June 20, 2010
June 20, 2010
June 23, 2010
Computers in Education
15.1045.1 - 15.1045.8
Robo-Billiards: A Game to Understand Adaptive Behavior of Middle School Students
Robo-Billiards is a timed competition in which middle school students remotely control robots to place billiards balls in pockets. Points are awarded in the game based on how the balls are combined in the pockets. If a ball is accidently knocked off the game surface it is out of play and the opportunity for the overall maximum score is lost. It was observed that once a ball was knocked off the surface, creating a fault, that students tended to panic and seldom adjusted their strategy to achieve the maximum score with the remaining billiard balls. The capability to adapt in real-time is what makes humans successful in chaotic environments. In order for computer systems to be successful, they too must adapt in real-time to unplanned events. Two problems for adaptive systems are how to represent knowledge and how to use that knowledge to make adaptive decisions. With this research we examined the use of scripts (that specified robot ball selection and placement) to represent knowledge, and heuristics and dynamic scripting to make adaptive decisions. In this research, an Autonomous Robo-Billiards Opponent (ARBO) was developed to play Robo-Billiards. As a baseline, ARBO was tested to determine if it could execute a script in less than five minutes and still earn the maximum score. Then faults were simulated while ARBO was executing a script to test if the system could adapt and earn the optimal score with the remaining balls. A potential use of this system is to compete against middle school students. Two immediate benefits would be to: (i) stimulate interest in STEM disciplines and (ii) demonstrate adaptive behavior when a fault occurs.
Humans must adapt in real-time to new problems and situations. The ability to adapt well to problems makes humans successful. For intelligent software systems to succeed in human environments, they too must adapt in real-time to unexpected problems. The focus of this research is to explore how software systems can adapt in real-time in dynamic and chaotic environments to lead to successful results.
Expert systems have been developed that exhibit the same sophistication as humans to adapt in real-time . These systems are successful in environments that have constrained complexity. Because of real world complexity, it becomes necessary to do research with software systems in constrained environments. By constraining the environments, researchers reduce the number of variables in their experiments and increase confidence in their simpler results. Games provide environments that are rich enough to answer research questions that relate to the real world, yet are constrained enough to support experimentation.
Our interest in developing an adaptive real-time system began with our observation of a game called Robo-Billiards. In Robo-Billiards, participants use radio controllers to maneuver a robot that they have constructed. The objective of the game is to manipulate the robot’s movements to place the standard sixteen billiard balls into pockets located at the corner of a playing field.
Brown, K., & Doran, M., & Langan, D., & Thomas, T. (2010, June), Robo Billiards: A Game To Understand Adaptive Behavior Of Middle School Students Paper presented at 2010 Annual Conference & Exposition, Louisville, Kentucky. 10.18260/1-2--16186
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2010 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015