ShieldNN: A Provably Safe NN Filter for Unsafe NN Controllers

by   James Ferlez, et al.

In this paper, we consider the problem of creating a safe-by-design Rectified Linear Unit (ReLU) Neural Network (NN), which, when composed with an arbitrary control NN, makes the composition provably safe. In particular, we propose an algorithm to synthesize such NN filters that safely correct control inputs generated for the continuous-time Kinematic Bicycle Model (KBM). ShieldNN contains two main novel contributions: first, it is based on a novel Barrier Function (BF) for the KBM model; and second, it is itself a provably sound algorithm that leverages this BF to a design a safety filter NN with safety guarantees. Moreover, since the KBM is known to well approximate the dynamics of four-wheeled vehicles, we show the efficacy of ShieldNN filters in CARLA simulations of four-wheeled vehicles. In particular, we examined the effect of ShieldNN filters on Deep Reinforcement Learning trained controllers in the presence of individual pedestrian obstacles. The safety properties of ShieldNN were borne out in our experiments: the ShieldNN filter reduced the number of obstacle collisions by 99.4 incorporating ShieldNN during training: for a constant number of episodes, 28 less reward was observed when ShieldNN wasn't used during training. This suggests that ShieldNN has the further property of improving sample efficiency during RL training.


Learning Safe Neural Network Controllers with Barrier Certificates

We provide a novel approach to synthesize controllers for nonlinear cont...

Safety Filter Design for Neural Network Systems via Convex Optimization

With the increase in data availability, it has been widely demonstrated ...

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

While conventional reinforcement learning focuses on designing agents th...

EnergyShield: Provably-Safe Offloading of Neural Network Controllers for Energy Efficiency

To mitigate the high energy demand of Neural Network (NN) based Autonomo...

Synthesize Efficient Safety Certificates for Learning-Based Safe Control using Magnitude Regularization

Energy-function-based safety certificates can provide provable safety gu...

Safe Robot Learning in Assistive Devices through Neural Network Repair

Assistive robotic devices are a particularly promising field of applicat...

Verified Compositions of Neural Network Controllers for Temporal Logic Control Objectives

This paper presents a new approach to design verified compositions of Ne...

Please sign up or login with your details

Forgot password? Click here to reset