Safe Design of Stable Neural Networks for Fault Detection in Small UAVs - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

Safe Design of Stable Neural Networks for Fault Detection in Small UAVs

Abstract

Stability of a machine learning model is the extent to which a model can continue to operate correctly despite small perturbations in its inputs. A formal method to measure stability is the Lipschitz constant of the model which allows to evaluate how small perturbations in the inputs impact the output variations. Variations in the outputs may lead to high errors for regression tasks or unintended changes in the classes for classification tasks. Verification of the stability of ML models is crucial in many industrial domains such as aeronautics, space, automotive etc. It has been recognized that data-driven models are intrinsically extremely sensitive to small perturbation of the inputs. Therefore, the need to design methods for verifying the stability of ML models is of importance for manufacturers developing safety critical products. In this work, we focus on Small Unmanned Aerial Vehicles (UAVs) which are in the frontage of new technology solutions for intelligent systems. However, real-time fault detection/diagnosis in such UAVs remains a challenge from data collection to prediction tasks. This work presents application of neural networks to detect in real-time elevon positioning faults. We show the efficiency of a formal method based on the Lipschitz constant for quantifying the stability of neural network models. We also present how this method can be coupled with spectral normalization constraints at the design phase to control the internal parameters of the model and make it more stable while keeping a high level of performance (accuracy-stability trade-off).
Fichier principal
Vignette du fichier
WAISE_SafeComp.pdf (573.04 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03825404 , version 1 (22-10-2022)

Identifiers

Cite

Kavya Gupta, Fateh Kaakai, Béatrice Pesquet-Popescu, Jean-Christophe Pesquet. Safe Design of Stable Neural Networks for Fault Detection in Small UAVs. SAFECOMP 2022 - The 41st International Conference on Computer Safety, Reliability and Security, Sep 2022, Munich, Germany. pp.263-275, ⟨10.1007/978-3-031-14862-0_19⟩. ⟨hal-03825404⟩
38 View
165 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More