| 多障碍环境中基于增强式学习的势场优化和机器人路径规划 |
| |
| 引用本文： | 庄晓东,孟庆春,王汉萍,殷波.多障碍环境中基于增强式学习的势场优化和机器人路径规划[J].中国海洋大学学报(自然科学版),2001,31(6):937-942. |
| |
| 作者姓名： | 庄晓东 孟庆春 王汉萍 殷波 |
| |
| 作者单位： | 1. 青岛海洋大学电子工程系，青岛 266003
2. 青岛海洋大学电子工程系，青岛 266003;清华大学智能技术与系统国家重点实验室，北京 100084 |
| |
| 基金项目： | 高等学校重点实验室访问学者基金，青岛市科委课题资助 |
| |
| 摘 要： | 该文把增强式学习方法应用于多障碍环境中机器人路径规划 ,并将增强式学习和路径规划相结合 ,通过工作空间势场的自适应优化学习 ,实现机器人的全局路径规划 ,即得到从任何初始位置开始的最优路径。与传统的人工势场方法相比 ,该方法避免了势场中局部极小点所引起的陷阱区域 ,并且所得到的路径具有最优特性。计算机仿真实验结果表明 ,这种学习方法能有效的解决多障碍环境中的机器人路径规划问题
|
| 关 键 词： | 增强式学习 移动机器人 多障碍环境 人工势场 路径规划 |
| 文章编号： | 1001-1862(2001)06-937-06 |
| 修稿时间： | 2001年3月2日 |
Potential Field Optimization and Robot Path Planning in Multi-Obstacle Environment Based on Reinforcement Learning |
| |
| Zhuang Xiaodong \ Meng Qingchun , \ Wang Hanping \ Yin Bo.Potential Field Optimization and Robot Path Planning in Multi-Obstacle Environment Based on Reinforcement Learning[J].Periodical of Ocean University of China,2001,31(6):937-942. |
| |
| Authors: | Zhuang Xiaodong \ Meng Qingchun \ Wang Hanping \ Yin Bo |
| |
| Institution: | Zhuang Xiaodong 1\ Meng Qingchun 1,2 \ Wang Hanping 1\ Yin Bo 1 |
| |
| Abstract: | In this paper the reinforcement learning to robot path planning in complex environment of multiple obstacles is applied. An adaptive control strategy learning method is proposed. Reinforcement learning is an unsupervised learning method based on the reactive and feedback mechanism. In this paper the reinforcement learning and path planning are combined together. The optimal path from any initial position is obtained by optimizing the global potential field and control rules. Compared with traditional artificial potential field method, this method avoids irrelevant local minimal points, which can make the robot vibrate in a small local area. Furthermore, the path found is optimal. The computer simulation experiment result shows that this learning method can efficiently solve the robot path planning problem in multi obstacle environment. |
| |
| Keywords: | reinforcement learning mobile robot multi obstacle environment artificial potential field path planning |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
