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

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

Yes === 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. The applicatio...

Full description

Bibliographic Details
Main Authors: Aslansefat, K., Kabir, Sohag, Abdullatif, Amr R.A., Vasudevan, Vinod, Papadopoulos, Y.
Language:en
Published: IEEE 2021
Subjects:
Autonomous systems
Safety assurance
AI safety
Statistical distance measure
SafeML
Safe machine learning
Online Access:http://hdl.handle.net/10454/18591

Internet

http://hdl.handle.net/10454/18591

Similar Items