عرض بسيط للتسجيلة

المؤلفUnal, Devrim
المؤلفCatak, Ferhat Ozgur
المؤلفHoukan, Mohammad Talal
المؤلفMudassir, Mohammed
المؤلفHammoudeh, Mohammad
تاريخ الإتاحة2024-04-17T07:23:27Z
تاريخ النشر2023-01-01
اسم المنشورISA Transactions
المعرّفhttp://dx.doi.org/10.1016/j.isatra.2022.11.007
الاقتباسUnal, D., Catak, F. O., Houkan, M. T., Mudassir, M., & Hammoudeh, M. (2023). Towards robust autonomous driving systems through adversarial test set generation. ISA transactions, 132, 69-79.‏
الرقم المعياري الدولي للكتاب00190578
معرّف المصادر الموحدhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85142727361&origin=inward
معرّف المصادر الموحدhttp://hdl.handle.net/10576/53927
الملخصCorrect environmental perception of objects on the road is vital for the safety of autonomous driving. Making appropriate decisions by the autonomous driving algorithm could be hindered by data perturbations and more recently, by adversarial attacks. We propose an adversarial test input generation approach based on uncertainty to make the machine learning (ML) model more robust against data perturbations and adversarial attacks. Adversarial attacks and uncertain inputs can affect the ML model's performance, which can have severe consequences such as the misclassification of objects on the road by autonomous vehicles, leading to incorrect decision-making. We show that we can obtain more robust ML models for autonomous driving by making a dataset that includes highly-uncertain adversarial test inputs during the re-training phase. We demonstrate an improvement in the accuracy of the robust model by more than 12%, with a notable drop in the uncertainty of the decisions returned by the model. We believe our approach will assist in further developing risk-aware autonomous systems.
اللغةen
الناشرISA - Instrumentation, Systems, and Automation Society
الموضوعDL
Risk-aware autonomous systems
Test set generation
Uncertainty
العنوانTowards robust autonomous driving systems through adversarial test set generation
النوعArticle
الصفحات69-79
رقم المجلد132
dc.accessType Open Access


الملفات في هذه التسجيلة

Thumbnail

هذه التسجيلة تظهر في المجموعات التالية

عرض بسيط للتسجيلة