TY - GEN
T1 - Deep Multi-Task Learning for Anomalous Driving Detection Using CAN Bus Scalar Sensor Data
AU - Sadhu, Vidyasagar
AU - Misu, Teruhisa
AU - Pompili, Dario
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85081163419&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081163419&partnerID=8YFLogxK
U2 - 10.1109/IROS40897.2019.8967753
DO - 10.1109/IROS40897.2019.8967753
M3 - Conference contribution
AN - SCOPUS:85081163419
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 2038
EP - 2043
BT - 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019
Y2 - 3 November 2019 through 8 November 2019
ER -