EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LLM-Assisted Plan Execution for Robots in Dynamic Environments

Juan Diego Peña-Narvaez, Rodrigo Pérez-Rodríguez, Juan Carlos Manzanares, Francisco Miguel Moreno, Francisco Martín-Rico

Robotics · 15.04.2026 · 15 (4) · 80

DOI: 10.3390/robotics15040080 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Robotics, online erschienen am 15.04.2026. Verfasst von Juan Diego Peña-Narvaez und 4 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Commission.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, planning frameworks have enabled the creation and execution of plans in robots using classical planning approaches based on the Planning Domain Definition Language (PDDL). The dynamic nature of the environments in which these robots operate requires that execution plans adapt to new conditions, either by repairing plans to improve efficiency or because they are no longer valid. Determining the appropriate moment to initiate such repairs is the focus of our research. This paper presents a novel approach to this problem by using Large Language Models (LLMs) to make informed plan repair decisions during robot operation. Our approach introduces an LLM-based semantic evaluation heuristic that goes beyond the traditional heuristic methods employed in symbolic planning frameworks, while addressing the common hallucinations associated with task planning when relying solely on generative artificial intelligence. Our approach uses the semantic evaluation capabilities of LLMs to track environmental features and forecast hazards. This allows the system to proactively identify dangerous situations and adapt plans more efficiently. We experimentally demonstrate the validity of our approach using real robots in environments where both the environmental conditions and the goals to be achieved change dynamically.

Förderung

  • European Commission

Zitieren

APA

Peña-Narvaez, J. D., Pérez-Rodríguez, R., Manzanares, J. C., Moreno, F. M., & Martín-Rico, F. (2026). LLM-Assisted Plan Execution for Robots in Dynamic Environments. Robotics, 15(4), 80. https://doi.org/10.3390/robotics15040080

Vancouver

Peña-Narvaez JD, Pérez-Rodríguez R, Manzanares JC, Moreno FM, Martín-Rico F. LLM-Assisted Plan Execution for Robots in Dynamic Environments. Robotics. 2026;15(4):80. doi:10.3390/robotics15040080

BibTeX
@article{PeaNarvaez2026,
  author = {Peña-Narvaez, Juan Diego and Pérez-Rodríguez, Rodrigo and Manzanares, Juan Carlos and Moreno, Francisco Miguel and Martín-Rico, Francisco},
  title = {LLM-Assisted Plan Execution for Robots in Dynamic Environments},
  journal = {Robotics},
  year = {2026},
  volume = {15},
  number = {4},
  pages = {80},
  doi = {10.3390/robotics15040080}
}
Kostenlos starten →