Learning Safe Neural Network Controllers with Barrier Certificates

09/18/2020
by   Hengjun Zhao, et al.
7

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

12/20/2019

Learning for Safety-Critical Control with Control Barrier Functions

Modern nonlinear control theory seeks to endow systems with properties o...
06/16/2020

ShieldNN: A Provably Safe NN Filter for Unsafe NN Controllers

In this paper, we consider the problem of creating a safe-by-design Rect...
12/31/2018

Gray-box Adversarial Testing for Control Systems with Machine Learning Component

Neural Networks (NN) have been proposed in the past as an effective mean...
01/10/2019

Automated Synthesis of Safe Digital Controllers for Sampled-Data Stochastic Nonlinear Systems

We present a new method for the automated synthesis of digital controlle...
10/30/2020

Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions

Modern nonlinear control theory seeks to develop feedback controllers th...
09/03/2021

Provably Safe Model-Based Meta Reinforcement Learning: An Abstraction-Based Approach

While conventional reinforcement learning focuses on designing agents th...
07/07/2020

Automated Formal Synthesis of Neural Barrier Certificates for Dynamical Models

We introduce an automated, formal, counterexample-based approach to synt...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.