Controller Synthesis for Autonomous Systems With Deep-Learning Perception Components

Radu Călinescu

doi:10.1109/TSE.2024.3385378

Controller Synthesis for Autonomous Systems With Deep-Learning Perception Components

2024-06-01

0

OA

AI

Genaína Nunes Rodrigues

C

Corina S. Păsăreanu

M

Misael Alpizar Santana

G

Gricel Vázquez

DOI：10.1109/TSE.2024.3385378

原文链接

原文求助

摘要

En 中文

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.

Keyword:

Discrete-event controller synthesis

Markov model

deep neural network

uncertainty quantification

neuro-symbolic AI

Controller Synthesis for Autonomous Systems With Deep-Learning Perception Components

摘要

期刊

机构