Evaluation of Lane Departure Correction Systems Using a Regenerative Stochastic Driver Model

Wang, Wenshuo; Zhao, Ding

doi:10.1109/tiv.2017.2756342

Cited by 36 publications

(14 citation statements)

References 33 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The implementation of safe interaction is challenging because human actions and behaviors are often unpredictable [99]. Fortunately, studies in [98,100] provide some promising ideas (such as developing robust informative models or regenerative stochastic models). Secondly, intersection assistance may become a focal point with the development of vehicle embedded devices (e.g.…”

Section: F Discussionmentioning

confidence: 99%

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

et al. 2020

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

In recent decades, driving assistance systems have been evolving towards personalization for adapting to different drivers. With considering personal driving preferences and characteristics, these systems become more acceptable and trustworthy. This paper presents a survey of recent advances in implicit personalized driving assistance. We classify the collection of work into three main categories: 1) personalized Safe Driving Systems (SDS), 2) personalized Driver Monitoring Systems (DMS), and 3) personalized In-vehicle Information Systems (IVIS). For each category, we provide a comprehensive review of current applications and related techniques along with the discussion of industry status, gains of personalization, application prospects, and future focal points. Several existing driving datasets are summarized and open issues of personalized driving assistance are also suggested to facilitate future research. By creating an organized categorization of the field, this survey could not only support future research and the development of new technologies for personalized driving assistance but also facilitate the use of these techniques by researchers within the driving automation community.

show abstract

Section: F Discussionmentioning

confidence: 99%

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

et al. 2020

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

show abstract

“…The ability of nonlinear modeling of neural networks can be improved by adding activation function to convolution neural networks in ResNet block activation layer. In this paper, ReLu (Rectified Linear Units) and BN (batch normalization) [30] are used as the activation function. The combination of ReLu and BN can ensure data stability and maintain the gradient without attenuation, thus accelerating the convergence speed of the network and improving the training speed of the network.…”

Section: Activation Function In Residual Blockmentioning

confidence: 99%

Lane Departure Warning Mechanism of Limited False Alarm Rate Using Extreme Learning Residual Network and ϵ-Greedy LSTM

Gao

Yin

Zhang

2020

Sensors

View full text Add to dashboard Cite

Neglecting the driver behavioral model in lane-departure-warning systems has taken over as the primary reason for false warnings in human–machine interfaces. We propose a machine learning-based mechanism to identify drivers’ unintended lane-departure behaviors, and simultaneously predict the possibility of driver proactive correction after slight departure. First, a deep residual network for driving state feature extraction is established by combining time series sensor data and three serial ReLU residual modules. Based on this feature network, online extreme learning machine is organized to identify a driver’s behavior intention, such as unconscious lane-departure and intentional lane-changing. Once the system senses unconscious lane-departure before crossing the outermost warning boundary, the ϵ-greedy LSTM module in shadow mode is roused to verify the chances of driving the vehicle back to the original lane. Only those unconscious lane-departures with no drivers’ proactive correction behavior are transferred into the warning module, guaranteeing that the system has a limited false alarm rate. In addition, naturalistic driving data of twenty-one drivers are collected to validate the system performance. Compared with the basic time-to-line-crossing (TLC) method and the TLC-DSPLS method, the proposed warning mechanism shows a large-scale reduction of 12.9% on false alarm rate while maintaining the competitive accuracy rate of about 98.8%.

show abstract

“…Most observed driving data from drivers usually have bounded support features [56], [57]. For example, in the carfollowing scenario, the relative range between the ego and leading vehicle is usually larger than a critical value, and also drivers usually prefer certain relative ranges or vehicle speeds, thereby the distributions of the relative range and the vehicle speed will have the bounded supports.…”

Section: B Bounded Characteristics Of Variablesmentioning

confidence: 99%

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

Wang

Zhao

2018

IEEE Trans. Veh. Technol.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Evaluation of Lane Departure Correction Systems Using a Regenerative Stochastic Driver Model

Cited by 36 publications

References 33 publications

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

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

Lane Departure Warning Mechanism of Limited False Alarm Rate Using Extreme Learning Residual Network and ϵ-Greedy LSTM

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

Contact Info

Product

Resources

About