DeepAI AI Chat
Log In Sign Up

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

by   Koorosh Aslansefat, et al.

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.


page 1

page 4

page 7


Roadmap for Cybersecurity in Autonomous Vehicles

Autonomous vehicles are on the horizon and will be transforming transpor...

A machine learning environment for evaluating autonomous driving software

Autonomous vehicles need safe development and testing environments. Many...

Using Machine Learning to Enhance Vehicles Traffic in ATN (PRT) Systems

This paper discusses new techniques to enhance Automated Transit Network...

Certified Interpretability Robustness for Class Activation Mapping

Interpreting machine learning models is challenging but crucial for ensu...

Collective Risk Minimization via a Bayesian Model for Statistical Software Testing

In the last four years, the number of distinct autonomous vehicles platf...

Robustness testing of AI systems: A case study for traffic sign recognition

In the last years, AI systems, in particular neural networks, have seen ...