An Behavior-based Robotics
Real-Time Vision Processing for a Soccer Playing Mobile Robot
RoboCup-97: Robot Soccer World Cup I
The RoboCup Physical Agent Challenge: Goals and Protocols for Phase 1
RoboCup-97: Robot Soccer World Cup I
RoboCup: A Challenge Problem for AI and Robotics
RoboCup-97: Robot Soccer World Cup I
Hi-index | 0.00 |
The present work focuses on the implementation of a robust and fault tolerant global vision system for RoboCup Small League soccer teams. It is based on a vision control approach, in which vision processes are guided by necessit yof information and knowledge about the environment. The object detection is based on a chromatic approach where chromatic patterns were modeled using a mixture of gaussian functions, trained with a stochastic gradien tdescen t method. The implemented system meets, and in certain cases exceeds, the functionality required to participate in RoboCup and reported in related works.