A feature of tasks in embodied artificial intelligence is that a query to an intelligent agent is formulated in natural language. As a result, natural language processing methods have to be used to transform the query into a format convenient for generating an appropriate action plan. There are two basic approaches to the solution of this problem. One is based on specialized models trained with particular instances of instructions translated into agent-executable format. The other approach relies on the ability of large language models trained with a large amount of unlabeled data to store common sense knowledge. As a result, such models can be used to generate an agent’s action plan in natural language without preliminary learning. This paper provides a detailed review of models based on the second approach as applied to embodied artificial intelligence tasks.
DOI: 10.1134/S1064562422060138
Download PDF from the SpringerLink publishing house website: https://link.springer.com/content/pdf/10.1134/S1064562422060138.pdf
Read at the Russian Academy of Sciences publishing house website (in Russian, registration required): https://sciencejournals.ru/view-article/?j=danmiup&y=2022&v=508&n=1&a=DANMIUp2207013Kovalev
Download PDF or read online at ResearchGate: https://www.researchgate.net/publication/367277582_Application_of_Pretrained_Large_Language_Models_in_Embodied_Artificial_Intelligence
Download PDF from eLibrary (in Russian, registration required): https://elibrary.ru/item.asp?id=49991315
Kovalev A. K., Panov, A. I. (2022). Application of Pretrained Large Language Models in Embodied Artificial Intelligence // Doklady Mathematics, Vol. 106, pp. 85–90. https://doi.org/10.1134/S1064562422060138