Project Details
Abstract
Today, robots are used in many ways, from lawn mowing to auto manufacturing.
Robots can also be used in many places such as performing socially undesirable,
hazardous or even "impossible" tasks --- the search and rescue in a collapse or fire
building, trash collection, toxic waste clean-up, desert and space exploration, and more.
In recent years, robot soccer game creates many research issues such as multi-agent
systems, multi-robot cooperative teams, autonomous navigation, sensor fusion, fast
pattern recognition and real time decision. Soon after, the idea of robotic soccer game
gains worldwide support. The Robot World Cup Initiative (RoboCup), proposes a new
standard problem for AI and robotics research. The first world RoboCup soccer
championship took place in 1997 during the International Joint Conference on
Artificial Intelligence in Nagoya, Japan. Since soccer game is a teamwork game,
multiple soccer robots should implement some action with collaboration for offensive
and defensive. In this project, we want to investigate four research issues: message
exchange, behavior model, multi-agent cooperation, and real-time decision-making
strategy. The system developed by us is based on a hierarchical structure which is
similar to seven layer protocols in computer networks. This project starts with the
message exchange by each duty cycle defined by RoboCup. And then we will design
some skills on an individual agent such as kick the ball to goal, dribble the ball toward
goal, and pass the ball to a teammate. Finally, we have to design an efficient
decision-making strategy to decide which action should be performed or which tactics
should be made. The final objective of this project is to develop a robot soccer team
and can be evaluated by joining a robot soccer game.
Project IDs
Project ID:PB9801-1188
External Project ID:NSC96-2628-E182-019-MY3
External Project ID:NSC96-2628-E182-019-MY3
Status | Finished |
---|---|
Effective start/end date | 01/08/09 → 31/07/10 |
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.