Toward Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign Recognition Systems

Aslansefat, Koorosh; Kabir, Sohag; Abdullatif, Amr; Vasudevan, Vinod; Papadopoulos, Yiannis

doi:10.1109/mc.2021.3075054

Cited by 16 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…including all traffic signs not just speed limit) has been extensively studied in conjunction with autonomous driving (e.g. Atif et al, 2022), being one of the benchmark problem for ML and AI researchers seeking to demonstrate the robustness of their algorithms (Aslansefat et al, 2021). Some automotive manufacturers have attempted to build on the TSR capability with enhanced ADAS features based on TSR information input.…”

Section: Case Study Backgroundmentioning

confidence: 99%

Extending the function failure modes taxonomy for intelligent systems with embedded AI components

Campean,

Yildirim,

Korsunovs

et al. 2024

Proc. Des. Soc.

View full text Add to dashboard Cite

Early consideration of failure modes in the feature development process is essential to identify and trace risks across the physical and embedded AI components of intelligent systems, to enhance the robustness of the feature delivery as well as trust in the AI. This paper introduces an extension of the AIAG/VDA function failure modes taxonomy, to facilitate the integrated analysis of complex intelligent systems with embedded AI. A case study of an autonomous driving feature is discussed as validation of the proposed taxonomy.

show abstract

Section: Case Study Backgroundmentioning

confidence: 99%

Extending the function failure modes taxonomy for intelligent systems with embedded AI components

Campean,

Yildirim,

Korsunovs

et al. 2024

Proc. Des. Soc.

View full text Add to dashboard Cite

show abstract

“…ECDF-based statistical distance measures are then used to calculate the distance of each perturbed image from the original sample, similar to the approach used in Aslansefat et al [2021]. As before, this then enables us to train a weighted linear regression model as a surrogate model.…”

Section: Explaining Explainabilitymentioning

confidence: 99%

Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations

Aslansefat,

Hashemian,

Walker

et al. 2024

IEEE Softw.

Self Cite

View full text Add to dashboard Cite

Machine learning is currently undergoing an explosion in capability, popularity, and sophistication. However, one of the major barriers to widespread acceptance of machine learning (ML) is trustworthiness: most ML models operate as black boxes, their inner workings opaque and mysterious, and it can be difficult to trust their conclusions without understanding how those conclusions are reached. Explainability is therefore a key aspect of improving trustworthiness: the ability to better understand, interpret, and anticipate the behaviour of ML models. To this end, we propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.

show abstract

StaDRe and StaDRo: Reliability and Robustness Estimation of ML-Based Forecasting Using Statistical Distance Measures

Akram

Ambekar

Sorokos

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Toward Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign Recognition Systems

Cited by 16 publications

References 14 publications

Extending the function failure modes taxonomy for intelligent systems with embedded AI components

Extending the function failure modes taxonomy for intelligent systems with embedded AI components

Explaining Black Boxes With a SMILE: Statistical Model-Agnostic Interpretability With Local Explanations

StaDRe and StaDRo: Reliability and Robustness Estimation of ML-Based Forecasting Using Statistical Distance Measures

Contact Info

Product

Resources

About