are discussed. / Att bygga autonoma robotar som passar ett stort antal olika användardefinierade applikationer kräver ett språng från dagens specialiserade maskiner till mer flexibla lösningar. För att nå detta mål, bör man övergå från traditionella förprogrammerade robotar till robotar som själva kan lära sig nya färdigheter. Learning from Demonstration (LfD) och Imitation Learning (IL), där roboten lär sig genom att observera en människa eller en annan robot, är bland de mest populära inlärningsteknikerna. Att visa roboten hur den ska utföra en uppgift är ofta mer naturligt och intuitivt än att modifiera ett komplicerat styrprogram. Men att lära robotar nya färdigheter så att de kan reproducera dem under nya yttre förhållanden, på rätt tid och på ett lämpligt sätt, kräver god förståelse för alla utmaningar inom området. Studier av LfD och IL hos människor och djur visar att flera kognitiva förmågor är inblandade för att lära sig nya färdigheter på rätt sätt. De mest anmärkningsvärda är förmågan att rikta uppmärksamheten på de relevanta aspekterna i en demonstration, och förmågan att anpassa observerade rörelser till robotens egen kropp. Dessutom är det viktigt att ha en klar förståelse av lärarens avsikter, och att ha förmågan att kunna generalisera dem till nya situationer. När en inlärningsfas är slutförd kan stimuli trigga det kognitiva systemet att utföra de nya färdigheter som blivit en del av robotens repertoar. Målet med denna avhandling är att utveckla metoder för LfD som huvudsakligen fokuserar på att förstå lärarens intentioner, och vilka delar av en demonstration som ska ha robotens uppmärksamhet. Den föreslagna arkitekturen innehåller de kognitiva funktioner som behövs för lärande och återgivning av högnivåaspekter av demonstrationer. Flera inlärningsmetoder för att rikta robotens uppmärksamhet och identifiera relevant information föreslås. Arkitekturen integrerar motorkommandon med begrepp, föremål och omgivningens tillstånd för att säkerställa korrekt återgivning av beteenden. Ett annat huvudresultat i denna avhandling rör metoder för att lösa tvetydigheter i demonstrationer, där lärarens intentioner inte är klart uttryckta och flera demonstrationer är nödvändiga för att kunna förutsäga intentioner på ett korrekt sätt. De utvecklade lösningarna är inspirerade av modeller av människors minne, och en primingmekanism används för att ge roboten ledtrådar som kan öka sannolikheten för att intentioner förutsägs på ett korrekt sätt. De utvecklade teknikerna har, i tillägg till robotinlärning, använts i ett halvautomatiskt system (shared control) baserat på visuellt guidade beteenden och primingmekanismer. Arkitekturen och inlärningsteknikerna tillämpas och utvärderas i flera verkliga scenarion som kräver en tydlig förståelse av mänskliga intentioner i demonstrationerna. Slutligen jämförs de utvecklade inlärningsmetoderna, och deras applicerbarhet under olika förhållanden diskuteras. / INTRO

The field of automated vehicle demands outstanding reliability figures to be matched by the artificially driving agents. The software architectures commonly used originate from decades of automation engineering, when robots operated only in confined environments on predefined tasks. On the other hand, autonomous driving represents an “into the wild” application for robotics. The architectures embraced until now may not be sufficiently robust to comply with such an ambitious goal. This research activity proposes a bio-inspired sensorimotor architecture for cognitive robots that addresses the lack of autonomy inherent to the rules-based paradigm. The new architecture finds its realization in an agent for autonomous driving named “Co-driver”. The Agent synthesis was extensively inspired by biological principles that contribute to give the Co-driver some cognitive abilities. Worth to be mentioned are the “simulation hypothesis of cognition” and the “affordance competition hypothesis”. The former is mainly concerned with how the Agent builds its driving skills, whereas the latter yields an interpretable agent notwithstanding the complex behaviors produced. Throughout the essay, the Agent is explained in detail, together with the bottom-up learning framework adopted. Overall, the research effort bore an effectively performing autonomous driving agent whose underlying architecture provides considerable adaptation capability. The thesis also discusses the aspects related to the implementation of the proposed ideas into a versatile software that supports both simulation environments and real vehicle platforms. The step-by-step explanation of the Co-driver is made up of theoretical considerations supported by working simulation examples, some of which are also released open-source to the research community as a driving benchmark. Eventually, guidelines are given for future research activities that may originate from the Agent and the hierarchical training framework devised. First and foremost, the exploitation of the hierarchical training framework to discover optimized longer-term driving policies.