Defect-Repairable Latent Feature Extraction of Driving Behavior via a Deep Sparse Autoencoder

Abstract

Data representing driving behavior, as measured by various sensors installed in a vehicle, are collected as multi-dimensional sensor time-series data. These data often include redundant information, e.g., both the speed of wheels and the engine speed represent the velocity of the vehicle. Redundant information can be expected to complicate the data analysis, e.g., more factors need to be analyzed; even varying the levels of redundancy can influence the results of the analysis. We assume that the measured multi-dimensional sensor time-series data of driving behavior are generated from low-dimensional data shared by the many types of one-dimensional data of which multi-dimensional time-series data are composed. Meanwhile, sensor time-series data may be defective because of sensor failure. Therefore, another important function is to reduce the negative effect of defective data when extracting low-dimensional time-series data. This study proposes a defect-repairable feature extraction method based on a deep sparse autoencoder (DSAE) to extract low-dimensional time-series data. In the experiments, we show that DSAE provides high-performance latent feature extraction for driving behavior, even for defective sensor time-series data. In addition, we show that the negative effect of defects on the driving behavior segmentation task could be reduced using the latent features extracted by DSAE.

Research on Traffic Vehicle Behavior Prediction Method Based on Game Theory and HMM

“…The prototype trajectory method matches the vehicle's prototype trajectory with the vehicle's possible motion pattern, and then combines the matching results with the historical trajectory for behavior identification. The driver behavior can be extracted by many methods, H. Liu et al propose a defect-repairable feature extraction method based on a deep sparse autoencoder (DSAE) to extract low-dimensional time-series data that represents driving behavior [1]. And the prototype trajectory can be obtained by classifying the vehicle's sample trajectories, two kinds of Spectral clustering method are adopted by Atev et al to classify the trajectory [2], and Vasquez et al classify the trajectory by calculating the mean and standard deviation of the sample trajectory [3].…”

Driving behavior model considering driver's over-trust in driving automation system

“…For the second condition, an evaluation system can be expected to estimate the ability of the DAS on realtime. For example, the defects detecting system may be used to detect the generated control signal of the DAS is different from the normal driving behaviors [37]. Meanwhile, the reliability of the DAS should be evaluated, too [38].…”