A dual-agent framework for physically grounded and syntactically verifiable industrial robot programming
Robotica · 2026-05 · 44 (5) · 1516-1533
DOI: 10.1017/s0263574726103646 ↗Kurz gefasst
Fachartikel in der Zeitschrift Robotica, online erschienen am 08.07.2026. Verfasst von Zhendao Chen und 5 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben.
Abstract (Originalsprache)
The integration of large language models (LLMs) into KUKA industrial robots offers a promising pathway toward intuitive natural language control and a higher level of intelligence. However, existing methods face two primary challenges: their reliance on predefined motion primitives and the syntactic fragility imposed by the strict constraints of proprietary KUKA Robot Language (KRL). To address these challenges, we propose MIKI (multi-agent integrated KUKA interface), a decoupled dual-agent framework that bridges high-level reasoning and low-level syntactic verification for industrial robot programming. The controller agent incorporates a chain-of-thought (CoT) reasoning mechanism to systematically decompose abstract human instructions into logical intermediate steps. By leveraging a visual toolchain, it translates these reasoned plans into a sequence of executable actions, each embedded with precise world coordinates. Subsequently, the code generation agent employs a syntax-guided iterative refinement process, underpinned by an ANTLR4 parser, to transform these actions into verified and executable KRL code. Experimental results demonstrate that this closed-loop approach substantially improves the syntactic success rate of code generation from 0.61 to 0.89. Furthermore, the framework achieves an average success rate of 0.6 across five desktop manipulation tasks of varying complexity using a physical KUKA robotic arm, validating its effectiveness in bridging high-level cognitive reasoning with deterministic industrial execution.
Zitieren
APA
Chen, Z., Chao, H., He, Y., Hou, C., Chen, W., & Tan, N. (2026). A dual-agent framework for physically grounded and syntactically verifiable industrial robot programming. Robotica, 44(5), 1516-1533. https://doi.org/10.1017/s0263574726103646
Vancouver
Chen Z, Chao H, He Y, Hou C, Chen W, Tan N. A dual-agent framework for physically grounded and syntactically verifiable industrial robot programming. Robotica. 2026;44(5):1516-1533. doi:10.1017/s0263574726103646
BibTeX
@article{Chen2026,
author = {Chen, Zhendao and Chao, Haibo and He, Yanhao and Hou, Che and Chen, Wenjie and Tan, Ning},
title = {A dual-agent framework for physically grounded and syntactically verifiable industrial robot programming},
journal = {Robotica},
year = {2026},
volume = {44},
number = {5},
pages = {1516--1533},
doi = {10.1017/s0263574726103646}
}
EUVIMED