Machine-Learned Correctness Properties, Runtime Verification, and Advance-Warning Oracles for Autonomous Systems
- 23 September 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Computer
- Vol. 57 (10) , 118-130
Abstract
We describe machine-learned classifiers that act as correctness properties for runtime verification of autonomous systems. Additionally, we show an advance collision detection system using such machine learning correctness properties that provides an uncertainty measure alongside a prediction.Keywords
This publication has 32 references indexed in Scilit:
- A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement2022
- Uncertainty propagation for dropout-based Bayesian neural networksNeural Networks, 2021
- Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methodsMachine Learning, 2021
- Machine Learning for Time Series Forecasting with Python®2020
- Enhanced Transfer Learning for Autonomous Driving with Systematic Accident Simulation2020
- Aleatoric and Epistemic Uncertainty with Random Forests2020
- Bayesian Learning for Neural Networks1996
- Smart cars on smart roads: problems of controlIEEE Transactions on Automatic Control, 1993
- Ironies of automationAutomatica, 1983
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948