A Hierarchical LLM-Based Framework for Heterogeneous Multi-Robot Orchestration in High-Risk Energy Facility Maintenance
IEEE Access · 2026 · 14 · 66881-66898
DOI: 10.1109/access.2026.3684055 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Jungi Lee und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information and Communications Technology Planning and Evaluation, Korean Government (MSIT), Development of a Foundation Model-Based Power Sector-Specialized Agent for Stable Power Generation and Operation.
Abstract (Originalsprache)
Maintenance and operation of critical energy infrastructure require extreme precision and strict adherence to safety protocols to prevent catastrophic failures. While recent advancements in general-purpose Vision-Language-Action (VLA) foundation models have shown promise in robotics, their inherent stochasticity and lack of procedural precision often result in unacceptable safety risks in high-stakes industrial environments. To address these limitations, this paper proposes a novel Hierarchical Multi-Robot Orchestration Framework designed for the coordinated control of heterogeneous robots in energy facility maintenance. The proposed framework decouples high-level cognitive reasoning from low-level execution by utilizing a local Large Language Model (LLM) as a strategic orchestrator. Grounded in a Structured Environmental Representation ( $\mathcal {M}$ ), the LLM employs Chain-of-Thought (CoT) reasoning to decompose complex maintenance missions into verifiable sub-tasks, effectively bridging the gap between linguistic intent and physical constraints. These tasks are then dispatched to specialized execution modules: a manipulation unit utilizing Action Chunking with Transformers (ACT) adapted for high-precision industrial tasks, an autonomous navigation unit for Simultaneous Localization and Mapping (SLAM)-based pathfinding, and a vision-guided logistics unit for retrieval. Experimental evaluations in a simulated power plant environment validate the efficacy of the framework. A comparative ablation study demonstrates that utilizing structured environmental grounding significantly enhances the reasoning reliability of large-scale models compared to unstructured text baselines. Specifically, the GPT-OSS (20B) model achieved a peak planning success rate of 91.7%, with a notable proficiency in handling long-horizon Strategic commands (73.3%), validating that structural clarity is essential for complex causal inference. Furthermore, the integrated execution layer demonstrated exceptional reliability, achieving a 90% success rate specifically in distribution panel maintenance tasks, confirming that the hierarchical decoupling of probabilistic reasoning and deterministic execution provides a reliable solution for autonomous maintenance.
Förderung
- Institute of Information and Communications Technology Planning and Evaluation
- Korean Government (MSIT), Development of a Foundation Model-Based Power Sector-Specialized Agent for Stable Power Generation and Operation
Zitieren
APA
Lee, J., Kim, S., Lee, G., Kim, K., Jeon, J., Ko, S., & Lee, K. (2026). A Hierarchical LLM-Based Framework for Heterogeneous Multi-Robot Orchestration in High-Risk Energy Facility Maintenance. IEEE Access, 14, 66881-66898. https://doi.org/10.1109/access.2026.3684055
Vancouver
Lee J, Kim S, Lee G, Kim K, Jeon J, Ko S, et al. A Hierarchical LLM-Based Framework for Heterogeneous Multi-Robot Orchestration in High-Risk Energy Facility Maintenance. IEEE Access. 2026;14:66881-66898. doi:10.1109/access.2026.3684055
BibTeX
@article{Lee2026,
author = {Lee, Jungi and Kim, Seu-Jan and Lee, Geonhyup and Kim, Kangmin and Jeon, Jimin and Ko, Seok-Kap and Lee, Kyoobin},
title = {A Hierarchical LLM-Based Framework for Heterogeneous Multi-Robot Orchestration in High-Risk Energy Facility Maintenance},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {66881--66898},
doi = {10.1109/access.2026.3684055}
}
EUVIMED