Formal Verification and Control with Conformal Prediction

2024-08-31

arXiv.org

AI Summary

Traditional model-based verification and safety control methods fail for learning-enabled autonomous systems (LEAS) due to the inherent complexity and opacity of learning-enabled components (LECs). Method: This paper proposes the first model-free, unified framework for formal verification and safety control of LEAS, grounded in conformal prediction (CP). The framework enables distribution-free, real-time, and interpretable uncertainty quantification without requiring system models. Contribution/Results: It establishes, for the first time, a rigorous theoretical foundation for CP in formal verification, safety-critical control, and robotic task execution—integrating linear temporal logic (LTL), neural network input-output verification, and scenario-based optimization. Evaluated on navigation tasks, the framework achieves high-accuracy offline and online verification with provably safe, computationally efficient, and statistically guaranteed control. This work introduces a novel safety assurance paradigm for LEAS that bridges formal rigor and practical deployability.

Technology Category

• Natural Language Processing: Safety and Robustness
• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements

Abstract

In this survey, we design formal verification and control algorithms for autonomous systems with practical safety guarantees using conformal prediction (CP), a statistical tool for uncertainty quantification. We focus on learning-enabled autonomous systems (LEASs) in which the complexity of learning-enabled components (LECs) is a major bottleneck that hampers the use of existing model-based verification and design techniques. Instead, we advocate for the use of CP, and we will demonstrate its use in formal verification, systems and control theory, and robotics. We argue that CP is specifically useful due to its simplicity (easy to understand, use, and modify), generality (requires no assumptions on learned models and data distributions, i.e., is distribution-free), and efficiency (real-time capable and accurate). We pursue the following goals with this survey. First, we provide an accessible introduction to CP for non-experts who are interested in using CP to solve problems in autonomy. Second, we show how to use CP for the verification of LECs, e.g., for verifying input-output properties of neural networks. Third and fourth, we review recent articles that use CP for safe control design as well as offline and online verification of LEASs. We summarize their ideas in a unifying framework that can deal with the complexity of LEASs in a computationally efficient manner. In our exposition, we consider simple system specifications, e.g., robot navigation tasks, as well as complex specifications formulated in temporal logic formalisms. Throughout our survey, we compare to other statistical techniques (e.g., scenario optimization, PAC-Bayes theory, etc.) and how these techniques have been used in verification and control. Lastly, we point the reader to open problems and future research directions.

Problem

• Design formal verification for autonomous systems using conformal prediction
• Address complexity of learning-enabled components in verification
• Apply CP for safe control and real-time uncertainty quantification

Innovation

• Uses conformal prediction for uncertainty quantification
• Applies CP to formal verification and control
• Focuses on learning-enabled autonomous systems