Vision-Based Robot Learning Towards RoboCup: Osaka University "Trackies"
نویسندگان
چکیده
The authors have applied reinforcement learning methods to real robot tasks in several aspects. We selected a skill of soccer as a task for a vision-based mobile robot. In this paper, we explain two of our method; (1)learning a shooting behavior, and (2)learning a shooting with avoiding an opponent. These behaviors were obtained by a robot in simulation and tested in a real environment in RoboCup-97. We discuss current limitations and future work along with the results of RoboCup97.
منابع مشابه
Osaka University \trackies 99"
This is the team description of Osaka University \Trackies" for RoboCup-99. We have worked two issues for our new team. First, we have changed our robot system from a remote controlled vehicle to a self-contained robot. The other, we have proposed a new learning method based on a Q-learning method so that a real robot can aquire a behavior by reinforcement learning.
متن کاملThe Team Description of Osaka University "Trackies-99"
This is the team description of Osaka University “Trackies” for RoboCup-99. We have worked two issues for our new team. First, we have changed our robot system from a remote controlled vehicle to a self-contained robot. The other, we have proposed a new learning method based on a Q-learning method so that a real robot can aquire a bhevior by reinforcement learning.
متن کاملOsaka University "Trackies 2000"
This is the team description of Osaka University “Trackies” for RoboCup2000. The hardware and software architecture are presented.
متن کاملOsaka University "Trackies 2001"
This is the team description of Osaka University “Trackies” for RoboCup2001. The hardware and software architecture are presented.
متن کاملTRACKIES: RoboCup-97 Middle-Size League World Cochampion
efforts toward the real robot competition in RoboCup. We participated in the middle-size league at RoboCup-97, held in conjunction with the Fifteenth International Joint Conference on Artificial Intelligence in Nagoya, Japan. The most significant features of our team, TRACKIES, are the application of a reinforcement learning method enhanced for real robot applications and the use of an omnidire...
متن کامل