Extracting counterexamples induced by safety violation in linear hybrid systems

Goyal, Manish; Duggirala, Parasara Sridhar

doi:10.1016/j.automatica.2020.109005

Cited by 4 publications

(2 citation statements)

References 61 publications

(80 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…for the set of reachable states. While these techniques are useful for proving that the safety specification is satisfied, some other recent works [25], [26] have explored using reachability analysis to generate counterexamples of interest.…”

Section: Related Workmentioning

confidence: 99%

NExG: Provable and Guided State Space Exploration of Neural Network Control Systems using Sensitivity Approximation

Goyal¹,

Dewaskar²,

Duggirala³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a new technique for performing state space exploration of closed loop control systems with neural network feedback controllers. Our approach involves approximating the sensitivity of the trajectories of the closed loop dynamics. Using such an approximator and the system simulator, we present a guided state space exploration method that can generate trajectories visiting the neighborhood of a target state at a specified time. We present a theoretical framework which establishes that our method will produce a sequence of trajectories that will reach a suitable neighborhood of the target state. We provide thorough evaluation of our approach on various systems with neural network feedback controllers of different configurations. We outperform earlier state space exploration techniques and achieve significant improvement in both the quality (explainability) and performance (convergence rate). Finally, we adopt our algorithm for the falsification of a class of temporal logic specification, assess its performance against a state-of-the-art falsification tool, and show its potential in supplementing existing falsification algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

NExG: Provable and Guided State Space Exploration of Neural Network Control Systems using Sensitivity Approximation

Goyal¹,

Dewaskar²,

Duggirala³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…These techniques use a symbolic representation for the reachable set of states. While these are useful for proving that the safety specification is satisfied, generating counterexamples using reachability analysis is still an area of research [24,26].…”

Section: Related Workmentioning

confidence: 99%

NeuralExplorer: State Space Exploration of Closed Loop Control Systems Using Neural Networks

Goyal¹,

Duggirala²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a framework for performing state space exploration of closed loop control systems. Our approach involves approximating sensitivity and a newly introduced notion of inverse sensitivity by a neural network. We show how the approximation of sensitivity and inverse sensitivity can be used for computing estimates of the reachable set. We then outline algorithms for performing state space exploration by generating trajectories that reach a neighborhood. We demonstrate the effectiveness of our approach by applying it not only to standard linear and nonlinear dynamical systems, but also to nonlinear hybrid systems and also neural network based feedback control systems.

show abstract

Falsification of hybrid systems with symbolic reachability analysis and trajectory splicing

Bogomolov

Frehse

Gurung

et al. 2021

Nonlinear Analysis: Hybrid Systems

View full text Add to dashboard Cite

Extracting counterexamples induced by safety violation in linear hybrid systems

Cited by 4 publications

References 61 publications

NExG: Provable and Guided State Space Exploration of Neural Network Control Systems using Sensitivity Approximation

NExG: Provable and Guided State Space Exploration of Neural Network Control Systems using Sensitivity Approximation

NeuralExplorer: State Space Exploration of Closed Loop Control Systems Using Neural Networks

Falsification of hybrid systems with symbolic reachability analysis and trajectory splicing

Contact Info

Product

Resources

About