Abstract
In this paper, we present a model for semantic memory that allows machines collect information and experiences and become more competent with time. After a semantic analysis of the data, information is stored in a knowledge graph and used to comprehend instructions expressed in natural language and execute required tasks properly and in a deterministic manner. This provides industrial robots with cognitive behavior and an intuitive user interface, which is most appreciated in an era, when collaborative robots are to work alongside humans. The paper outlines the architecture of the system together with a practical implementation proposal.
Abstract (translated)
URL
https://arxiv.org/abs/2101.01099