Misbehaviour Prediction for Autonomous Driving Systems

Deep Neural Networks (DNNs) are the core component of modern autonomous driving systems. To date, it is still unrealistic that a DNN will generalize correctly to all driving conditions. Current testing techniques consist of offline solutions that identify adversarial or corner cases for improving th...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2020 IEEE/ACM 42nd International Conference on Software Engineering (ICSE) s. 359 - 371
Hlavní autoři: Stocco, Andrea, Weiss, Michael, Calzana, Marco, Tonella, Paolo
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: ACM 01.10.2020
Témata:
anomaly detection
deep learning
misbehaviour prediction
testing
ISSN:1558-1225
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Deep Neural Networks (DNNs) are the core component of modern autonomous driving systems. To date, it is still unrealistic that a DNN will generalize correctly to all driving conditions. Current testing techniques consist of offline solutions that identify adversarial or corner cases for improving the training phase. In this paper, we address the problem of estimating the confidence of DNNs in response to unexpected execution contexts with the purpose of predicting potential safety-critical misbehaviours and enabling online healing of DNN-based vehicles. Our approach SelfOracle is based on a novel concept of self-assessment oracle, which monitors the DNN confidence at runtime, to predict unsupported driving scenarios in advance. SelfOracle uses autoencoder- and time series-based anomaly detection to reconstruct the driving scenarios seen by the car, and to determine the confidence boundary between normal and unsupported conditions. In our empirical assessment, we evaluated the effectiveness of different variants of SelfOracle at predicting injected anomalous driving contexts, using DNN models and simulation environment from Udacity. Results show that, overall, SelfOracle can predict 77% misbehaviours, up to six seconds in advance, outperforming the online input validation approach of DeepRoad.
ISSN:1558-1225
DOI:10.1145/3377811.3380353