EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Framework for LLM-Enabled Construction Robot Task Planning: Knowledge Base Preparation and Robot–LLM Dialogue for Interior Wall Painting

Kyungki Kim, Prashnna Ghimire, Pei-Chi Huang

Robotics · 27.08.2025 · 14 (9) · 117

DOI: 10.3390/robotics14090117 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Robotics, online erschienen am 27.08.2025. Verfasst von Kyungki Kim und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Task planning for a construction robot requires systematically integrating diverse elements, such as building components, construction processes, user input, and robot software. Conventional robot programming complicates this by requiring precise entity naming, relationship definitions, unstructured language interpretation, and accurate action selection. Existing research has focused on isolated components, such as natural language processing, hardcoded data linkages, or BIM data extraction. We introduce a novel framework using an LLM as the cognitive core for autonomous construction robots, encompassing both data preparation and task planning phases. Leveraging OpenAI’s ChatGPT-4, we demonstrate how LLMs can process structured BIM data and unstructured human inputs to generate robot instructions. A prototype tested in a simulated environment with a mobile painting robot adaptively executed tasks through real-time dialogues with ChatGPT-4, reducing reliance on hardcoded logic. Results suggest that LLMs can serve as the cognitive core for construction robots, with potential for extension to more complex operations.

Zitieren

APA

Kim, K., Ghimire, P., & Huang, P. (2025). Framework for LLM-Enabled Construction Robot Task Planning: Knowledge Base Preparation and Robot–LLM Dialogue for Interior Wall Painting. Robotics, 14(9), 117. https://doi.org/10.3390/robotics14090117

Vancouver

Kim K, Ghimire P, Huang P. Framework for LLM-Enabled Construction Robot Task Planning: Knowledge Base Preparation and Robot–LLM Dialogue for Interior Wall Painting. Robotics. 2025;14(9):117. doi:10.3390/robotics14090117

BibTeX
@article{Kim2025,
  author = {Kim, Kyungki and Ghimire, Prashnna and Huang, Pei-Chi},
  title = {Framework for LLM-Enabled Construction Robot Task Planning: Knowledge Base Preparation and Robot–LLM Dialogue for Interior Wall Painting},
  journal = {Robotics},
  year = {2025},
  volume = {14},
  number = {9},
  pages = {117},
  doi = {10.3390/robotics14090117}
}
Kostenlos starten →