基于队形分布和Q学习的多机器人围捕策略
ooperative Hunting Strategy of Multiple mobile robots Based on New State Partition
提出了一种机器人队形矩阵的标识方法，设计了维数更少的状态空间。 通过分析不同队形对围捕的利弊，设计了状态评价及强化函数，减少了由于感知区域划分不精细等因素对学习结果合理性的影响。通过仿真实验，验证了方法的可行性，并对存在问题进行了分析。
formation matrix is presented to identify the positions of the mobile robots and state space with lower dimension is constructed. By analyzing the merit and demerit of various formations, state criterion and reinforcement function is given. The effect on the learning result owing to uncertain partition of sensed area is weakened. Simulation experiment shows that the presented approach is feasible. Finally, some deficiencies are analyzed.
黄旭、代桂平、陈阳舟
自动化技术、自动化技术设备自动化基础理论
Q学习队形分布矩阵多机器人围捕
Q-learningFormation matrixMultiple mobile robotsHunting
黄旭,代桂平,陈阳舟.基于队形分布和Q学习的多机器人围捕策略[EB/OL].(2010-01-28)[2025-08-10].http://www.paper.edu.cn/releasepaper/content/201001-1215.点此复制
评论