Deep Multi-Task Learning for Anomalous Driving Detection Using CAN Bus Scalar Sensor Data

Corner cases are the main bottlenecks when applying Artificial Intelligence (AI) systems to safety-critical applications. An AI system should be intelligent enough to detect such situations so that system developers can prepare for subsequent planning. In this paper, we propose semi-supervised anomaly detection considering the imbalance of normal situations: In particular, driving data consists of multiple normal situations (e.g., right turn, going straight), some of which (e.g., U-turn) could be as rare as anomalous ones. Existing machine learning based anomaly detection approaches do not fare sufficiently well when applied to such imbalanced data. In this paper, we present a novel multi-task learning (LSTM autoencoder and predictor) based approach that leverages domain-knowledge (maneuver labels) for anomaly detection in driving data. We evaluate the proposed approach both quantitatively and qualitatively on 150 hours of real-world driving data and show improved performance over baseline/existing approaches.

[1]  Miriam A. M. Capretz,et al.  An ensemble learning framework for anomaly detection in building energy consumption , 2017 .

[2]  Ira Cohen,et al.  Real-time anomaly detection system for time series at scale , 2017, ADF@KDD.

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

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Dario Pompili,et al.  CollabLoc: Privacy-Preserving Multi-Modal Localization via Collaborative Information Fusion , 2017, 2017 26th International Conference on Computer Communication and Networks (ICCCN).

[6]  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).

[7]  Miriam A. M. Capretz,et al.  Contextual anomaly detection framework for big sensor data , 2015, Journal of Big Data.

[8]  Fiorella Lauro,et al.  Fault detection analysis using data mining techniques for a cluster of smart office buildings , 2015, Expert Syst. Appl..

[9]  Dario Pompili,et al.  Argus: Smartphone-Enabled Human Cooperation via Multi-agent Reinforcement Learning for Disaster Situational Awareness , 2016, 2016 IEEE International Conference on Autonomic Computing (ICAC).

[10]  Dario Pompili,et al.  HCFContext: Smartphone Context Inference via Sequential History-based Collaborative Filtering , 2019, 2019 IEEE International Conference on Pervasive Computing and Communications (PerCom.

[11]  Rok Sosic,et al.  Drive2Vec: Multiscale State-Space Embedding of Vehicular Sensor Data , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[12]  Phyks.  Introducing practical and robust anomaly detection in a time series | Twitter Blogs , 2015 .

[13]  Lovekesh Vig,et al.  Long Short Term Memory Networks for Anomaly Detection in Time Series , 2015, ESANN.

[14]  Kate Saenko,et al.  Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.