Litcius/Paper detail

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

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

2021Computer24 citationsDOI

Abstract

This article proposes an approach named SafeML II, which applies empirical cumulative distribution function-based statistical distance measures in a designed human-in-the loop procedure to ensure the safety of machine learning-based classifiers in autonomous vehicle software.

Topics & Concepts

Computer scienceSoftwareFunction (biology)Artificial intelligenceMachine learningSign (mathematics)Operating systemMathematicsMathematical analysisEvolutionary biologyBiologyAnomaly Detection Techniques and ApplicationsAutonomous Vehicle Technology and SafetyAdvanced Statistical Process Monitoring
Toward Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign Recognition Systems | Litcius