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 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.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Lionel C. Briand,et al.  Testing advanced driver assistance systems using multi-objective search and neural networks , 2016, 2016 31st IEEE/ACM International Conference on Automated Software Engineering (ASE).

[3]  Lionel C. Briand,et al.  Testing Vision-Based Control Systems Using Learnable Evolutionary Algorithms , 2018, 2018 IEEE/ACM 40th International Conference on Software Engineering (ICSE).

[4]  Dieter Schramm,et al.  Requirements on driving dynamics in autonomous driving with regard to motion and comfort , 2018 .

[5]  Nathalie Japkowicz,et al.  Anomaly Detection in Automobile Control Network Data with Long Short-Term Memory Networks , 2016, 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[6]  Sarfraz Khurshid,et al.  DeepRoad: GAN-Based Metamorphic Testing and Input Validation Framework for Autonomous Driving Systems , 2018, 2018 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE).

[7]  Lovekesh Vig,et al.  LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection , 2016, ArXiv.

[8]  Charles C. Kemp,et al.  A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational Autoencoder , 2017, IEEE Robotics and Automation Letters.

[9]  Tommi S. Jaakkola,et al.  Towards Robust Interpretability with Self-Explaining Neural Networks , 2018, NeurIPS.

[10]  Anupam Joshi,et al.  OBD_SecureAlert: An Anomaly Detection System for Vehicles , 2016, 2016 IEEE International Conference on Smart Computing (SMARTCOMP).

[11]  Junfeng Yang,et al.  DeepXplore: Automated Whitebox Testing of Deep Learning Systems , 2019, GETMBL.

[12]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[13]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[14]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[15]  Christian Berger,et al.  Towards Structured Evaluation of Deep Neural Network Supervisors , 2019, 2019 IEEE International Conference On Artificial Intelligence Testing (AITest).

[16]  DAVID G. KENDALL,et al.  Introduction to Mathematical Statistics , 1947, Nature.

[17]  Andreas Rausch,et al.  Toward a Holistic Software Systems Engineering Approach for Dependable Autonomous Systems , 2018, 2018 IEEE/ACM 1st International Workshop on Software Engineering for AI in Autonomous Systems (SEFAIAS).

[18]  Jingyi Wang,et al.  Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing , 2018, 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE).

[19]  Shin Yoo,et al.  Guiding Deep Learning System Testing Using Surprise Adequacy , 2018, 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE).

[20]  Michele Colajanni,et al.  Evaluation of anomaly detection for in-vehicle networks through information-theoretic algorithms , 2016, 2016 IEEE 2nd International Forum on Research and Technologies for Society and Industry Leveraging a better tomorrow (RTSI).

[21]  Yang Feng,et al.  Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications , 2018, WWW.

[22]  S. C. Choi,et al.  Maximum Likelihood Estimation of the Parameters of the Gamma Distribution and Their Bias , 1969 .

[23]  Takaya Saito,et al.  The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets , 2015, PloS one.

[24]  Takehisa Yairi,et al.  Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction , 2014, MLSDA'14.

[25]  Apoorva Nandini Saridena,et al.  Adversarial Learning-Based On-Line Anomaly Monitoring for Assured Autonomy , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[26]  Arthur Zimek,et al.  On the evaluation of unsupervised outlier detection: measures, datasets, and an empirical study , 2016, Data Mining and Knowledge Discovery.

[27]  Tim Fingscheidt,et al.  Towards Corner Case Detection for Autonomous Driving , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

[28]  Bernd Bischl,et al.  Robust Anomaly Detection in Images using Adversarial Autoencoders , 2019, ECML/PKDD.

[29]  Satyandra K. Gupta,et al.  Adaptive generation of challenging scenarios for testing and evaluation of autonomous vehicles , 2018, J. Syst. Softw..

[30]  Eliahu Khalastchi,et al.  Detecting anomalies in unmanned vehicles using the Mahalanobis distance , 2010, 2010 IEEE International Conference on Robotics and Automation.

[31]  Abhinav Sethy,et al.  Towards Better Confidence Estimation for Neural Models , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[32]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[33]  Yong Haur Tay,et al.  Abnormal Event Detection in Videos using Spatiotemporal Autoencoder , 2017, ISNN.

[34]  Heni Ben Amor,et al.  Deep Predictive Models for Collision Risk Assessment in Autonomous Driving , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[35]  Annibale Panichella,et al.  Testing Autonomous Cars for Feature Interaction Failures using Many-Objective Search , 2018, 2018 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE).

[36]  Vinton G. Cerf,et al.  A comprehensive self-driving car test , 2018, Commun. ACM.

[37]  Wolfgang Rosenstiel,et al.  Robustness Evaluation and Improvement for Vision-Based Advanced Driver Assistance Systems , 2015, 2015 IEEE 18th International Conference on Intelligent Transportation Systems.

[38]  Corina S. Pasareanu,et al.  DeepSafe: A Data-Driven Approach for Assessing Robustness of Neural Networks , 2018, ATVA.

[39]  Gordon Fraser,et al.  Automatically testing self-driving cars with search-based procedural content generation , 2019, ISSTA.

[40]  Jürgen Schmidhuber,et al.  Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction , 2011, ICANN.

[41]  Donghwan Shin,et al.  Comparing Offline and Online Testing of Deep Neural Networks: An Autonomous Car Case Study , 2019, 2020 IEEE 13th International Conference on Software Testing, Validation and Verification (ICST).

[42]  Sungzoon Cho,et al.  Variational Autoencoder based Anomaly Detection using Reconstruction Probability , 2015 .

[43]  Suman Jana,et al.  DeepTest: Automated Testing of Deep-Neural-Network-Driven Autonomous Cars , 2017, 2018 IEEE/ACM 40th International Conference on Software Engineering (ICSE).

[44]  Pushmeet Kohli,et al.  Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures , 2018, ICLR.