Learning and Inferring a Driver's Braking Action in Car-Following Scenarios

Abstract

Accurately predicting and inferring a driver's decision to brake is critical for designing warning systems and avoiding collisions. In this paper we focus on predicting a driver's intent to brake in car-following scenarios from a perceptiondecision-action perspective according to his/her driving history. A learning-based inference method, using onboard data from CAN-Bus, radar and cameras as explanatory variables, is introduced to infer drivers' braking decisions by combining a Gaussian mixture model (GMM) with a hidden Markov model (HMM). The GMM is used to model stochastic relationships among variables, while the HMM is applied to infer drivers' braking actions based on the GMM. Real-case driving data from 49 drivers (more than three years' driving data per driver on average) have been collected from the University of Michigan Safety Pilot Model Deployment database. We compare the GMM-HMM method to a support vector machine (SVM) method and an SVM-Bayesian filtering method. The experimental results are evaluated by employing three performance metrics: accuracy, sensitivity, and specificity. The comparison results show that the GMM-HMM obtains the best performance, with an accuracy of 90%, sensitivity of 84%, and specificity of 97%. Thus, we believe that this method has great potential for real-world active safety systems.Index Terms-Learning and inferring behaviors, braking action, Gaussian mixture regression, hidden Markov model, carfollowing behavior.

Implicit Personalization in Driving Assistance: State-of-the-Art and Open Issues

“…Gains of personalization: Safe driving systems can obtain several benefits by introducing personalization. The primary gain is the enhanced acceptability [26,68]. In [26], the false-warning rate of a lane departure warning system can be reduced to 3.13%.…”

“…According to [3,22,26,[30][31][32][33][34], driving assistance systems should be safe, effective, and comfortable. To meet these criteria, personalization is introduced to understand the status of a specific driver [35], and take individual driving styles [29], requirements, and preferences [36] into account.…”

“…However, a failure to understand the driver's correct behavior may cause a significant number of false warnings. This could make drivers mistrust or even abandon lane-keeping assistance systems [26,92]. To reduce false positive rate, Hidden Markov Models, Gaussian Mixture Models, and their combination are used in personalized lanekeeping assistance systems [57,77].…”

“…The predictors of machine learning approaches are obtained by training a classifier or regressor (e.g. Bayesian network, decision tree, and support vector machine) as in [5,25,26]. Then, the predictor is used in a generic system.…”

“…The procedure of collecting normal and aggressive driving data for individual drivers is outlined in [28]. Driving preference and characteristic refer to personal driving behaviors such as preferred distance to the car in-front [20,26] and adaptive lane change assistance [29]. This paper presents a comprehensive review of personalized driving assistance.…”