Push and Pull: Shepherding Multi-Agent Robot Teams in Adversarial Situations
Push and Pull: Shepherding Multi-Agent Robot Teams in Adversarial Situations
复制标题
DOI：
10.1109/arso46408.2019.8948797
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Michael J. Pettinati;R. Arkin
中科院分区：
文献类型：
--
作者：
Michael J. Pettinati;R. Arkin
在竞争激烈的环境中，负责做出关键决策的机器人团队面临着被引导或误导到对竞争团队有利的位置的风险。我们的实验室正在努力了解机器人的对抗团队如何成功地将他们的竞争对手转移到所需的位置，以便我们可以制定实践来对抗这些策略，并帮助团队运作更加成功和安全。在本文中，提出了初步的研究，研究如何一队机器人可以被引导或误导到一个不利的位置。我们从放牧行为以及在高级灵长类动物和人类中看到的欺骗行为中汲取灵感。我们定义的目标（标记）代理移动以及成员的牧羊队（推代理和拉shills）的行为，并提出模拟结果，显示这些行为如何移动机器人到所需的位置。这些行为在硬件平台上实现和测试。讨论正在进行的研究理解误导多机器人团队结束本文。
Teams of robots tasked with making critical decisions in competitive environments are at risk for being shepherded or misdirected to a location that is advantageous for a competing team. Our lab is working to understand how adversarial teams of robots can successfully move their competition to desired locations in part so that we can then devise practices to counter these strategies and help make team functioning more successful and secure. In this paper, preliminary research is presented that studies how a team of robots can be shepherded or misdirected to a disadvantageous location. We draw inspiration from herding practices as well as deceptive practices seen in higher-order primates and humans. We define behaviors for the target (mark) agents to be moved as well as members of the shepherding team (a pushing agent and pulling shills) and present simulation results showing how these behaviors move robots to a desired location. These behaviors were implemented and trialed on hardware platform. A discussion of ongoing research into understanding misdirection in multi-robot teams concludes this paper.