Projects

This is a collaboration with our industry partner The Home Depot seeking to optimize the current curbside process from the associate perspective.
The internet, mobile, and social media technologies have been successful in connecting large segments of the world's population, generating wide access to global networks of information. There are several clusters of unconnected/under-connected populations across the world, however, who do not have access due to financial, social, or political limitations.
Juvenile idiopathic arthritis (JIA) is the most common cause of chronic childhood arthritis, affecting 1 in 1000 children.
This project aims to ensure that the dignity of a Parkinson's patient is maintained during interactions with caregivers using a robot as a co-mediator. The mediator will hold a mental representation of the patient's and caregiver's emotional state and react accordingly. The co-mediator will express the patient's internal emotional state through spatial and emotive gestures.
We are creating a platform for experiencing room-scale augmented reality through head-mounted displays. Prototypes will involve various tracking methods to interpret the user's gestures and movements.

ROOTS

Lab: 
The Responsive Objects, Surfaces, and Spaces (ROSS) API is a way for tangible applications to operate seamlessly across a variety of tangible input devices and platforms. It allows applications to exchange information about the devices they are running on and obtain real-time data about tangible and touch interactions with other devices. In a ROSS world, you can use your mobile phone as a controller to play games on the digital coffee table in your living room; and your guests can join in with their phones too.
Large, multisensor datasets are available covering a large portion of Mars. Analysis and display of these datasets are currently in use for path planning tools that provide a precise, low-level visualization that fosters precision planning for Rover Planners at NASA Jet Propulsion Laboratory. However, these visualizations do not foster path planning at a higher level of abstraction. In addition, planning a path uses a non-intuitive process of generating rover commands, simulating them, visualizing the results, and then tweaking the commands until the path looks correct.
Spatio-temporal data is often displayed using regional aggregation or heatmaps, which are useful for exploring large distributed trends or working to unearth the cause of more localized behavior. For individual users that live and work in the region, however, these representations are inaccessible and difficult to put into practice. We present a new technique for exploring spatio-temporal data as personal routes through a geographic area.
Pedestrians are the largest group of road-users and they represent a large proportion of road casualties. The researchers have found some evidence that divided attention disrupts walking; making people less likely to notice novel stimuli and more likely to cross a street in a risky fashion. More than 1,500 pedestrians were estimated to be treated in emergency rooms in 2010 for injuries related to using a cell phone while walking, according to a new nationwide study.
Due to the physical and spatial disconnect, online learners frequently experience social isolation that negatively impacts students' well-being and learning experiences. We present an AI agent named SAMI (stands for Social Agent Mediated Interaction) that can read and analyze online learners' self-introduction posts on the class discussion forum to connect students with similar interests together. In the poster, we describe how SAMI works and what the online learners think of SAMI. We then discuss the potential of human-AI interaction research under the theoretical framework of Mutual Theory o
Recently featured in Georgia County Government magazine, the SayWhyPoll mobile app enables elected officials, civic leaders, and media producers to engage with constituents and audiences either remotely or face-to-face using surveys that tightly couple close-ended survey items with rich media, such as video. The SayWhyPoll is designed to increase opportunities for public debate on civic issues, but is also suitable for pure entertainment topics, such as sports and lifestyle.
SCADE is a visual text analytic tool. The goal of the project is to help analysts make sense of a larger number of text document while tracking the analyst's provenance.
Story generation is the problem of automatically selecting a sequence of events that meet a set of criteria and can be told as a story. Story generation is knowledge-intensive; traditional story generators rely on a priori defined domain models about fictional worlds, including characters, places, and actions that can be performed. Manually authoring the domain models is costly and thus not scalable. We present a novel class of story generation system--called an Open Story Generator--that can generate stories about any topic.
We are working with Atlanta Public Schools (APS) to design a school bus information system that streamlines communication between parents, school administrators, and APS. Parents are empowered with pertinent information like late buses and substitute drivers, so they can know when the bus is coming and when it has safely arrived at school. With relevant bus tracking information and the ability to send announcements, the tool helps schools manage their morning arrival and afternoon dismissal processes.

Pages