Papers › Toward Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign...

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

3 Aug 2021Computer 2021 8archive 2025-07-28

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

The application of artificial intelligence (AI) and data-driven decision-making systems in autonomous vehicles is growing rapidly. As autonomous vehicles operate in dynamic environments, the risk that they can face an unknown observation is relatively high due to insufficient training data, distributional shift, or cyber-security attack. Thus, AI-based algorithms should make dependable decisions to improve their interpretation of the environment, lower the risk of autonomous driving, and avoid catastrophic accidents. This paper proposes an approach named SafeML II, which applies empirical cumulative distribution function (ECDF)-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 approach is model-agnostic and it can cover various machine learning and deep learning classifiers. The German Traffic Sign Recognition Benchmark (GTSRB) is used to illustrate the capabilities of the proposed approach.

PaperPDFCode

Code

ISorokos/SafeML mentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Autonomous DrivingAutonomous VehiclesBIG-bench Machine LearningDecision MakingExplainable artificial intelligenceImage ClassificationTraffic Sign Recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionMax PoolingR-CNNSVM

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections