Research and scholarship are a vital part of the GAMMA Program’s mission. Researchers from the Computer Science Department explore, discover and innovate new technological advances in the field of computing. The impact of the GAMMA Program’s research has the potential to influence game and mobile development studios in Texas and around the world, as well as provide benefits to the general population.
The focus of UT’s research on game technology are:
- Games for Good (Beyond Just Entertainment)
- Gaming with Artificial Intelligence
- Graphics and Visualization
- Tools for Game Development/Education
Games for Good (Beyond Just Entertainment)
The GAMMA Program is working with the College of Education’s Learn Technologies Program on the continued development of Alien Rescue, a design research project. Alien Rescue is an online problem-based 3D game-like learning environment for sixth-grade science. It combines best practices from educational research with innovative technologies to deliver an engaging learning experience.
Kinect Games for Teaching Social Interaction Skills for Autistic Children
Jason Brown is developing games that seek to be helpful in improving social interaction skills among autistic children. The below videos are a proof of concept in exploring the capabilities of the Microsoft Kinect.
- Kinect Games for Teaching Social Interaction Skills for Autistic Kids (YouTube)
- Kinect Prototype: Mimic Game Commentary 1 (YouTube)
- Kinect Prototype: Bee Game Commentary 1 (YouTube)
Gaming with Artificial Intelligence
Games constitute an effective platform for developing and testing artificial intelligence techniques: they are well defined and easy to implement, yet challenging and fun. Research in this area involves learning to play traditional games such as Othello and Go, on learning general game playing and on developing intelligent behaviors for non-player characters in video games. Learn more. Below are descriptions of three major AI initiatives in games: General Game Playing, The Open NERO Project and Robot Soccer.
General Game Playing
Most successful game-playing programs, such as the famous chess-playing program Deep Blue, are highly engineered to play a specific game. The challenge of General Game Playing is creating programs that can play new, previously unseen games mainly by analyzing the rules and possibly through small amounts of practice. Learn more.
OpenNERO AI Research and Education Platform
A general research and education platform for artificial intelligence (AI) called OpenNERO will be built. The platform is based on a sophisticated simulation and graphical display of a 3D physical world, including multiple agents with embedded sensors and effectors, multiple objects, together with GUIs for manipulating the environment and the agents. Using the existing NERO game as a starting points, our goals are to (1) implement the game entirely with open-source software, (2) extend it to more general physical and communicative interactions among the agents and the agents and the environment, (3) build tools for the user to construct new environments, tasks and AI methods, and to visualize the behaviors and analyze performance statistically, and (4) implement and demonstrate a number of AI techniques, such as search, vision and supervised and reinforcement learning. The resulting OpenNERO software environment will allow developing and testing new AI methods as well as demonstrating existing methods in a sophisticated and concrete simulation of the physical world. Learn more.
The Learning Agents Research Group (LARG) uses robot soccer extensively as a testbed domain for multiagent systems, machine learning, robotics and autonomous agents. We compete and WIN regularly in the annual RoboCup. You can Google “UT Austin Wins RoboCup” to verify! Our latest win was RoboCup 2015. Some of our research uses real robots, and some is in simulation. Learn more.
Graphics and Visualization
Evolved Virtual Creatures
Dan Lessin, a UT Ph.D. student, is currently working on evolved virtual creatures, i.e. constructing believable content for virtual environments. His approach is called ESP for Encapsulation of behaviors, a Syllabus for training them, and Pandemonium of selecting between them. The idea is to evolve both the morphology (including muscles) and the control simultaneously.
- Adapting Morphology to Multiple Tasks in Evolved Virtual Creatures
- Open-Ended Behavioral Complexity for Evolved Virtual Creatures
- Trading Control Intelligence for Physical Intelligence: Muscle Drives in Evolved Virtual Creatures
Fluid-Based Brush Systems for Novel Digital Media
Sarah Abraham, Ph.D., did her dissertation on Non-Photorealistic Rendering, which covers a wide range of visual effects. Much of the work was dedicated to creating digital representations of traditional media — either through artist controls or programmatically. It explored a variation of this work, which creates digital media using the metaphors of traditional media but applying them in ways that have no physical equivalent. This expands current notions of what digital media can represent. The Smoke Brush system is an interface for applying smoke-like brush strokes to a digital canvas. Using Smoke Brush, artists can add animated, constrained smoke effects to existing pictures or create images represented entirely by smoke. Smoke Brush produces artifacts realized as animated GIFs (a commonly available digital format used in cinemagraphs) that loop in a smooth continuous motion that is faithful to the original artist input. Based on this existing work, she intended to expand this system to include more variety of paintable fluid effects. We ideally can do this by modifying the underlying velocity field of our existing fluid simulation, while also including a higher level of artistic control based on brush movements. Learn more about Sarah and her Educational Games research at Akula Games.
Frankenrigs is a new rigging and skinning method that uses a database of partial rigs extracted from a set of source characters. Given a target mesh and a set of joint locations, the system can automatically scan through the database to find the best-fitting body parts, tailor them to match the target mesh and transfer their skinning information onto the new character. For the cases where our automatic procedure fails, the system provides an intuitive set of tools to fix the problems. When used fully automatically, the system can generate results of much higher quality than a standard smooth bind, and with some user interaction, it can create rigs approaching the quality of artist-created manual rigs in a small fraction of the time.
Texas Advanced Computing Center Vislab
To support the world-class research being performed on our high-performance computing systems, Texas Advanced Computing Center provides the Visualization Laboratory (Vislab). The Vislab serves as a research hub for human-computer interaction, tiled display software development and visualization consulting. The Vislab encompasses both hardware and software and includes Stallion, among the highest resolution tiled displays in the world; Longhorn, the largest hardware accelerated, remote, interactive visualization cluster; and the Longhorn Visualization Portal, an Internet gateway to the Longhorn cluster and an easy-to-use interface for scientific visualization. The Vislab serves as a research hub for human-computer interaction, tiled display software development and visualization consulting.
Tools for Game Development/Education
Currently, the GAMMA Program is performing research on tools to improve the game development process and tools to teach game design and development to student. Check back in the future for more details.
If you wish to conduct further research within the GAMMA Program, please contact Paul Toprac.