Sign in to unlock AI Chat and more features

Falsification of Learning-Based Controllers through Multi-Fidelity Bayesian Optimization

Abstract
Simulation-based falsification is a practical testing method to increase confidence that the system will meet safety requirements. Because full-fidelity simulations can be computationally demanding, we investigate the use of simulators with different levels of fidelity. As a first step, we express the overall safety specification in terms of environment parameters and structure this safety specifi...
View PDF
Keywords
Fidelity
Bayesian optimization
Computer science
High fidelity
Bayesian probability
Machine learning
Artificial intelligence
Engineering
Telecommunications
Electrical engineering
Sustainable Development Goals (SDG)
Peace, justice, and strong institutions


pdf file

Falsification of Learning-Based Controllers through Multi-Fidelity Bayesian Optimization
pdf file

Falsification of Learning-Based Controllers through Multi-Fidelity Bayesian Optimization

Abstract
Simulation-based falsification is a practical testing method to increase confidence that the system will meet safety requirements. Because full-fidelity simulations can be computationally demanding, we investigate the use of simulators with different levels of fidelity. As a first step, we express the overall safety specification in terms of environment parameters and structure this safety specifi...
View PDF
Keywords
Fidelity
Bayesian optimization
Computer science
High fidelity
Bayesian probability
Machine learning
Artificial intelligence
Engineering
Telecommunications
Electrical engineering
Sustainable Development Goals (SDG)
Peace, justice, and strong institutions


pdf file