Conservative Safety Monitors of Stochastic Dynamical Systems

01/26/2023
by   Matthew Cleaveland, et al.
0

Generating accurate runtime safety estimates for autonomous systems is vital to ensuring their continued proliferation. However, exhaustive reasoning about future behaviors is generally too complex to do at runtime. To provide scalable and formal safety estimates, we propose a method for leveraging design-time model checking results at runtime. Specifically, we model the system as a probabilistic automaton (PA) and compute bounded-time reachability probabilities over the states of the PA at design time. At runtime, we combine distributions of state estimates with the model checking results to produce a bounded time safety estimate. We argue that our approach produces well-calibrated safety probabilities, assuming the estimated state distributions are well-calibrated. We evaluate our approach on simulated water tanks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/04/2021

Monotonic Safety for Scalable and Data-Efficient Probabilistic Safety Analysis

Autonomous systems with machine learning-based perception can exhibit un...
research
07/17/2020

PAC Model Checking of Black-Box Continuous-Time Dynamical Systems

In this paper we present a novel model checking approach to finite-time ...
research
05/26/2021

Runtime Monitoring for Markov Decision Processes

We investigate the problem of monitoring partially observable systems wi...
research
11/16/2018

Quantifying Attacker Capability Via Model Checking Multiple Properties (Extended Version)

This work aims to solve a practical problem, i.e., how to quantify the r...
research
06/01/2022

Formal Analysis of Lending Pools in Decentralized Finance

Decentralised Finance (DeFi) applications constitute an entire financial...
research
12/10/2018

Probabilistic Model Checking of Robots Deployed in Extreme Environments

Robots are increasingly used to carry out critical missions in extreme e...
research
04/03/2018

A Learning Approach to Enhance Assurances for Real-Time Self-Adaptive Systems

The assurance of real-time properties is prone to context variability. P...

Please sign up or login with your details

Forgot password? Click here to reset