Universal Safety Controllers with Learned Prophecies

2025-11-14

AI Summary

To address the high computational complexity of precisely computing and verifying prophecies in Universal Safety Controllers (USCs), this paper proposes a learning-based symbolic approach: leveraging small-scale system traces, it automatically learns upper and lower symbolic approximations of prophecies and induces them into concise, human-interpretable CTL formulas. The method integrates Computation Tree Logic (CTL), formal verification, tree automata approximation, and supervised learning to achieve symbolic prophecy learning and logical induction. Experiments demonstrate that the learned prophecies exhibit strong generalization across unseen systems, yield more compact and interpretable representations than conventional tree automata constructions, and significantly reduce verification overhead. The core contribution is the first integration of logical induction with machine learning to generate provably safe, computationally efficient, and semantically transparent prophecy approximations.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

emph{Universal Safety Controllers (USCs)} are a promising logical control framework that guarantees the satisfaction of a given temporal safety specification when applied to any realizable plant model. Unlike traditional methods, which synthesize one logical controller over a given detailed plant model, USC synthesis constructs a emph{generic controller} whose outputs are conditioned by plant behavior, called emph{prophecies}. Thereby, USCs offer strong generalization and scalability benefits over classical logical controllers. However, the exact computation and verification of prophecies remain computationally challenging. In this paper, we introduce an approximation algorithm for USC synthesis that addresses these limitations via learning. Instead of computing exact prophecies, which reason about sets of trees via automata, we only compute under- and over-approximations from (small) example plants and infer computation tree logic (CTL) formulas as representations of prophecies. The resulting USC generalizes to unseen plants via a verification step and offers improved efficiency and explainability through small and concise CTL prophecies, which remain human-readable and interpretable. Experimental results demonstrate that our learned prophecies remain generalizable, yet are significantly more compact and interpretable than their exact tree automata representations.

Problem

• Universal Safety Controllers synthesize generic controllers using plant behavior prophecies
• Exact prophecy computation remains computationally challenging for verification
• Learning approximate CTL prophecies improves efficiency, generalization and interpretability

Innovation

• Universal Safety Controllers with learned prophecies
• Approximating prophecies via CTL formula inference
• Generalizable controllers with compact interpretable prophecies