EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Making humanoid robots teaching assistants by using natural language processing (NLP) cloud-based services

Anna Lekova, Paulina Tsvetkova, Tanio Tanev, Peter Mitrouchev, Snezhana Kostova

Journal of Mechatronics and Artificial Intelligence in Engineering · 2022

DOI: 10.21595/jmai.2022.22720 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Mechatronics and Artificial Intelligence in Engineering, 2022. Verfasst von Anna Lekova und 4 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Humanoid robots have a substantial potential to serve as teaching and social assistants. However, the expectations of the children from robots to interact like humans are huge. This study presents a general model for understanding the natural language in human-robot interaction by applying Generative Pre-trained Transformer (GPT) language models as a service in the Internet of Things. Thus, the physical presence of the robot can help in fine-tuning the GPT model by prompts derived from the environmental context and subsequent robot actions for embodiment understanding of the GPT outputs. The model uses web or cloud services for Natural Language Processing (NLP) to produce and play human-like text, question answering or text generation. Verbal questions are processed either via a local speech recognition software or via a Speech-to-Text (STT) cloud service. The converted question into machine-readable code is sent to one of the GPT language models with zero- or few-shot learning prompts. GPT-J model has been tested and deployed either in the web or cloud with options for varying the parameters for controlling the haphazardness of the generated text. The robot produces human-like text by using Text-to-Speech (TTS) cloud services that convert the response into audio format rendered on the robot to be played. Useful requirements how the model to be used in order to be feasible were determined based on the evaluation of the outputs given from the different NLP and GPT-J web or cloud-services. We designed and implemented the model in order to be used by a humanoid NAO-type robot in the speech language therapy practice, however it can be used for other open-source and programmable robots and in different contexts.

Zitieren

APA

Lekova, A., Tsvetkova, P., Tanev, T., Mitrouchev, P., & Kostova, S. (2022). Making humanoid robots teaching assistants by using natural language processing (NLP) cloud-based services. Journal of Mechatronics and Artificial Intelligence in Engineering. https://doi.org/10.21595/jmai.2022.22720

Vancouver

Lekova A, Tsvetkova P, Tanev T, Mitrouchev P, Kostova S. Making humanoid robots teaching assistants by using natural language processing (NLP) cloud-based services. Journal of Mechatronics and Artificial Intelligence in Engineering. 2022. doi:10.21595/jmai.2022.22720

BibTeX
@article{Lekova2022,
  author = {Lekova, Anna and Tsvetkova, Paulina and Tanev, Tanio and Mitrouchev, Peter and Kostova, Snezhana},
  title = {Making humanoid robots teaching assistants by using natural language processing (NLP) cloud-based services},
  journal = {Journal of Mechatronics and Artificial Intelligence in Engineering},
  year = {2022},
  doi = {10.21595/jmai.2022.22720}
}
Kostenlos starten →