Confidence‐driven weighted retraining for predicting safety‐critical failures in autonomous driving systems
Open Access
- 5 October 2021
- journal article
- research article
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 34 (10) , e2386
Abstract
Safe handling of hazardous driving situations is a task of high practical relevance for building reliable and trustworthy cyber‐physical systems such as autonomous driving systems. This task necessitates an accurate prediction system of the vehicle's confidence to prevent potentially harmful system failures on the occurrence of unpredictable conditions that make it less safe to drive. In this paper, we discuss the challenges of adapting a misbehavior predictor with knowledge mined during the execution of the main system. Then, we present a framework for the continual learning of misbehavior predictors, which records in‐field behavioral data to determine what data are appropriate for adaptation. Our framework guides adaptive retraining using a novel combination of in‐field confidence metric selection and reconstruction error‐based weighing. We evaluate our framework to improve a misbehavior predictor from the literature on the Udacity simulator for self‐driving cars. Our results show that our framework can reduce the false positive rate by a large margin and can adapt to nominal behavior drifts while maintaining the original capability to predict failures up to several seconds in advance.Keywords
Funding Information
- H2020 European Research Council (787703)
This publication has 41 references indexed in Scilit:
- Adaptive generation of challenging scenarios for testing and evaluation of autonomous vehiclesJournal of Systems and Software, 2018
- DeepXplore2017
- Search-based test case generation for Cyber-Physical Systems2017
- Testing advanced driver assistance systems using multi-objective search and neural networks2016
- Robustness Evaluation and Improvement for Vision-Based Advanced Driver Assistance Systems2015
- FaceNet: A unified embedding for face recognition and clustering2015
- Analysis of focus measure operators for shape-from-focusPattern Recognition, 2013
- Anomaly detectionACM Computing Surveys, 2009
- THE GENERALIZATION OF ‘STUDENT'S’ PROBLEM WHEN SEVERAL DIFFERENT POPULATION VARLANCES ARE INVOLVEDBiometrika, 1947
- Individual Comparisons by Ranking MethodsBiometrics Bulletin, 1945