Multiple autonomous agents working cooperatively have contributed to the development of robust large-scale systems. While substantial work has been done in manufacturing and domestic environments, a key consideration for small hardware agents engaged in collaborative factory automation and welfare support systems is limited area and power on-board. When the agents attempt to meet for performing a task, it is natural for them to encounter obstacles and it is desirable for each agent to optimize its resources during its navigation. In this paper, we develop efficient geometric algorithms to find a point, termed as the gathering point (and denoted by $P_G$), for the agents that minimizes the maximum of path lengths. In particular, we present an $O(n \log _2 n)$ time algorithm for calculation of $P_G$ for an environment with two agents and $n$ static polygonal obstacles. We then use the notion of a weighted minimax point to derive an efficient algorithm (with complexity of $O(k^2 + kn \log _2 n)$) for computing $P_G$ for an environment with $k$ agents and $n$ obstacles. An enhancement to a dynamic environment is then presented. We also present details of an efficient hardware realization of the algorithms. Each agent, equipped with only an ATmega328P microcontroller and no external memory, executes the algorithms. Experiments with multiple agents navigating amidst static as well as dynamic obstacles are reported.

中文翻译：

---

避免碰撞和最小最大距离准则的多智能体聚集-高效算法和硬件实现

多个自治代理共同合作为强大的大型系统的开发做出了贡献。尽管在制造和家庭环境中已经进行了大量工作，但是参与协作工厂自动化和福利支持系统的小型硬件代理商的主要考虑因素是有限的面积和车载电源。当代理试图见面以执行任务时，他们自然会遇到障碍，并且希望每个代理在其导航期间优化其资源。在本文中，我们开发了有效的几何算法来找到一个点，称为点聚集点 （并用 $ P_G $），对于代理商 最小化最大路径长度。特别是，我们提出了一个$ O（n \ log _2 n）$ 计算时间的算法 $ P_G $ 对于具有两个代理的环境 $ n $静态多边形障碍。然后，我们使用a的概念加权极大极小点 得出有效的算法（复杂度为 $ O（k ^ 2 + kn \ log _2 n）$）用于计算 $ P_G $ 用于环境 $ k $ 代理商和 $ n $障碍。然后提出了对动态环境的增强。我们还介绍了算法的有效硬件实现的细节。每个代理程序仅配备一个ATmega328P微控制器，而没有外部存储器，它们执行算法。报告了在动态和静态障碍中使用多种智能体进行导航的实验。