Taxonomy-Agnostic Neurosymbolic Grounding of Robot Kinematics
Taxonomy-Agnostic Neurosymbolic Grounding of Robot Kinematics
This paper introduces URDF2Ontology, an automated neurosymbolic framework that transforms raw Unified Robot Description Format (URDF) files into populated OWL ontologies. The system leverages a Large Language Model for semantic reasoning and employs a morphology-aware dual-track architecture to handle complex kinematic structures. Empirical evaluations on a diverse fleet of robots demonstrate effective schema alignment and structural extraction, significantly reducing the need for manual domain authoring.
The authors propose URDF2Ontology, a framework that uses an LLM and graph-purging to convert standard URDF files into grounded OWL ontologies, claiming reduced manual overhead in empirical evaluations across heterogeneous robots.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
lic guardrails, the framework extracts functional sub-graphs and asserts populated ontologies aligned with arbitrary user-provided taxonomies. Empirical evaluation across a diverse fleet of heterogeneous robots demonstrates strong schema alignment, valid structural extraction, and a significant reduction in manual domain authoring overhead.
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org