Physical Sciences and Mathematics Commons^™

Distributed Artificial Intelligence In A Virtual Reality Setting: A Case Study, Rebecca Lohr

Presidential Scholars Theses (1990 – 2006)

Artificial intelligence, or Al, is a fascinating area of research. Al refers to the attempt to create a computer program, known as an intelligent agent, which can "think" and operate in a complex, changing environment. Many problems have been discovered in attempting to develop these intelligent agents, including the simulation of learning, planning, and natural language understanding. While researching these issues, a new branch of Al research has developed. Researchers discovered that there are other problems associated with how intelligent agents work together to solve problems. This field of research has become known as distributed artificial intelligence, or DAI.

Multiple Stochastic Learning Automata For Vehicle Path Control In An Automated Highway System, Cem Unsal, Pushkin Kachroo, John S. Bay

Electrical & Computer Engineering Faculty Research

This paper suggests an intelligent controller for an automated vehicle planning its own trajectory based on sensor and communication data. The intelligent controller is designed using the learning stochastic automata theory. Using the data received from on-board sensors, two automata (one for lateral actions, one for longitudinal actions) can learn the best possible action to avoid collisions. The system has the advantage of being able to work in unmodeled stochastic environments, unlike adaptive control methods or expert systems. Simulations for simultaneous lateral and longitudinal control of a vehicle provide encouraging results

Graded Functional Activation In The Visuo-Spatial System With The Amount Of Task Demand, Patricia Carpenter, Marcel Just, Timothy Keller, William Eddy, Keith Thulborn

Marcel Adam Just

No abstract provided.

Time Course Of Fmri-Activation In Language And Spatial Networks During Sentence Comprehension, Patricia A. Carpenter, Marcel Adam Just, Timothy A. Keller, William F. Eddy, Keith R. Thulborn

Marcel Adam Just

No abstract provided.

Plasticity Of Language-Related Brain Function During Recovery From Strok, Keith R. Thulborn, Patricia A. Carpenter, Marcel Adam Just

Marcel Adam Just

No abstract provided.

Computational Modeling Of High-Level Cognition And Brain Function, Marcel Adam Just, Patricia A. Carpenter, Sashank Varma

Marcel Adam Just

No abstract provided.

Fuzzy Logic Applied To System Control To Enhance Commercial Appliance Performance, Glenn Moffett

Doctoral Dissertations

The purpose of this research is to determine the usefulness of fuzzy logic and fuzzy control when applied to a commercial appliance. Fuzzy logic is a structured, model-free estimator that approximates a function through linguistic input/output associations. Fuzzy rule-based systems apply these methods to solve many types of "real-world" problems, especially where a system is difficult to model, is controlled by a human operator or expert, or where ambiguity or vagueness is common.

This dissertation presents fuzzy sets, fuzzy systems, and fuzzy control, with an example conveying the use of fuzzy control of a consumer product and an overview of …

Singularity Avoidance Strategies For Satellite Mounted Manipulators Using Attitude Control, Nathan A. Titus

Theses and Dissertations

Control concepts for satellite mounted manipulators (SMM) are examined. The primary focus is on base actuated concepts, which eliminate singularity problems associated with free floating SMMs. A new form of the equations of motion for an n-link SMM is developed using a quasi coordinate form of Lagrange's Equation. Alternative free floating SMM designs are presented which eliminate dynamic singularities, but still experience difficulties due to the unactuated base. A new generic SMM controller is developed as a framework for various control concepts with and without base actuation. Momentum constrained Jacobians are shown to produce better SMM tracking than fixed base …

Study Of Human Factors Variables In Battle Outcome Prediction Models, David Andrew Glovier

Engineering Management & Systems Engineering Theses & Dissertations

Over time there have been many improvements in models that are used to predict the outcome of battles. Currently there is much supposition and speculation surrounding the use of human performance related factors as additional inputs to battle simulation models to improve their accuracy. However there is no conclusive scientific evidence which shows that these factors do make a significant difference. This study investigates the use of factors that may impact on the human performance directly or indirectly in battle prediction models. These factors consist of traditional human factors and external factors that may influence the human performance. The research …

Starcraft - Maps & Benchmark Problems, Nathan R. Sturtevant, Blizzard Corp.

Moving AI Lab: 2D Maps and Benchmark Problems

Maps extracted from Starcraft from Blizzard Corp. for use and distribution as benchmark problems.

Contains 75 maps and benchmark problem sets, converted to standard format by Dave Churchill and post-processed to remove all but the largest connected component.

Robots In The Undergraduate Curriculum, D. Kumar, Lisa A. Meeden

Computer Science Faculty Works

No abstract provided.

Design And Design Centers In Engineering Education, Clive L. Dym

All HMC Faculty Publications and Research

This paper is intended to be the opening salvo of the workshop, Computing Futures in Engineering Design (Dym, 1997). Thus, I want to take this privileged moment to ask you to think with me about the role of design in engineering. In particular, I want to reflect upon how design is articulated and how design is taught; about the role of design in engineering education and in the practice of engineering; and about the role that could be played locally and, perhaps, nationally by a center devoted to design education. Because I teach here at Harvey Mudd College (HMC), …

Virtual Reality Modelling Of A Cnc Machine, Damian O'Sullivan

Theses

The increasing importance of training and upgrading skills has led to the use of new interactive technologies in the development of more effective training tools. Previous techniques for training Computer Numerical Control (CNC) machine operators, while excellent for their time, varied from brief inexpensive tutorials to expensive on the job training. A CNC machine uses a computer to perform the functions of the machine using a part program stored in the memory of the computer. This thesis describes a Virtual Reality (VR) model of a CNC milling machine, implemented within a VR environment representing a CNC workshop. Its development and …

Dynamic Control Models As State Abstractions, Jefferson A. Coelho, Roderic Grupen

Roderic Grupen

This work proposes a methodology for the construction of state abstraction from a set of empirically derived models of system behavior. The idea is to treat the agent in its environment as a dynamical system and augment its observation space with contextual cues extracted empirically as the agent exercises each element out of the set of available control policies--the control bias. Contextual cues are provided by the correlation between dynamic features of the agent-environment interaction and agent performance. The resulting state abstraction (observations + context information) defines also a temporal abstraction, and offers interesting answers to some of the issues …

Learning To See Analogies: A Connectionist Exploration, Douglas S. Blank

Computer Science Faculty Research and Scholarship

The goal of this dissertation is to integrate learning and analogy-making. Although learning and analogy-making both have long histories as active areas of research in cognitive science, not enough attention has been given to the ways in which they may interact. To that end, this project focuses on developing a computer program, called Analogator, that learns to make analogies by seeing examples of many different analogy problems and their solutions. That is, it learns to make analogies by analogy. This approach stands in contrast to most existing computational models of analogy in which particular analogical mechanisms are assumed a priori …

Simulation Study Of Learning Automata Games In Automated Highway Systems, Cem Unsal, Pushkin Kachroo, John S. Bay

Electrical & Computer Engineering Faculty Research

One of the most important issues in Automated Highway System (AHS) deployment is intelligent vehicle control. While the technology to safely maneuver vehicles exists, the problem of making intelligent decisions to improve a single vehicle’s travel time and safety while optimizing the overall traffic flow is still a stumbling block. We propose an artificial intelligence technique called stochastic learning automata to design an intelligent vehicle path controller. Using the information obtained by on-board sensors and local communication modules, two automata are capable of learning the best possible (lateral and longitudinal) actions to avoid collisions. This learning method is capable of …

A Control Basis For Learning Multifingered Grasps, Jefferson Coelho, Roderic Grupen

Roderic Grupen

In this paper, we introduce a robust controller that uses contact position and normal feedback to generate contact configurations for statically stable grasps. The approach uses a context sensitive composition of two controllers that minimize force and moment residuals in the grasp configuration. We show that equilibria in the composite controller correspond to optimal contact configurations for 2 and 3 contacts on regular, convex polygons. The preimage is used to generalize the controller to arbitrary object geometries by learning a policy for compensation and to address object recognition, and contact (de)allocation.

Velocity Estimation Via A Neural Network Enhanced By Classical Detection Algorithms, Zeki Berk Hamşioğlu

Electrical & Computer Engineering Theses & Dissertations

The goal of this research is to show how to solve a velocity estimation problem using a neural network connected to an array of sensors. Motivated by biological studies involving insect vision, the neural network utilized is a member of a class of shunting neural networks. When an object moves across the face of the sensor array, the neural network's pulse response is first temporally located using classical M-ary detection techniques. Both the deterministic and stochastic cases are considered. Then the network's pulse response is post-processed via an existing velocity estimation algorithm based on a Volterra series model of the …

A Synthesized Methodology For Eliciting Expert Judgment For Addressing Uncertainty In Decision Analysis, Richard W. Monroe

Engineering Management & Systems Engineering Theses & Dissertations

This dissertation describes the development, refinement, and demonstration of an expert judgment elicitation methodology. The methodology has been developed by synthesizing the literature across several social science and scientific fields. The foremost consideration in the methodology development has been to incorporate elements that are based on reasonable expectations for the human capabilities of the user, the expert in this case.

Many methodologies exist for eliciting assessments for uncertain events. These are frequently elicited in probability form. This methodology differs by incorporating a qualitative element as a beginning step for the elicitation process. The qualitative assessment is a more reasonable way …

Autonomous Construction Of Multi Layer Perceptron Neural Networks, Thomas F. Rathbun

Theses and Dissertations

The construction of Multi Layer Perceptron (MLP) neural networks for classification is explored. A novel algorithm is developed, the MLP Iterative Construction Algorithm (MICA), that designs the network architecture as it trains the weights of the hidden layer nodes. The architecture can be optimized on training set classification accuracy, whereby it always achieves 100% classification accuracies, or it can be optimized for generalization. The test results for MICA compare favorably with those of backpropagation on some data sets and far surpasses backpropagation on others while requiring less FLOPS to train. Feature selection is enhanced by MICA because it affords the …

A Feedback Control Structure For On-Line Learning Tasks, Manfred Huber, Roderic Grupen

Roderic Grupen

This paper addresses adaptive control architectures for systems that respond autonomously to changing tasks. Such systems often have many sensory and motor alternatives and behavior drawn from these produces varying quality solutions. The objective is then to ground behavior in control laws which, combined with resources, enumerate closed-loop behavioral alternatives. Use of such controllers leads to analyzable and predictable composite system, permitting the construction of abstract behavioral models. Here, discrete event system and reinforcement learning techniques are employed to constrain the behavioral alternatives and to synthesize behavior on-line. To illustrate this, a quadruped

Learning To Coordinate Controllers -- Reinforcement Learning On A Control Basis, Manfred Huber, Roderic Grupen

Roderic Grupen

Autonomous robot systems operating in an uncertain environment have to be reactive and adaptive in order to cope with changing environment conditions and task requirements. To achieve this, the hybrid control architecture presented in this paper uses reinforcement learning on top of a Discrete Event Dynamic System (DEDS) framework to learn to supervise a set of basis controllers in order to achieve a given task. The use of an abstract system model in the automatically derived supervisor reduces the complexity of the learning problem. In addition, safety constraints may be imposed a priori, such that the system learns on-line in …

Expert System For The Generation Of A Work Breakdown Structure, Bernard O'Callaghan

Theses

This thesis outlines research work carried out in the Mechanical & Manufacturing Department in Cork Regional Technical College, Ireland. With computers now having an increasingly dominant role in all areas of business, it was inevitable that computer-based project management packages would become more popular. To date however, these packages have concentrated on monitoring and controlling projects. The definition and brainstorming phases required to generate a project plan are still largely manual tasks. Planning a project initially involves generating a complete and organised list of all the tasks needing to be completed in order to achieve a project’s goal. This list …

The "Hoover" Project: Home Occupants Vehicular Electronic Reconnaissance, Kelvin Chan

SWITCH

The article explains telepresence, as well as its potential in safety and security, along with its traditional usage of traversing dangerous situations. This article describes a dystopian plan to place drones equipped with cameras and microphones in all homes in the Silicon Valley as a vehicle for telepresence. The data achieved through this method would also be stored into a public domain browser on the internet, free for anyone in the public to view, including larger corporations and the government. The idea behind this is the assimilation of data behind all cultures for understanding and to assist law enforcement in …

The Toysim Project, Anthony Rodriguez

Theses : Honours

No abstract provided.

Software Reuse: Architecture, Process And Organization For Business Success, Ivar Jacobson, Martin Griss, Patrik Jonsson

Martin L Griss

No abstract provided.

Aphasic Sentence Comprehension As A Resource Deficit: A Computational Approach, Henk J. Haarmann, Marcel Adam Just, Patricia A. Carpenter

Marcel Adam Just

No abstract provided.

Neural Network Classification Of Environmental Samples, Jeffrey L. Blackmon

Theses and Dissertations

This research develops a general methodology for designing neural network classifiers for real-world environmental problems. This methodology is demonstrated through the design of a multi-layer perceptron to classify stainless steel and actinide samples. Neural networks, sometimes called artificial neural networks, have been shown capable of classifying complex patterns. Artificial neural networks are physiologically motivated computer algorithms which attempt to mimic the function of the large interconnected network of neurons in the human brain, which has extraordinary pattern recognition capabilities. These artificial neural networks learn to map a set of input features, elemental composition, onto a set of outputs such as …

Development Of Object-Based Teleoperator Control For Unstructured Applications, Hyunki Cho

Theses and Dissertations

For multi-fingered end effectors in unstructured applications, the main issues are control in the presence of uncertainties and providing grasp stability and object manipulability. The suggested concept in this thesis is object based teleoperator control which provides an intuitive way to control the robot in terms of the grasped object and reduces the operator's conceptual constraints. The general control law is developed using a hierarchical control structure, i.e., human interface I gross motion control level in teleoperation control and fine motion control/object grasp stability in autonomous control. The gross motion control is required to provide the position/orientation of the Super …

Exploring Knowledge Processes For Technology Assimilation, Rochelle K. Young

Engineering Management & Systems Engineering Theses & Dissertations

In the emerging knowledge society, the ability to make the experience and expertise of those involved in and affected by new technology unconditionally available to all members of an organization is becoming increasingly important. One of the problems in developing such knowledge processes for technology assimilation is that current social structures do not easily accommodate unconditional participation. Since the implementation of modern information technology is changing the workplace and the nature of work itself, alternative social structures are needed. This research takes as given that deep questions concerning knowledge processes and social transformation are in principle undecidable; and, only questions …