Formal verification of neural networks is a promising technique to improve their dependability for safety critical applications. Autonomous driving is one such application where the controllers supervising different functions in a car should undergo a rigorous certification process. In this pa- per we present an example about learning and verification of an adaptive cruise control function on an autonomous car. We detail the learning process as well as the attempts to ver- ify various safety properties using the tool NEVER2, a new framework that integrates learning and verification in a sin- gle easy-to-use package intended for practictioners rather than experts in formal methods and/or machine learning.
Formal Verification of Neural Networks: a Case Study about Adaptive Cruise Control
Demarchi, Stefano;Guidotti, Dario;Tacchella, Armando
2022-01-01
Abstract
Formal verification of neural networks is a promising technique to improve their dependability for safety critical applications. Autonomous driving is one such application where the controllers supervising different functions in a car should undergo a rigorous certification process. In this pa- per we present an example about learning and verification of an adaptive cruise control function on an autonomous car. We detail the learning process as well as the attempts to ver- ify various safety properties using the tool NEVER2, a new framework that integrates learning and verification in a sin- gle easy-to-use package intended for practictioners rather than experts in formal methods and/or machine learning.File | Dimensione | Formato | |
---|---|---|---|
main.pdf
accesso aperto
Descrizione: Contributo in atti di convegno
Tipologia:
Documento in Post-print
Dimensione
3.99 MB
Formato
Adobe PDF
|
3.99 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.