[2310.01802] A Unifying Perspective for Safety of Stochastic Systems: From Barrier Functions to Finite Abstractions

Providing safety guarantees for stochastic dynamical systems is a central problem in various fields, including control theory, machine learning, and robotics. Existing methods either employ Stochastic Barrier Functions (SBFs) or rely on numerical approaches based on finite abstractions. SBFs, analogous to Lyapunov functions, are used to establish (probabilistic) set invariance, whereas abstraction-based approaches approximate the stochastic system with a finite model to compute safety probability bounds. This paper presents a unifying perspective on these seemingly different approaches. Specifically, we show that both methods can be interpreted as approximations of a stochastic dynamic programming problem. This perspective allows us to formally establish the correctness of both techniques, characterize their convergence and optimality properties, and analyze their respective assumptions, advantages, and limitations. Our analysis reveals that, unlike SBFs-based methods, abstraction-based approaches can provide asymptotically optimal safety certificates, albeit at the cost of increased computational effort.

View PDF HTML (experimental) Abstract:Providing safety guarantees for stochastic dynamical systems is a central problem in various fields, including control theory, machine learning, and robotics. Existing methods either employ Stochastic Barrier Functions (SBFs) or rely on numerical approaches based on finite abstractions. SBFs, analogous to Lyapunov functions, are used to establish (probabilistic) set invariance, whereas abstraction-based approaches approximate the stochastic system with a finite model to compute safety probability bounds. This paper presents a unifying perspective on…

saved by

• Gilbert Chang

related reading

• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewarxiv.org
• [2202.11762] Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction Methods for Robotics and Controlar5iv.labs.arxiv.org
• How Complex Systems Failhow.complexsystems.fail
• Updating Robot Safety Representations Online from Natural Language Feedback ∗ Equal Contribution. † Equal Advising. 1School of Engineering, Federal University of Minas Gerais, Brazil. Email: leohmcs@ufmg.br. Work done during Robotics Institarxiv.org
• The Concentration of Invariant Measures for Stochastic Dynamical Systems with Locally Lipschitz Continuous Coefficients in R^darxiv.org
• Stochastic dynamical systems - Scholarpediascholarpedia.org
• Stochastic Stability of Differential Equationslink.springer.com
• A Review of Modern Stochastic Modeling: SDE/SPDE Numerics, Data-Driven Identification, and Generative Methods with Applications in Biology and Epidemiologyarxiv.org
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• Underactuated Roboticsunderactuated.mit.edu
• Regulation_7Nov25.pdfstatic1.squarespace.com
• Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundationsjmlr.org