DeepAI AI Chat
Log In Sign Up

Learning Safe Neural Network Controllers with Barrier Certificates

by   Hengjun Zhao, et al.

We provide a novel approach to synthesize controllers for nonlinear continuous dynamical systems with control against safety properties. The controllers are based on neural networks (NNs). To certify the safety property we utilize barrier functions, which are represented by NNs as well. We train the controller-NN and barrier-NN simultaneously, achieving a verification-in-the-loop synthesis. We provide a prototype tool nncontroller with a number of case studies. The experiment results confirm the feasibility and efficacy of our approach.


page 1

page 2

page 3

page 4


Differentiable Safe Controller Design through Control Barrier Functions

Learning-based controllers, such as neural network (NN) controllers, can...

ShieldNN: A Provably Safe NN Filter for Unsafe NN Controllers

In this paper, we consider the problem of creating a safe-by-design Rect...

Quantifying Safety of Learning-based Self-Driving Control Using Almost-Barrier Functions

Path-tracking control of self-driving vehicles can benefit from deep lea...

Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions

Neural Networks (NNs) have been successfully employed to represent the s...

Safe Control Under Input Limits with Neural Control Barrier Functions

We propose new methods to synthesize control barrier function (CBF)-base...

Risk-Awareness in Learning Neural Controllers for Temporal Logic Objectives

In this paper, we consider the problem of synthesizing a controller in t...

A General Verification Framework for Dynamical and Control Models via Certificate Synthesis

An emerging branch of control theory specialises in certificate learning...