EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Model-Class Comparison of Large Language Models for Translating Chinese Route Instructions into Robot Command Sequences

Ruizhe Yang, Yuki Nishimura

Journal of Sensor and Actuator Networks · 17.11.2026 · 15 (6) · 91

DOI: 10.3390/jsan15060091 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Sensor and Actuator Networks, online erschienen am 17.11.2026. Verfasst von Ruizhe Yang und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advances in large language models (LLMs) have accelerated the real-world deployment of embodied intelligent robots, supporting intuitive human–robot interaction without specialized robotics expertise. However, few systematic assessments examine how well LLMs translate natural-language route instructions into executable robot command sequences, particularly for non-English instructions and across deployment-relevant model classes. In this paper, a Chinese route-instruction corpus was constructed, which comprised 212 instructions collected from six native speakers across 50 procedurally generated town maps. Each was annotated with a ground-truth command sequence verified by simulation to reach its goal, and a 100% performance ceiling was established. Using this corpus, 12 LLMs spanning three capability tiers—cloud proprietary models, mid-sized open-weight models, and small open-weight models—were evaluated under three system prompts differing only in the number of worked examples (zero, one, and three). Open-weight models in the 3–9B range reached at most 9.2% of goals, while proprietary cloud models reached 80.0%, a substantial gap that increasing the number of worked examples did not measurably narrow. A paired analysis across the three prompt conditions detected no reliable effect of demonstration count: pooled path_reach rose modestly from 25.0% under zero-shot prompting to 27.2% with one example and 27.7% with three examples (three versus zero examples: odds ratio: 1.15; 95% CI: 0.98–1.34). None of these differences was significant after multiple-comparison correction (Holm-adjusted p ≥ 0.247). Low-Rank Adaptation (LoRA) fine-tuning on 126 examples raised mid-sized open-weight models to 27.7–35.4%, and the gain spanned both output-format compliance and route competence.

Zitieren

APA

Yang, R., & Nishimura, Y. (2026). A Model-Class Comparison of Large Language Models for Translating Chinese Route Instructions into Robot Command Sequences. Journal of Sensor and Actuator Networks, 15(6), 91. https://doi.org/10.3390/jsan15060091

Vancouver

Yang R, Nishimura Y. A Model-Class Comparison of Large Language Models for Translating Chinese Route Instructions into Robot Command Sequences. Journal of Sensor and Actuator Networks. 2026;15(6):91. doi:10.3390/jsan15060091

BibTeX
@article{Yang2026,
  author = {Yang, Ruizhe and Nishimura, Yuki},
  title = {A Model-Class Comparison of Large Language Models for Translating Chinese Route Instructions into Robot Command Sequences},
  journal = {Journal of Sensor and Actuator Networks},
  year = {2026},
  volume = {15},
  number = {6},
  pages = {91},
  doi = {10.3390/jsan15060091}
}
Kostenlos starten →