Polynomial-Time Reachability for LTI Systems with Two-Level Lattice Neural Network Controllers

09/20/2022
by   James Ferlez, et al.
7

In this paper, we consider the computational complexity of bounding the reachable set of a Linear Time-Invariant (LTI) system controlled by a Rectified Linear Unit (ReLU) Two-Level Lattice (TLL) Neural Network (NN) controller. In particular, we show that for such a system and controller, it is possible to compute the exact one-step reachable set in polynomial time in the size of the size of the TLL NN controller (number of neurons). Additionally, we show that it is possible to obtain a tight bounding box of the reachable set via two polynomial-time methods: one with polynomial complexity in the size of the TLL and the other with polynomial complexity in the Lipschitz constant of the controller and other problem parameters. Crucially, the smaller of the two can be decided in polynomial time for non-degenerate TLL NNs. Finally, we propose a pragmatic algorithm that adaptively combines the benefits of (semi-)exact reachability and approximate reachability, which we call L-TLLBox. We evaluate L-TLLBox with an empirical comparison to a state-of-the-art NN controller reachability tool. In these experiments, L-TLLBox was able to complete reachability analysis as much as 5000x faster than this tool on the same network/system, while producing reach boxes that were from 0.08 to 1.42 times the area.

READ FULL TEXT
research
12/22/2020

Bounding the Complexity of Formally Verifying Neural Networks: A Geometric Approach

In this paper, we consider the computational complexity of formally veri...
research
10/31/2018

Formal Verification of Neural Network Controlled Autonomous Systems

In this paper, we consider the problem of formally verifying the safety ...
research
07/09/2022

Efficient Backward Reachability Using the Minkowski Difference of Constrained Zonotopes

Backward reachability analysis is essential to synthesizing controllers ...
research
09/13/2022

Verified Compositions of Neural Network Controllers for Temporal Logic Control Objectives

This paper presents a new approach to design verified compositions of Ne...
research
11/17/2021

Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networks

In this paper, we present the tool Fast Box Analysis of Two-Level Lattic...
research
06/21/2023

Polynomial Logical Zonotopes: A Set Representation for Reachability Analysis of Logical Systems

In this paper, we introduce a set representation called polynomial logic...
research
09/21/2021

Assured Neural Network Architectures for Control and Identification of Nonlinear Systems

In this paper, we consider the problem of automatically designing a Rect...

Please sign up or login with your details

Forgot password? Click here to reset