From Neuron Coverage to Steering Angle: Testing Autonomous Vehicles Effectively

From Neuron Coverage to Steering Angle: Testing Autonomous Vehicles Effectively

A deep neural network (DNN)-based system is a black box of complex interactions, resulting in a classification or prediction. We investigate the use of realistic transformations to create new images for testing a trained autonomous vehicle DNN as well as their impact on neuron coverage.

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer (Long Beach, Calif.) Calif.), 2021-08, Vol.54 (8), p.77-85
Hauptverfasser: Toohey, Jack R, Raunak, M S, Binkley, David
Format: Artikel
Sprache:eng
Schlagworte:
Artificial neural networks
Autonomous vehicles
Deep learning
Neurons
Steering
Testing
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A deep neural network (DNN)-based system is a black box of complex interactions, resulting in a classification or prediction. We investigate the use of realistic transformations to create new images for testing a trained autonomous vehicle DNN as well as their impact on neuron coverage.
ISSN:0018-9162
1558-0814
DOI:10.1109/MC.2021.3079921