| 引用本文: | 叶剑, 乔俊飞, 李明爱, 阮晓钢.一种基于行为控制的两自由度机械臂智能控制器[J].控制理论与应用,2007,24(3):440~444.[点击复制] |
| YE Jian, QIAO Jun-fei, LI Ming-ai, RUAN Xiao-gang.A behavior-based intelligent controller for a 2-dof manipulator[J].Control Theory and Technology,2007,24(3):440~444.[点击复制] |
|
| 一种基于行为控制的两自由度机械臂智能控制器 |
| A behavior-based intelligent controller for a 2-dof manipulator |
| 摘要点击 1614 全文点击 1770 投稿时间：2005-10-25 修订日期：2006-02-23 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 |
| 2007,24(3):440-444 |
| 中文关键词 反应式行为 智能控制器 评价－控制模型 强化学习 机械臂 |
| 英文关键词 reactive behavior intelligent controller critic-control model reinforcement learning manipulator |
| 基金项目 国家自然科学基金资助项目(60375017); 北京市教委科技发展计划资助项目(KM200610005019) |
|
| 中文摘要 |
| 基于行为的控制方法相对于传统的控制方法在解决未知环境中的机器人中有着更好的鲁棒性和实时性.本文提出了一种基于反应式行为控制的智能控制器, 以强化学习作为智能控制器的学习算法. 通过采用评价－控制模型, 该智能控制器能够不依赖于系统模型, 通过连续地在线学习得到机器人的行为. 将该智能控制器应用到两自由度仿真机械臂的控制中, 仿真结果表明该智能控制器可以实现对两自由度机械臂的连续控制, 使其能够迅速达到目标位置. |
| 英文摘要 |
| The behavior-based method is more robust and better in real-time performance than the traditional method for the robot control in the unknown environment. A behavior-based intelligent controller is designed for the control of a 2-dof manipulator in this paper. The intelligent controller(IC) is based on the critic-action model and takes the reinforcement learning algorithm as the learning algorithm. By using the critic-action model, the controller can learn the behavior online and does not rely on the system model. The experiment shows that the controller can realize the continuous control for the 2-dof manipulator and the manipulator can reach the target position quickly. |
|
|
|
|
|