Abstract The purpose of the study is to develop a learning system for internal representation of the events localization space to realize orientation and navigation of autonomous mobile systems. The task of the research is the development of simulation models of the semantics of the event localization space based on multi-agent neurocognitive architectures. The paper proves that the multi-agent neurocognitive architecture is an effective formalism for describing the semantics of the spatial localization of events. Main theoretical foundations have been developed for the simulation of spatial relations using the so-called multi-agent facts, consisting of software agents-concepts, reflecting semantic categories corresponding to parts of speech. It is shown that locative software agents that describe the spatial location of objects and events, forming homogeneous connections, compose the so-called field locations. The latter describes a holistic view of the intellectual agent about the environment. The paper defines conceptual foundations of multi-agent modeling of the semantics of subjective reflexive mapping of the interaction between real objects, space and time.

中文翻译：

---

事件空间定位语义的多智能体神经认知模型

摘要 本研究的目的是开发一种用于事件定位空间内部表示的学习系统，以实现自主移动系统的定向和导航。研究的任务是开发基于多智能体神经认知架构的事件定位空间语义模拟模型。论文证明多智能体神经认知架构是描述事件空间定位语义的有效形式。使用所谓的多代理事实（由软件代理概念组成，反映与词性相对应的语义类别）模拟空间关系的主要理论基础已经发展。结果表明，描述对象和事​​件空间位置的定位软件代理，形成同质连接，组成所谓的场位置。后者描述了有关环境的智能代理的整体视图。该论文定义了真实物体、空间和时间之间交互的主观反射映射语​​义的多智能体建模的概念基础。