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.
2022
9783937436777
File in questo prodotto:
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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/1094835
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? ND
social impact