Approximate Conformance Checking for Closed-Loop Systems With Neural Network Controllers

Habeeb, P and Gupta, L and Prabhakar, P (2024) Approximate Conformance Checking for Closed-Loop Systems With Neural Network Controllers. In: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 43 (11). pp. 4322-4333.

PDF IEE_Tra_Com_Aid_Des_Int_Cir_Sys_2024.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

In this article, we consider the problem of checking approximate conformance of closed-loop systems with the same plant but different neural network (NN) controllers. First, we introduce a notion of approximate conformance on NNs, which allows us to quantify semantically the deviations in closed-loop system behaviors with different NN controllers. Next, we consider the problem of computationally checking this notion of approximate conformance on two NNs. We reduce this problem to that of reachability analysis on a combined NN, thereby, enabling the use of existing NN verification tools for conformance checking. Our experimental results on an autonomous rocket landing system demonstrate the feasibility of checking approximate conformance on different NNs trained for the same dynamics, as well as the practical semantic closeness exhibited by the corresponding closed-loop systems. © 2024 IEEE.

Item Type:	Journal Article
Publication:	IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to the Publisher.
Keywords:	Neural networks; Rockets, Closed-loop system; Combined neural networks; Conformance checking; Landing system; Neural network controllers; Neural-networks; Reachability analysis; System behaviors; Verification tools, Closed loop control systems
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	09 Dec 2024 16:39
Last Modified:	09 Dec 2024 16:39
URI:	http://eprints.iisc.ac.in/id/eprint/87065

Actions (login required)

View Item