A Framework for Building Uncertainty Wrappers for AI/ML-Based Data-Driven Components

Kläs, Michael; Jöckel, Lisa

doi:10.1007/978-3-030-55583-2_23

Cited by 14 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…93% certain that an object is a pedestrian, they usually do not provide an explicit consideration of uncertainty or provide a measure that is not statistically robust. However, even if the algorithms do not provide specific measures, some degree of uncertainty must be ascribed to the DDMs in the cases where they are used for safety critical functions [23].…”

Section: Capabilities and Limitations Of Camera-based Perception Systemsmentioning

confidence: 99%

“…In general, three common sources of uncertainty should be considered for DDMs: the model fit, the data quality, and the scope compliance [23]. Model fit is the inherent uncertainty in the DDM, Data quality is the DDM's uncertainty as a result of it's application to input data obtained in sub-optimal conditions (and greatly affect by sensor performance), and scope compliance is where the model may be applied to the scenarios outside of the intended use [24].…”

Section: Capabilities and Limitations Of Camera-based Perception Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Safety Assessment for Autonomous Systems' Perception Capabilities

Molloy¹,

McDermid²

2022

Preprint

View full text Add to dashboard Cite

Autonomous Systems (AS) are increasingly proposed, or used, in Safety Critical (SC) applications. Many such systems make use of sophisticated sensor suites and processing to provide scene understanding which informs the AS' decision-making. The sensor processing typically makes use of Machine Learning (ML) and has to work in challenging environments, further the ML-algorithms have known limitations,e.g., the possibility of false-negatives or false-positives in object classification. The well-established safety-analysis methods developed for conventional SC systems are not well-matched to AS, ML, or the sensing systems used by AS. This paper proposes an adaptation of well-established safety-analysis methods to address the specifics of perception-systems for AS, including addressing environmental effects and the potential failure-modes of ML, and provides a rationale for choosing particular sets of guidewords, or prompts, for safety-analysis. It goes on to show how the results of the analysis can be used to inform the design and verification of the AS and illustrates the new method by presenting a partial analysis of a road vehicle. Illustrations in the paper are primarily based on optical sensing, however the paper discusses the applicability of the method to other sensing modalities and its role in a wider safety process addressing the overall capabilities of AS.

show abstract

Section: Capabilities and Limitations Of Camera-based Perception Systemsmentioning

confidence: 99%

Section: Capabilities and Limitations Of Camera-based Perception Systemsmentioning

confidence: 99%