Controller Synthesis for Autonomous Systems with Deep-Learning Perception Components

Radu Calinescu, Calum Corrie Imrie, Ravi Mangal, Genaina Rodrigues, Corina S.Păsăreanu, Misael Alpizar Santana, Gricel Vazquez Flores

Research output: Contribution to journalArticlepeer-review

Abstract

We present DeepDECS, a new method for the synthesis of correct-by-construction software controllers for autonomous systems that use deep neural network (DNN) classifiers for the perception step of their decision-making processes. Despite major advances in deep learning in recent years, providing safety guarantees for these systems remains very challenging. Our controller synthesis method addresses this challenge by integrating DNN verification with the synthesis of verified Markov models. The synthesised models correspond to discrete-event software controllers guaranteed to satisfy the safety, dependability and performance requirements of the autonomous system, and to be Pareto optimal with respect to a set of optimisation objectives. We evaluate the method in simulation by using it to synthesise controllers for mobile-robot collision limitation, and for maintaining driver attentiveness in shared-control autonomous driving.
Original languageEnglish
JournalIEEE Transactions on Software Engineering
Publication statusAccepted/In press - 26 Mar 2024

Bibliographical note

This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy.

Keywords

  • discrete-event controller synthesis
  • Markov model
  • deep neural network
  • uncertainty quantification
  • neuro-symbolic AI

Cite this