学習とロボット　視覚に基づく強化学習によるロボットの行動獲得

• 浅田 稔

  大阪大学工学部

• 野田 彰一

  大阪大学工学部

• 俵積田 健

  大阪大学工学部

• 細田 耕

  大阪大学工学部

書誌事項

タイトル別名

• Learning in robotics. Purposive Behavior Acquisition for a Robot by Vision-Based Reinforcement Learning.

抄録

We propose a method which acquires a purposive behavior for a mobile robot to shoot a ball into the goal by using the Q-learning, one of the reinforcement learning methods. A mobile robot (an agent) does not need to know any parameters of the 3-D environment or its kinematics/dynamics. Information about the changes of the environment is only the image captured from a single TV camera mounted on the robot. Image positions of the ball and the goal are used as a state variable which shows the effect of an action taken by the robot during the learning process. After the learning process, the robot tries to carry a ball near the goal and to shoot it. Computer simulation is used not only to check the validity of the method but also to save the learning time on the real robot. The real robot succeeded in shooting a ball into the goal using the learned policy transferred to it.

収録刊行物

• 日本ロボット学会誌

  日本ロボット学会誌 13 (1), 68-74, 1995

  一般社団法人 日本ロボット学会

キーワード

• Vision-Based Reinforcement Learning
• Q-Learning
• Behavior Acquisition
• Soccer Robot
• State-Action Deviation

詳細情報

• CRID: 1390282679702535680
• NII論文ID: 10007546853
• NII書誌ID: AN00141189
• DOI: 10.7210/jrsj.13.68
• ISSN: 18847145
• ISSN: 02891824
• 本文言語コード: ja
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可