Results 51 to 60 of about 276 (160)
Safety Monitoring of Machine Learning Perception Functions: A Survey
ABSTRACT Machine Learning (ML) models, such as deep neural networks, are widely applied in autonomous systems to perform complex perception tasks. New dependability challenges arise when ML predictions are used in safety‐critical applications, like autonomous cars and surgical robots. Thus, the use of fault tolerance mechanisms, such as safety monitors,
Raul Sena Ferreira +4 more
wiley +1 more source
Field Testing of ADAS Technologies in Naturalistic Driving Conditions
This paper evaluates Advanced Driver Assistance Systems (ADASs) in test scenarios derived from naturalistic driving and crash data, mapped to ISO 26262, ISO/PAS 21448 (SOTIF), and ISO 34502.
Adam Skokan
doaj +1 more source
Model‐based systems engineering and safety assessment: A workflow for mechatronic systems design
Abstract Mechatronic systems become ever more complex because of their increasing number of interconnected safety critical components and sophistication. MBSE (Model‐based Systems Engineering) and MBSA (Model‐Based Safety Assessment) are the most commonly adopted approaches to deal with the design and safety analysis of mechatronic systems ...
Imane Bouhali +6 more
wiley +1 more source
We propose an evaluation metric for communication status that classifies the communication delay as passive, additive, and temporary communication delay and an asynchronous delay compensation Kalman filter with an outlier rejection strategy. Experimental
Eugene Kim +6 more
doaj +1 more source
Ranking guidance actions to support engineers in fulfilling process constraints
In safety‐critical systems engineering, this paper addresses the challenges, engineers encounter in non‐trivial quality assurance (QA) conditions. We propose a guidance action ranking framework to provide engineers with the most relevant guidance actions.
Anmol Bilal +2 more
wiley +1 more source
Generating Quality Assurance Constraints From Natural Language With LLMs
ABSTRACT This paper addresses the challenge of automating process‐centric quality assurance (QA) in safety‐critical domains, where compliance with regulations is crucial. Currently, QA engineers manually check compliance using tedious methods like browsing engineering artifacts and ad‐hoc scripts.
Christoph Mayr‐Dorn +3 more
wiley +1 more source
The research addresses the critical challenge of resource management in mixed‐criticality (MC) systems, which integrate tasks with varying criticality levels onto a shared platform. The authors propose a novel learner‐based approach that effectively predicts system mode transitions and optimises resource allocation, leading to significant improvements ...
Mohammadreza Saberikia +3 more
wiley +1 more source
The complexity and interconnectivity of modern automotive systems are rapidly increasing, particularly with the rise of distributed and cooperative driving functions. These developments increase exposure to a range of disruptions, from technical failures
Isaac Mpidi Bita +3 more
doaj +1 more source
Analysis of ISO 26262 Compliant Techniques for the Automotive Domain. [PDF]
The ISO 26262 standard defines functional safety for automotive E/E systems. Since the publication of the first edition of this standard in 2011, many different safety techniques complying to the ISO 26262 have been developed. However, it is not clear which parts and (sub-) phases of the standard are targeted by these techniques and which objectives of
M. S. Kannan +3 more
openaire +2 more sources
Automotive software developed under ISO 26262 and ISO/SAE 21434 depends on requirements that are traceable, reviewable, and grounded in safety and cybersecurity evidence.
Alexander Lomovtsev
doaj +1 more source

