EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Streamlining Human–Robot Interaction: Integrating LLM-Based Planning into Modular Robotic Frameworks

MinHyuk Kim, JooHee Park, Kwanyong Park, Yong-Ju Lee iD, Sanghun Jeon

Sensors · 2026

DOI: 10.3390/s26061978 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von MinHyuk Kim und 4 weiteren Autor:innen. Beteiligte Einrichtung: Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of Korea. Hauptthemen laut MEDLINE: Robotics, Artificial Intelligence. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & communications Technology Planning & Evaluation (IITP) grants funded by the Korea government (MSIT), Development of AI Autonomy and Knowledge Enhancement for AI Agent Collaboration, Korea government.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Embodied artificial intelligence (AI), which integrates AI and robotics, has made significant progress, particularly in human–robot interaction, task-assisting robots, and the integration of multimodal AI models. Experimental studies have demonstrated strong performance in complex tasks, such as providing human assistance, performing household chores, and object manipulation through pick-and-place operations. However, despite these impressive capabilities, real-world applicability remains limited. While tasks such as household chores and object manipulation offer significant practical utility, users often struggle to provide effective instructions, and execution remains prohibitively slow for real-world deployment. This study introduces an approach to enhance usability through spoken human instructions and reduce operation time by streamlining intermediate steps through our Module Handler. The proposed approach leverages a large language model to extract information from spoken human instructions accurately. Through experiments, we validated the accuracy of our approach and confirmed speed improvements compared with related studies. Our experiments evaluated system accuracy in extracting relevant information from spoken human instruction, achieving an object identification accuracy rate of approximately 92.47%. In addition, our method reduced task completion times by an average of 33 s across four different experimental environments compared with existing modular robotics systems. This time reduction is significant for enhancing robotic task execution efficiency.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RoboticsArtificial IntelligenceHumansLarge Language ModelsIntelligent SystemsAlgorithms

Stichwörter der Autor:innen

embodied AIhuman–robot interactionlarge language modelmodular roboticstask execution

Autor:innen und Institutionen

  • Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of Korea.
  • Department of Mechanical Engineering, Korea University, Anam-ro 145, Seongbuk-gu, Seoul 02841, Republic of Korea.

ORCID-Profile: Yong-Ju Lee

Förderung

  • Institute of Information & communications Technology Planning & Evaluation (IITP) grants funded by the Korea government (MSIT)
  • Development of AI Autonomy and Knowledge Enhancement for AI Agent Collaboration
  • Korea government

Zitieren

APA

Kim, M., Park, J., Park, K., Lee, Y. J., & Jeon, S. (2026). Streamlining Human–Robot Interaction: Integrating LLM-Based Planning into Modular Robotic Frameworks. Sensors. https://doi.org/10.3390/s26061978

Vancouver

Kim M, Park J, Park K, Lee YJ, Jeon S. Streamlining Human–Robot Interaction: Integrating LLM-Based Planning into Modular Robotic Frameworks. Sensors. 2026. doi:10.3390/s26061978

BibTeX
@article{Kim2026,
  author = {Kim, MinHyuk and Park, JooHee and Park, Kwanyong and Lee, Yong-Ju and Jeon, Sanghun},
  title = {Streamlining Human–Robot Interaction: Integrating LLM-Based Planning into Modular Robotic Frameworks},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26061978}
}
Kostenlos starten →