Approach for Argumenting Safety on Basis of an Operational Design Domain
The Operational Design Domain (ODD) is a representative model of the real world in which an Automated Driving System (ADS) is intended to operate. The definition of the ODD is a crucial part of the development process for such an artificial intelligence (AI)-enabled system. This is due to the fact that the ODD is the basis for several critical development activities, like defining system-level requirements, test & verification, and building a well-founded safety case for an AI-based ADS. Since an inadequately defined ODD poses a major safety concern for the entire development, an ODD must be defined completely and consistently during the development process. In this work, we present an approach for the ODD definition and maintenance during the development of safety-critical AI-based ADS functionalities and provide evidences to argue the sufficient completeness and consistency. We demonstrate the feasibility of our approach by an industrial use case of a fully automated system in the railway domain.
Sun 14 AprDisplayed time zone: Lisbon change
11:00 - 12:30 | Architecting, Designing, Managing, and Modeling AI-Enabled SystemsIndustry Talks / Research and Experience Papers at Pequeno Auditório Chair(s): Nicolás Cardozo Universidad de los Andes | ||
11:00 10mTalk | A Taxonomy of Foundation Model based Systems through the Lens of Software Architecture Research and Experience Papers Qinghua Lu Data61, CSIRO, Liming Zhu CSIRO’s Data61, Xiwei (Sherry) Xu Data61, CSIRO, Yue Liu CSIRO's Data61 & University of New South Wales, Zhenchang Xing CSIRO's Data61, Jon Whittle CSIRO's Data61 and Monash University | ||
11:10 15mTalk | Investigating the Impact of Solid Design Principles on Machine Learning Code UnderstandingDistinguished paper Award Candidate Research and Experience Papers Raphael Cabral Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Marcos Kalinowski Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Maria Teresa Baldassarre Department of Computer Science, University of Bari , Hugo Villamizar Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Tatiana Escovedo Pontifical Catholic University of Rio de Janeiro, Helio Côrtes Vieira Lopes PUC-Rio Pre-print | ||
11:25 10mIndustry talk | KnowING Intelligent Document Classification: A Deep Dive into Microservices and Efficient Models at ING Industry Talks A: Andrew Rutherfoord CWI; University of Groningen, A: Gert Vermeer , Andrea Capiluppi Brunel University | ||
11:35 15mTalk | An Exploratory Study of V-Model in Building ML-Enabled Software: A Systems Engineering PerspectiveDistinguished paper Award Candidate Research and Experience Papers Jie JW Wu University of British Columbia (UBC) Pre-print | ||
11:50 10mIndustry talk | Engineering Challenges in Industrial AI Industry Talks | ||
12:00 10mTalk | Approach for Argumenting Safety on Basis of an Operational Design Domain Research and Experience Papers Gereon Weiss Fraunhofer IKS, Marc Zeller Siemens AG, Hannes Schoenhaar Siemens Corporate Technology, Christian Drabek Fraunhofer Institute for Cognitive Systems IKS, Andreas Kreutz Fraunhofer Institute for Cognitive Systems IKS | ||
12:10 15mTalk | The Impact of Knowledge Distillation on the Performance and Energy Consumption of NLP Models Research and Experience Papers Ye Yuan Vrije Universiteit Amsterdam, Jiacheng Shi Vrije Universiteit Amsterdam, Zongyao Zhang Vrije Universiteit Amsterdam, Kaiwei Chen Vrije Universiteit Amsterdam, Eloise Zhang Vrije Universiteit Amsterdam, Vincenzo Stoico Vrije Universiteit Amsterdam, Ivano Malavolta Vrije Universiteit Amsterdam |