Probabilistic Model Checking and Autonomy

Kwiatkowska, Marta; Norman, Gethin; Parker, David

doi:10.1146/annurev-control-042820-010947

Cited by 15 publications

(4 citation statements)

References 125 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Formal verification. To formally verify M θ , we implemented a value iteration (VI) engine, handling the neural network encoding of the latent space for discounted properties, which is one of the most popular algorithms for checking property probabilities in MDPs (e.g., Baier & Katoen 2008;Hensel et al 2021;Kwiatkowska et al 2022). We verify time-to-failure properties ϕ, often used to check the failure rate of a system (Pnueli, 1977) by measuring whether the agent fails before the end of the episode.…”

Section: Methodsmentioning

confidence: 99%

Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes

Delgrange

Nowé

Pérez

2022

AAAI

View full text Add to dashboard Cite

We consider the challenge of policy simplification and verification in the context of policies learned through reinforcement learning (RL) in continuous environments. In well-behaved settings, RL algorithms have convergence guarantees in the limit. While these guarantees are valuable, they are insufficient for safety-critical applications. Furthermore, they are lost when applying advanced techniques such as deep-RL. To recover guarantees when applying advanced RL algorithms to more complex environments with (i) reachability, (ii) safety-constrained reachability, or (iii) discounted-reward objectives, we build upon the DeepMDP framework to derive new bisimulation bounds between the unknown environment and a learned discrete latent model of it. Our bisimulation bounds enable the application of formal methods for Markov decision processes. Finally, we show how one can use a policy obtained via state-of-the-art RL to efficiently train a variational autoencoder that yields a discrete latent model with provably approximately correct bisimulation guarantees. Additionally, we obtain a distilled version of the policy for the latent model.

show abstract

Section: Methodsmentioning

confidence: 99%

Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes

Delgrange

Nowé

Pérez

2022

AAAI

View full text Add to dashboard Cite

show abstract

“…Probabilistic model checkers have been developed for discrete-time discrete-state fully observed Markov decision processes (MDP) and partially observed Markov decision processes (POMDP) [12], [13], [14], [15], [16], and have gained success in applications of control synthesis with probabilistic temporal logics [17], [18], [19], [20].…”

Section: A Related Workmentioning

confidence: 99%

Robustly Complete Finite-State Abstractions for Verification of Stochastic Systems

Meng

Liu

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The essential step of abstraction-based control synthesis for nonlinear systems to satisfy a given specification is to obtain a finite-state abstraction of the original systems. The complexity of the abstraction is usually the dominating factor that determines the efficiency of the algorithm. For the control synthesis of discrete-time nonlinear stochastic systems modelled by nonlinear stochastic difference equations, recent literature has demonstrated the soundness of abstractions in preserving robust probabilistic satisfaction of ω-regular lineartime properties. However, unnecessary transitions exist within the abstractions, which are difficult to quantify, and the completeness of abstraction-based control synthesis in the stochastic setting remains an open theoretical question. In this paper, we address this fundamental question from the topological view of metrizable space of probability measures, and propose constructive finite-state abstractions for control synthesis of probabilistic linear temporal specifications. Such abstractions are both sound and approximately complete. That is, given a concrete discrete-time stochastic system and an arbitrarily small L 1 -perturbation of this system, there exists a family of finite-state controlled Markov chains that both abstracts the concrete system and is abstracted by the slightly perturbed system. In other words, given an arbitrarily small prescribed precision, an abstraction always exists to decide whether a control strategy exists for the concrete system to satisfy the probabilistic specification.

show abstract

“…Our framework is underpinned by probabilistic model checking, a technique that is broadly used to assess quantitative properties, e.g., reliability, performance and energy cost of systems exhibiting stochastic behaviour. Such systems include autonomous robots from numerous domains 16 , e.g., mobile service robots 17 , spacecraft 18 , drones 19 and robotic swarms 20 . While we present a case study involving an autonomous underwater vehicle (AUV), the generalisability of our approach stems from the broad adoption of probabilistic model checking for the modelling and verification of this wide range of autonomous robots.…”

Section: Introductionmentioning

confidence: 99%

Bayesian learning for the robust verification of autonomous robots

Zhao,

Gerasimou,

Calinescu

et al. 2024

Commun Eng

View full text Add to dashboard Cite

Autonomous robots used in infrastructure inspection, space exploration and other critical missions operate in highly dynamic environments. As such, they must continually verify their ability to complete the tasks associated with these missions safely and effectively. Here we present a Bayesian learning framework that enables this runtime verification of autonomous robots. The framework uses prior knowledge and observations of the verified robot to learn expected ranges for the occurrence rates of regular and singular (e.g., catastrophic failure) events. Interval continuous-time Markov models defined using these ranges are then analysed to obtain expected intervals of variation for system properties such as mission duration and success probability. We apply the framework to an autonomous robotic mission for underwater infrastructure inspection and repair. The formal proofs and experiments presented in the paper show that our framework produces results that reflect the uncertainty intrinsic to many real-world systems, enabling the robust verification of their quantitative properties under parametric uncertainty.

show abstract

Probabilistic Model Checking and Autonomy

Cited by 15 publications

References 125 publications

Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes

Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes

Robustly Complete Finite-State Abstractions for Verification of Stochastic Systems

Bayesian learning for the robust verification of autonomous robots

Contact Info

Product

Resources

About