Browsing by Author "Dr. Robert St. Amant, Committee Chair"

Now showing 1 - 7 of 7

Augmented Reality as a Perceptual Aid in Robot Teleoperation
(2007-02-28) Boyce, Curtis Wesley; Dr. Robert St. Amant, Committee Chair; Dr. R. Michael Young, Committee Member; Dr. Chrsitopher G. Healey, Committee Member
Robots have reached a level of sophistication such that it is now productive to include robot-assisted search teams in urban search and rescue scenarios. The perceptual interface to the human operator is frequently a video display that relays images from a camera on the robot. Research into issues surrounding human-robot interaction has suggested that if more intelligence were placed on the robot, it could lessen the load on the human operator and improve performance in the search task. In this thesis we examine the relative performance in a search task where the robot is controlled by a remote human operator under different simulated environmental conditions. Three distinct environmental conditions are represented by: a nominal display from the robot's camera, an artificially degraded display (representing signal interference) of the same information, and an augmented display of the degraded information, in which object recognition algorithms enable the application of a visual overlay to identify a search target. Results show that reduced performance under the degraded condition can be improved to near the nominal level by this augmentation method.
Coglaborate - An Environment For Collaborative Cognitive Modeling
(2009-11-24) Cornel, Reuben Francis; Dr. James Lester, Committee Member; Dr. Christopher Healey, Committee Member; Dr. Robert St. Amant, Committee Chair
Cognitive scientists who build computational models of their work, as exemplified by the ACT-R and Soar research communities, have limited means of sharing knowledge: annual conferences and workshops, summer schools, and model code distributed via Web sites. The consequence is that results obtained by different groups are scattered across the Internet, making it difficult for researchers to obtain a comprehensive view of cognitive modeling research. The goal of my project is to develop a collaborative modeling environment for cognitive scientists in which they can develop and share models. The current system supports collaboration by providing a structured representation for ACT-R cognitive models using frames. The rationale for providing a structured representation for cognitive models is two-fold: it not only provides a mechanism for sharing models (i.e. via consistent APIs); it also enables the application of analytical techniques to cognitive models. As a proof of concept for the approach, a medium-scale modeling application has been developed, integrating an extension of ACT-R developed elsewhere, to solve synonym crossword puzzles.
Data Organization and Abstraction for Distributed Intrusion Detection
(2005-04-06) McBride, Sean Patrick; Dr. Christopher G. Healey, Committee Member; Dr. Robert St. Amant, Committee Chair; Dr. Laurie Williams, Committee Member
Due to the rapid pace of technological development, we find that old systems are 'thrown away' in favor of newer technology. However, we find that data created by these earlier systems is persistent. A Digital Rosetta Stone [16] must be created to allow newer systems to correctly process data created by earlier technology. This document provides a case study of techniques that can be used to create a Digital Rosetta Stone between data formats and within a single evolving format. The intrusion detection domain provides a solid basis for this study. In a distributed intrusion detection system, many sensors and analyzers must communicate with each other. The Intrusion Detection Message Exchange Format (IDMEF) is a standardized XML format for such communication. To its detriment, the IDMEF specification has been evolving since its inception. Also, the XML parsing during queries can be cumbersome and hinder intrusion detection. Therefore, two Digital Rosetta Stones were created. One migrates information between different versions of the IDMEF standard. The other translates IDMEF XML information into a relational database management system to improve query performance.
Image Processing for Cognitive Models in Dynamic Gaming Environments
(2003-07-07) Shah, Kunal Deepak; Dr. Robert St. Amant, Committee Chair; Dr. Michael Young, Committee Member; Dr. Munindar Singh, Committee Member
Cognitive models have typically dealt with environments that are either artificial or real but too simplistic. This stems from the fact that the process of describing the environment to the cognitive model is a complex vision problem. In order to realize the full potential of cognitive models, it is imperative that they be able to operate in natural domains. We attempt to overcome this limitation by providing a perceptual component to a cognitive model that interacts with more realistic environments. This perceptual component is an image processing substrate that has been customized for two different gaming environments. The substrate formerly worked only for the static environments we associate with conventional graphical user interfaces; the work we describe here extends its functionality to a more general class of interfaces, as represented by the driving game and Mars rover game. A cognitive model built on the ACT-R cognitive architecture has been developed that demonstrates the use of the image processing substrate in performing the driving task.
Image Processing Substrate to Assist Cognitive Models Interact with Dynamic Environments
(2003-08-18) Rajyaguru, Sameer Rajendra; Dr. R. Michael Young, Committee Member; Dr. James Lester, Committee Member; Dr. Robert St. Amant, Committee Chair
Cognitive models have typically dealt with artificial environments or real environments that are simple. This is because the cognitive models either use indirect approaches to interact with environments, or in cases where they adopt direct approaches to interact, the image processing substrate is incapable of dealing with complex interfaces. However, it is imperative for cognitive models to interact directly with complex environments in order to ascertain the reliability of the underlying cognition theory. The image processing substrate proposed in this thesis overcomes the above-mentioned limitations and enables cognitive models to interact directly with complex environments. This is due to the functionality provided by the substrate that facilitates representation and identification of complex visual patterns. As part of the research work for this thesis, the substrate has been customized to process two interfaces and a cognitive model has also been built on the ACT-R cognitive architecture that uses the proposed substrate to control a driving game environment.
Incorporating Student Note-Taking into Online Computer-Assisted Instruction
(2008-04-24) Damm, Kevin Blake; Dr. Robert St. Amant, Committee Chair; Dr. James C. Lester, Committee Member; Dr. Donald L. Bitzer, Committee Member; Dr. Christopher Healey, Committee Member
User Interface Softbots
(2003-12-11) Dudani, Ajay; Dr. Munindar Singh, Committee Member; Dr. Michael Young, Committee Member; Dr. Robert St. Amant, Committee Chair
A user interface softbot is a software agent that controls an interactive system through its graphical user interface, relying on visual information of the system rather than an application programming interfaces or access to source code. We have developed a prototype system that facilitates the use and extension of interface softbots, reforming the programming process and making it easier for new developers. We present the JSegMan substrate that facilitates the representation and identification of the conventional graphical user interface. The JSegMan substrate consists of sensors, effectors and framework for an agent that can control the user interface environment. Using image processing the sensor builds a representation of the desktop's visual interface. The effector module generates mouse and keyboard gestures to control the desktop environment. The sensor and effector modules work as eyes and hands of a controller application that can be tailored for a given application domain. We also present three applications - MSN Chatbots, the classical Blocks World problem solver and a GUI testing tool that use the JSegMan substrate and demonstrates applicability of JSegMan in use with off-the shelf applications, PDDL based planners and in testing environment respectively.