arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.09564cs.ROcs.MA
收藏

通信受限环境下的集体决策

Collective Decision Making in Communication-Constrained Environments

University of Southampton(南安普顿大学);School of Electronics and Computer Science, University of Southampton(南安普顿大学电子与计算机科学学院)

Thomas G. Kelly, Mohammad Divband Soorati, Klaus-Peter Zauner, Sarvapali D. Ramchurn, Danesh Tarapore

摘要:

自主机器人群的主要任务之一是集体决定最佳可用选项。实现这一点需要代理之间的高质量通信,而这在现实环境中可能并不总是可用的。在本文中,我们介绍了通信约束的集体决策问题的环境中的某些领域限制代理的通信能力,无论是通过降低成功率或阻塞的通信渠道。我们提出了一个分散的算法映射环境特征的机器人群,以及改善集体决策的通信有限的环境中没有事先了解的通信景观。我们的研究结果表明,使一个集体意识到的通信环境可以提高收敛的速度,在通信限制的存在下,至少快3倍,而不牺牲准确性。

英文摘要:

One of the main tasks for autonomous robot swarms is to collectively decide on the best available option. Achieving that requires a high quality communication between the agents that may not be always available in a real world environment. In this paper we introduce the communication-constrained collective decision-making problem where some areas of the environment limit the agents' ability to communicate, either by reducing success rate or blocking the communication channels. We propose a decentralised algorithm for mapping environmental features for robot swarms as well as improving collective decision making in communication-limited environments without prior knowledge of the communication landscape. Our results show that making a collective aware of the communication environment can improve the speed of convergence in the presence of communication limitations, at least 3 times faster, without sacrificing accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑