Balancing automated behavior and human control in multi-agent systems: a case study in RoboFlag
Balancing automated behavior and human control in multi-agent systems: a case study in RoboFlag
复制标题
平衡多智能体系统中的自动化行为和人类控制：RoboFlag 中的案例研究
DOI：
10.1109/acc.2003.1239096
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
A. T. Hayes
中科院分区：
文献类型：
--
作者：
P. Zigoris;J. Siu;O. Wang;A. T. Hayes
许多潜在的机器人应用需要在高度动态的环境中操作，并且在多智能体系统中，机器人之间需要一定程度的协调。通常，为了弥补代理人可用的自动推理的局限性，有必要包括人工控制的元素。本文的重点是如何在多智能体系统的反馈回路中包括人类操作员，其中智能体与人类的比例大于1。使用RoboFlag环境作为测试平台，我们已经实现了从最基本的运动控制到高级行为分配的各种级别的人类交互。在实时竞争中对我们的系统进行评估表明，多层次的交互是成功运行所必需的。由于智能体与人类的比例相对较高，人类很难维持对所有机器人的低级别控制，但在关键或新的情况下，人类必须绕过更高级别的自动智能。
Many potential robotic applications require operation in a highly dynamic environments and, in multi-agent systems, some degree of coordination between robots. Often it becomes necessary to include an element of human control in order to compensate for limitations in the automated reasoning available to the agents. This paper focuses on how one might include a human operator in the feedback loop of a multi-agent system, where the agent to human ratio is greater than one. Using the RoboFlag environment as a test-bed, we have implemented various levels of human interaction ranging from the most basic motion control to high-level behavior assignments. Evaluating our system in real time competition has shown that multiple levels of interaction are necessary for successful operation. Because the agent to human ratio is relatively high, it becomes difficult for the human to maintain low-level control of all the robots, but in critical or novel situations higher-level automated intelligence must be circumvented by the human.