aiqbench analysis
This research addresses a critical bottleneck in cognitive robotics by using Large Language Models to automatically infer semantic meanings from low-level URDF robot descriptions. The proposed pipeline enhances reliability through majority voting and schema validation, effectively bridging the gap between raw kinematic data and structured ontologies required for explainable human-robot interaction. While presented as preliminary work at ICSR 2026, it demonstrates a viable path toward scalable knowledge representation in embodied AI systems without manual ontology construction.
Extracting Semantics: LLM-Guided Automatic Population of Robot Ontology from URDF
arXiv:2606.17073v1 Announce Type: new Abstract: While commonsense knowledge may suffice for virtual agents, embodied robots interacting with humans require grounded and semantically rich representations of both their environment and their own physical embodiment. In cognitive robotics, ontologies are effective for integrating such heterogeneous knowledge to enable explainable reasoning, even during continuous knowledge updates. Yet, their manual construction remains a bottleneck. We present a preliminary approach for the automatic generation of robot semantic abstractions by transforming Unified Robot Description Format (URDF) models into populated ontologies. Although URDF files provide structural and kinematic descriptions, their identifiers often require commonsense interpretation to recover meaningful semantics, a task at which Large Language Models (LLMs) excel. Our pipeline leverages LLMs to infer semantic relationships by prompting them with concepts from an existing ontology, ensuring the final classification remains aligned with the formal model. To improve reliability, the pipeline combines majority voting across multiple LLM queries along with syntactic and schema-level validation to ensure that generated outputs conform to the expected representation format and ontology constraints. We evaluate the approach on multiple robot descriptions and discuss the generated abstractions. Initial results indicate that the proposed method can effectively bridge the gap between low-level robot descriptions and the structured, grounded knowledge representations required for human-robot interaction.
Abstract:While commonsense knowledge may suffice for virtual agents, embodied robots interacting with humans require grounded and semantically rich representations of both their environment and their own physical embodiment. In cognitive robotics, ontologies are effective for integrating such heterogeneous knowledge to enable explainable reasoning, even during continuous knowledge updates. Yet, their manual construction remains a bottleneck. We present a preliminary approach for the automatic generation of robot semantic abstractions by transforming Unified Robot Description Format (URDF) models into populated ontologies. Although URDF files provide structural and kinematic descriptions, their identifiers often require commonsense interpretation to recover meaningful semantics, a task at which Large Language Models (LLMs) excel. Our pipeline leverages LLMs to infer semantic relationships by prompting them with concepts from an existing ontology, ensuring the final classification remains aligned with the formal model. To improve reliability, the pipeline combines majority voting across multiple LLM queries along with syntactic and schema-level validation to ensure that generated outputs conform to the expected representation format and ontology constraints. We evaluate the approach on multiple robot descriptions and discuss the generated abstractions. Initial results indicate that the proposed method can effectively bridge the gap between low-level robot descriptions and the structured, grounded knowledge representations required for human-robot interaction.
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2606.17073 [cs.RO]
(or arXiv:2606.17073v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.17073 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 298 words
Related coverage
Multimodal Plant Root Phenotyping with Integration of 3D Skeleton Extraction and Language Analysis
arXiv · Aug 5, 2026
Problems of Proliferation
LessWrong · Sep 29, 2026
Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning
arXiv · Oct 8, 2026
Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments
arXiv · Aug 7, 2026