World2Rules: A Neuro-Symbolic Framework for Learning World-Governing Safety Rules for Aviation

View PDF HTML (experimental)

Abstract:Many real-world safety-critical systems are governed by explicit rules that define unsafe world configurations and constrain agent interactions. In practice, these rules are complex and context-dependent, making manual specification incomplete and error-prone. Learning such rules from real-world multimodal data is further challenged by noise, inconsistency, and sparse failure cases. Neural models can extract structure from text and visual data but lack formal guarantees, while symbolic methods provide verifiability yet are brittle when applied directly to imperfect observations. We present World2Rules, a neuro-symbolic framework for learning world-governing safety rules from real-world multimodal aviation data. World2Rules learns from both nominal operational data and aviation crash and incident reports, treating neural models as proposal mechanisms for candidate symbolic facts and inductive logic programming as a verification layer. The framework employs hierarchical reflective reasoning, enforcing consistency across examples, subsets, and rules to filter unreliable evidence, aggregate only mutually consistent components, and prune unsupported hypotheses. This design limits error propagation from noisy neural extractions and yields compact, interpretable first-order logic rules that characterize unsafe world configurations. We evaluate World2Rules on real-world aviation safety data and show that it learns rules that achieve 23.6% higher F1 score than purely neural and 43.2% higher F1 score than single-pass neuro-symbolic baseline, while remaining suitable for safety-critical reasoning and formal analysis.

Comments: 19 pages, 6 figures

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2603.28952 [cs.RO]

(or arXiv:2603.28952v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2603.28952

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Haichuan Wang [view email] [v1] Mon, 30 Mar 2026 19:48:03 UTC (6,625 KB)