Assurance Guidance for Machine Learning in a Safety-Critical System

被引：3

作者：

Feather, Martin S. ^{[1
]}

Slingerland, Philip C. ^{[2
]}

Guerrini, Steven ^{[1
]}

Spolaor, Max ^{[2
]}

机构：

[1] CALTECH, Jet Prop Lab, Pasadena, CA 91125 USA

[2] Aerosp Corp, El Segundo, CA 90245 USA

来源：

2022 IEEE INTERNATIONAL SYMPOSIUM ON SOFTWARE RELIABILITY ENGINEERING WORKSHOPS (ISSREW 2022) | 2022年

基金：

美国国家航空航天局;

关键词：

assurance; guidance; machine learning; safety;

D O I：

10.1109/ISSREW55968.2022.00098

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

We are developing guidance for space domain assurance personnel on how to assure Artificial intelligence (AI) and Machine Learning (ML) systems. Key to such guidance will be an assurance process for these personnel, who may be unfamiliar with such systems, to follow. We are investigating one such process, the "Assurance of Machine Learning in Autonomous Systems (AMLAS)" from the University of York, UK. To gauge its suitability, we are (retrospectively) applying it to a safety critical AI/ML system in the space domain. We report here on our experience so far in applying this process.

引用

收藏

页码：394 / 401

页数：8

相关论文

共 50 条

[21] Runtime Assurance for Safety-Critical Systems: An Introduction to Safety Filtering Approaches for Complex Control Systems [J].

Hobbs, Kerianne L. ;

Mote, Mark L. ;

Abate, Matthew C. L. ;

Coogan, Samuel D. ;

Feron, Eric M. .

IEEE CONTROL SYSTEMS MAGAZINE, 2023, 43 (02) :28-65

[22] Learning for Safety-Critical Control with Control Barrier Functions [J].

Taylor, Andrew J. ;

Singletary, Andrew ;

Yue, Yisong ;

Ames, Aaron D. .

LEARNING FOR DYNAMICS AND CONTROL, VOL 120, 2020, 120 :708-717

[23] Segmental Stator Switched Reluctance Machine for Safety-Critical Applications [J].

Szabo, Lorand ;

Ruba, Mircea .

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2012, 48 (06) :2223-2229

[24] Deobfuscating Machine Learning Assurance and Approval [J].

Wasson, Kimberly S. ;

Voros, Robert .

2024 AIAA DATC/IEEE 43RD DIGITAL AVIONICS SYSTEMS CONFERENCE, DASC, 2024,

[25] A Safe, Secure, and Predictable Software Architecture for Deep Learning in Safety-Critical Systems [J].

Biondi, Alessandro ;

Nesti, Federico ;

Cicero, Giorgiomaria ;

Casini, Daniel ;

Buttazzo, Giorgio .

IEEE EMBEDDED SYSTEMS LETTERS, 2020, 12 (03) :78-82

[26] A Safety-Critical Decision-Making and Control Framework Combining Machine-Learning-Based and Rule-Based Algorithms [J].

Aksjonov, Andrei ;

Kyrki, Ville .

SAE INTERNATIONAL JOURNAL OF VEHICLE DYNAMICS STABILITY AND NVH, 2023, 7 (03) :287-299

[27] A Systematic Analysis of the Gap Between Academia and Industry Perspectives on Machine Learning Applications in Safety-Critical Systems [J].

Das, Anwesa ;

Kumar, Vinay ;

Hati, Aditya Narayan ;

Bharti, Sharda .

IEEE TRANSACTIONS ON EDUCATION, 2024, 67 (06) :889-896

[28] SPECIFYING A SAFETY-CRITICAL CONTROL-SYSTEM IN Z [J].

JACKY, J .

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 1995, 21 (02) :99-106

[29] On the Necessity of Explicit Artifact Links in Safety Assurance Cases for Machine Learning [J].

Gauerhof, Lydia ;

Gansch, Roman ;

Heinzemann, Christian ;

Woehrle, Matthias ;

Heyl, Andreas .

2021 IEEE INTERNATIONAL SYMPOSIUM ON SOFTWARE RELIABILITY ENGINEERING WORKSHOPS (ISSREW 2021), 2021, :239-244

[30] Safety Assurance of Machine Learning for Chassis Control Functions [J].

Burton, Simon ;

Kurzidem, Iwo ;

Schwaiger, Adrian ;

Schleiss, Philipp ;

Unterreiner, Michael ;

Graeber, Torben ;

Becker, Philipp .

COMPUTER SAFETY, RELIABILITY, AND SECURITY (SAFECOMP 2021), 2021, 12852 :149-162

← 1 2 3 4 5 →