Sporty Robots Advance Artificial Intelligence

Improving decision-making skills in robots using physical situations

Artificial intelligence in the 21st Century is no longer a mere subject of sci-fi fantasy - robots are real and are here to stay.  Dr. Stone and his research team at The University of Texas at Austin, are at the forefront of artificial intelligence.  From autonomous cars that can safely navigate busy traffic intersections and motorways, to robots that work together on a team to compete with other robots in competitive soccer tournaments, Dr. Stone is the robot man.

 

 
  • Dr Stone is the founder and team leader of the UT Austin Villa robot soccer teams at The University of Texas at Austin.  Dr. Stone is also the Vice President of the RoboCup Federation.

  • Within the robot soccer domain, he is studying reinforcement learning which enables a team of autonomous robots to cooperate with each other and successfully compete on the soccer field.

  • Dr. Stone invented "Autonomous Intersection Management" which is a scalable, safe, and efficient multiagent framework for managing autonomous vehicles at intersections.

The impact of artificial intelligence is ultimately boundless. Dr. Stone's research produces complete, robust, autonomous agents that can learn to interact with other intelligent agents in a wide range of complex, dynamic environments. Dr. Stone has proven this through his multifaceted research endeavors and he believes that general purpose robots will soon be in a store near you.   

Bio

Dr. Peter Stone is an Alfred P. Sloan Research Fellow, Guggenheim Fellow, AAAI Fellow Fulbright Scholar, and University Distinguished Teaching Professor in the Department of Computer Science at the University of Texas at Austin.

He received his Ph.D. in 1998 and his M.S. in 1995 from Carnegie Mellon University, both in Computer Science.

He received his B.S. in Mathematics from the University of Chicago in 1993. From 1999 to 2002 he was a Senior Technical Staff Member in the Artificial Intelligence Principles Research Department at AT&T Labs - Research.

Prof. Stone's research interests include planning, machine learning, multiagent systems, robotics, and e-commerce.

Application domains include robot soccer, autonomous bidding agents, traffic management, and autonomic computing.

His doctoral thesis research contributed a flexible multiagent team structure and multiagent machine learning techniques for teams operating in real-time noisy environments in the presence of both teammates and adversaries.

He has developed teams of robot soccer agents that have won six robot soccer tournaments (RoboCup) in both simulation and with real robots.

He has also developed agents that have won four auction trading agent competitions (TAC). Prof. Stone is the author of "Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer" (MIT Press, 2000) as well as a co-author of "Autonomous Bidding Agents: Strategies and Lessons from the Trading Agent Competition" (MIT Press, 2007).

In 2003, he won a CAREER award from the National Science Foundation for his research on learning agents in dynamic, collaborative, and adversarial multiagent environments.

In 2004, he was named an ONR Young Investigator for his research on machine learning on physical robots.

In 2007, he was awarded the prestigious IJCAI Computers and Thought award, given once every two years to the top AI researcher under the age of 35.

In 2013 he was awarded the University of Texas System Regents' Outstanding Teaching Award and in 2014 he was inducted into the UT Austin Academy of Distinguished Teachers.

 

In the News

The Robots Are Coming!

Welcome to robot soccer. It's an intensely competitive game that tests advanced programming skills, and UT is really, really good at it

Disruptions: How Driverless Cars Could Reshape Cities

While driverless cars might still seem like science fiction outside the Valley, the people working and thinking about these technologies are starting to ask what these autos could mean for the city of the future. The short answer is "a lot"

Driverless Cars Get California License

Cars have gained a measure of autonomy in California. An effort spearheaded by Google to improve road safety by taking the human element out of the equation resulted in a new law that allows driverless cars on California roads

They Are Robots And This Is ROBOCUP

First contested in 1997, the RoboCup is an annual competition that brings together some of the finest minds in robotics and artificial intelligence, primarily to pit small-sided teams of fully automated robots against each other in games of football

Heavy Hitters

Sporting robots are still slow. But their inventors are making rapid strides

Publications

Modeling Uncertainty in Leading Ad Hoc Teams

Ad hoc teamwork is a new, developing area that emerged due to the growing use of cooperating agents in different domains, such as e-commerce and robotic search and rescue

PDF

Influencing a Flock via Ad Hoc Teamwork

Flocking is an emergent behavior in which each individual agent follows a simple behavior rule that leads to a group beh avior that appears cohesive and coordinated

PDF

Orienting a Flock via Ad Hoc Teamwork.

This abstract summarizes a portion of our work on influencing a flock of agents to adopt a desired behavior within the context of ad hoc teamwork

PDF

Planning in Action Language while Learning Action Costs for Mobile Robots

As robots deal with increasingly complex tasks, automated planning systems can provide great flexibility over direct implementation of behaviors

PDF

Multi-robot Human Guidance using Topological Graphs

This paper studies how ubiquitous robots in an environment can be used to guide people efficiently to their destinations

PDF

Awards

Regents' Outstanding Teaching Award (2013)

The University of Texas System

Faculty Research Award (2012)

Google

Robocup World Champion

Team member in 9 RoboCup events

Faculty Research and Engagement (FREP) award (2011)

Yahoo!