School of Interactive Computing Theses and Dissertations
The College of Computing formed the School of Interactive Computing in 2007. SIC has taken the initiative in creating new, more effective techniques and practices for computing education. At the doctoral level, we led in the development of a Ph.D. in robotics; we’ve led a national trend in offering a Ph.D. in human-centered computing; and we participate fully in the College’s Ph.D. in computer science.
All materials in SMARTech are protected under U.S. Copyright Law and all rights are reserved. Such materials may be used, quoted or reproduced for educational purposes only with prior permission, provided proper attribution is given. Any redistribution, reproduction or use of the materials, in whole or in part, is prohibited without prior permission of the author.
Recent Submissions
-
Improved search techniques for structured prediction
(Georgia Institute of Technology, 2020-07-29)Many useful AI tasks like machine translation, captioning or program syn- thesis to name a few can be abstracted as structured prediction problems. For these problems, the search space is well-defined but extremely large ... -
Search-based collision-free motion planning for robotic sculpting
(Georgia Institute of Technology, 2020-07-28)In this work, I explore the task of robot sculpting. I propose a search-based planning algorithm to solve the problem of sculpting by material removal with a multi-axis manipulator. I generate collision free trajectories ... -
Measuring the effect of user experience and engagement on learning using interactive simulations
(Georgia Institute of Technology, 2020-07-21)Previous studies have explored the best methods to measure emotional, cognitive, and physical engagement, but these methods have not been applied to fully understand the impact of multimodal interactive simulations on ... -
Human-guided task transfer for interactive robots
(Georgia Institute of Technology, 2020-07-06)Adaptability is an essential skill in human cognition, enabling us to draw from our extensive, life-long experiences with various objects and tasks in order to address novel problems. To date, robots do not have this kind ... -
Digital self-harm: Implications of eating disordered behaviors online
(Georgia Institute of Technology, 2020-07-21)It is estimated that 10%-20% of the US population will struggle with an eating disorder at some point in their lifetime [258]. Eating disorders is a complex set of psychiatric disorders that, regardless of classification, ... -
Efficient trajectory and policy optimization using dynamics models
(Georgia Institute of Technology, 2020-07-22)Data-driven approaches hold the promise of creating the next wave of robots that can perform diverse tasks and adapt to unstructured environments. However, gathering data of physical systems is often a labor-intensive, ... -
Designing collaborative mobile health experiences for adolescent patients
(Georgia Institute of Technology, 2020-05-17)The proliferation of patient-generated data and mobile health (mHealth) technologies has provided unprecedented opportunities for patients' everyday health management and active participation in health care. Designing and ... -
Low-shot learning for object recognition, detection, and segmentation
(Georgia Institute of Technology, 2020-05-17)Deep Neural Networks are powerful at solving classification problems in computer vision. However, learning classifiers with these models requires a large amount of labeled training data, and recent approaches have struggled ... -
Detecting and mitigating human bias in visual analytics
(Georgia Institute of Technology, 2020-05-17)People are susceptible to a multitude of biases, including perceptual biases and illusions; cognitive biases like confirmation bias or anchoring bias; and social biases like racial or gender bias that are borne of cultural ... -
Grasp contact between hand and object: Capture, analysis, and applications
(Georgia Institute of Technology, 2020-05-13)Contact is an important but often oversimplified component of human grasping. Capturing hand-object contact in detail can lead to important insights about grasping behavior, and enable applications in diverse fields like ... -
LEARNING TO WALK USING DEEP REINFORCEMENT LEARNING AND TRANSFER LEARNING
(Georgia Institute of Technology, 2020-05-17)We seek to develop computational tools to reproduce the locomotion of humans and animals in complex and unpredictable environments. Such tools can have significant impact in computer graphics, robotics, machine learning, ... -
Visualization by Demonstration
(Georgia Institute of Technology, 2020-05-05)A key component of visualization systems that helps human sensemaking is interactivity. Thoughtfully designed interactions make the visual analysis process a conversation between the user and the interface that results in ... -
Autonomous Rally Racing with AutoRally and Model Predictive Control
(Georgia Institute of Technology, 2019-07-30)The ability to conduct experiments in the real world is a critical step for roboticists working to create autonomous systems that achieve human-level task performance. Self-driving vehicles are a domain that has received ... -
Modeling Human and Robot Behavior During Dressing Tasks
Human dressing assistance tasks present a multitude of privacy, safety, and independence concerns for the daily lives of a vast number of individuals across the world, providing strong motivation for the application of ... -
Encoding 3D contextual information for dynamic scene understanding
(Georgia Institute of Technology, 2020-04-27)This thesis aims to demonstrate how using 3D cues improves semantic labeling and object classification. Specifically, we will consider depth, surface normals, object classification, and pixel-wise semantic labeling in this ... -
Policy-based exploration for efficient reinforcement learning
(Georgia Institute of Technology, 2020-04-25)Reinforcement Learning (RL) is the field of research focused on solving sequential decision-making tasks modeled as Markov Decision Processes. Researchers have shown RL to be successful at solving a variety of problems ... -
Disentangling neural network representations for improved generalization
(Georgia Institute of Technology, 2020-04-24)Despite the increasingly broad perceptual capabilities of neural networks, applying them to new tasks requires significant engineering effort in data collection and model design. Generally, inductive biases can make this ... -
Advanced machine learning approaches for characterization of transcriptional regulatory elements and genome-wide associations
(Georgia Institute of Technology, 2020-03-20)The deep learning revolution has initiated a surge of remarkable achievements in diverse research areas where large volumes of data that underlie complex processes exist. Despite the successful application of deep models ... -
Identifying opportunities to improve content moderation
(Georgia Institute of Technology, 2020-03-18)This thesis contributes a nuanced understanding of the challenges inherent in the design and implementation of fair and efficient content moderation systems. Using large-scale data analyses, participant observations, survey ... -
Building agents that can see, talk, and act
(Georgia Institute of Technology, 2020-04-25)A long-term goal in AI is to build general-purpose intelligent agents that simultaneously possess the ability to perceive the rich visual environment around us (through vision, audition, or other sensors), reason and infer ...
RSS 1.0