Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huo, Xinyun, Gnanasambandam, Raghav, Zhang, Xinyao
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.04233
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910105344147456
author Huo, Xinyun
Gnanasambandam, Raghav
Zhang, Xinyao
author_facet Huo, Xinyun
Gnanasambandam, Raghav
Zhang, Xinyao
contents Human-robot collaboration in industrial settings requires precise and reliable communication to enhance operational efficiency. While Large Language Models (LLMs) understand general language, they often lack the domain-specific rigidity needed for safe and executable industrial commands. To address this gap, this paper introduces a novel grammar-constrained LLM that integrates a grammar-driven Natural Language Understanding (NLU) system with a fine-tuned LLM, which enables both conversational flexibility and the deterministic precision required in robotics. Our method employs a two-stage process. First, a fine-tuned LLM performs high-level contextual reasoning and parameter inference on natural language inputs. Second, a Structured Language Model (SLM) and a grammar-based canonicalizer constrain the LLM's output, forcing it into a standardized symbolic format composed of valid action frames and command elements. This process guarantees that generated commands are valid and structured in a robot-readable JSON format. A key feature of the proposed model is a validation and feedback loop. A grammar parser validates the output against a predefined list of executable robotic actions. If a command is invalid, the system automatically generates corrective prompts and re-engages the LLM. This iterative self-correction mechanism allows the model to recover from initial interpretation errors to improve system robustness. We evaluate our grammar-constrained hybrid model against two baselines: a fine-tuned API-based LLM and a standalone grammar-driven NLU model. Using the Human Robot Interaction Corpus (HuRIC) dataset, we demonstrate that the hybrid approach achieves superior command validity, which promotes safer and more effective industrial human-robot collaboration.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04233
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Precise Robot Command Understanding Using Grammar-Constrained Large Language Models
Huo, Xinyun
Gnanasambandam, Raghav
Zhang, Xinyao
Robotics
Computation and Language
Human-robot collaboration in industrial settings requires precise and reliable communication to enhance operational efficiency. While Large Language Models (LLMs) understand general language, they often lack the domain-specific rigidity needed for safe and executable industrial commands. To address this gap, this paper introduces a novel grammar-constrained LLM that integrates a grammar-driven Natural Language Understanding (NLU) system with a fine-tuned LLM, which enables both conversational flexibility and the deterministic precision required in robotics. Our method employs a two-stage process. First, a fine-tuned LLM performs high-level contextual reasoning and parameter inference on natural language inputs. Second, a Structured Language Model (SLM) and a grammar-based canonicalizer constrain the LLM's output, forcing it into a standardized symbolic format composed of valid action frames and command elements. This process guarantees that generated commands are valid and structured in a robot-readable JSON format. A key feature of the proposed model is a validation and feedback loop. A grammar parser validates the output against a predefined list of executable robotic actions. If a command is invalid, the system automatically generates corrective prompts and re-engages the LLM. This iterative self-correction mechanism allows the model to recover from initial interpretation errors to improve system robustness. We evaluate our grammar-constrained hybrid model against two baselines: a fine-tuned API-based LLM and a standalone grammar-driven NLU model. Using the Human Robot Interaction Corpus (HuRIC) dataset, we demonstrate that the hybrid approach achieves superior command validity, which promotes safer and more effective industrial human-robot collaboration.
title Precise Robot Command Understanding Using Grammar-Constrained Large Language Models
topic Robotics
Computation and Language
url https://arxiv.org/abs/2604.04233