This paper is an extension to our work presented in Ben Slimane and Tagina (in: Nguyen, Pimenidis, Khan and Trawiński (eds) Computational collective intelligence, Springer, Cham, 2018). It deals with the the problem of partitioning the space in an even way between a number of autonomous mobile robots. In our previous work we proposed a distributed one-phased partitioning method where each robot constructs its corresponding Voronoi cell from the information received from its neighbors. We propose in what follows a two-phased partitioning approach, starting with a dispersion task, followed by the distributed Voronoi partitioning as for the one-phased method. For the dispersion phase, we propose a novel parametrized algorithm from which we seek to control the dispersion behavior of the robots. The individual actions of the agents are controlled by the belief–desire–intention model which endows them with the required know-how needed to operate deliberately and readjust the plans dynamically on the go. We show in this paper, through a series of experiments, the results of the dispersion method and the impact of its parameters on the generated maps. We also compare the results of the two partitioning methods to show the impact of the dispersion on the partitioning in terms of the actual performed steps towards convergence and the generated maps for both methods.

本文是对我们在Ben Slimane和Tagina上发表的工作的扩展（在：Nguyen，Pimenidis，Khan和Trawiński（eds）计算集体智能，Springer，Cham，2018年）。它解决了在多个自动移动机器人之间均匀分配空间的问题。在我们以前的工作中，我们提出了一种分布式的单阶段分区方法，其中每个机器人都从从其邻居那里收到的信息中构造相应的Voronoi细胞。我们提出以下两阶段划分方法，首先是分散任务，然后是针对一阶段方法的分布式Voronoi划分。对于分散阶段，我们提出了一种新颖的参数化算法，从中我们寻求控制机器人的分散行为。行为人的个人行动受信念-愿望-意图模型的控制，该模型为他们提供了所需的专门知识，可以有意识地进行操作并在旅途中动态调整计划。通过一系列实验，我们在本文中展示了分散方法的结果及其参数对生成图的影响。我们还比较了两种分区方法的结果，以显示在趋于收敛的实际执行步骤以及两种方法生成的映射方面，色散对分区的影响。分散方法的结果及其参数对生成图的影响。我们还比较了两种分区方法的结果，以显示在趋于收敛的实际执行步骤以及两种方法生成的映射方面，色散对分区的影响。分散方法的结果及其参数对生成图的影响。我们还比较了两种分区方法的结果，以显示在趋于收敛的实际执行步骤以及两种方法生成的映射方面，色散对分区的影响。