Vehicles can utilize their sensors or receive messages from other vehicles to acquire information about the surrounding environments. However, the information may be inaccurate, faulty, or maliciously compromised due to sensor failures, communication faults, or security attacks. The goal of this work is to detect if a lane-changing decision and the sensed or received information are anomalous. We develop three anomaly detection approaches based on deep learning: a classifier approach, a predictor approach, and a hybrid approach combining the classifier and the predictor. All of them do not need anomalous data nor lateral features so that they can generally consider lane-changing decisions before the vehicles start moving along the lateral axis. They achieve at least 82% and up to 93% F1 scores against anomaly on data from Simulation of Urban MObility (SUMO) [1] and HighD [2]. We also examine system properties and verify that the detected anomaly includes more dangerous scenarios.
Deep-Learning-Based Anomaly Detection for Lane-Changing Decisions
2022 IEEE Intelligent Vehicles Symposium (IV) ; 1536-1542
2022-06-05
363917 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Harmonious Lane Changing via Deep Reinforcement Learning
IEEE | 2022
|A data-driven lane-changing model based on deep learning
Elsevier | 2019
|Variable speed limit strategy with anticipatory lane changing decisions
Taylor & Francis Verlag | 2021
|