Autonomous Learning of Target Decision Strategies without Communications for Continuous Coordinated Cleaning Tasks
Autonomous Learning of Target Decision Strategies without Communications for Continuous Coordinated Cleaning Tasks
复制标题
无需通信即可自主学习目标决策策略，实现持续协调的清洁任务
DOI：
10.1109/wi-iat.2013.112
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
and Toshiharu Sugawara
中科院分区：
文献类型：
--
作者：
Keisuke Yoneda;Chihiro Kato;and Toshiharu Sugawara
我们提出了一种方法，用于自主学习的目标决策策略的协调在连续清洗域。随着计算机和传感器技术的不断进步，我们可以期待机器人应用覆盖大面积，通常需要多个机器人协调/合作活动。在本文中，我们专注于清洁任务，由多个机器人或代理，软件来控制机器人。我们假设代理不能直接交换内部信息，如计划和目标的协调，而是单独学习他们的目标决策策略，通过观察有多少垃圾/污垢已在多代理系统环境中被吸尘。我们实验评估所提出的方法，通过比较其性能与那些由代理人的制度与一个单一的战略。结果表明，该方法使代理人选择目标决策策略，从自己的角度来看，在适当的组合，导致多个战略。
We propose a method for the autonomous learning of target decision strategies for coordination in the continuous cleaning domain. With ongoing advances in computer and sensor technologies, we can expect robot applications for covering large areas that often require coordinated/cooperative activities by multiple robots. In this paper, we focus the cleaning tasks by multiple robots or by agents, software to control the robots. We assume that agents cannot directly exchange internal information such as plans and targets for coordination, but rather individually learn their target decision strategies by observing how much trash/dirt has been vacuumed up in the multi-agent system environments. We experimentally evaluated the proposed method by comparing its performance with those obtained by the regimes of agents with a single strategy. Results showed that the proposed method enables agents to select target decision strategies from their own perspectives, resulting in the appropriate combinations of multiple strategies.