Road curvature estimation for vehicle lane departure detection using a robust Takagi–Sugeno fuzzy observer

Dahmani, H.; Chadli, Mohammed; Rabhi, Abdelhamid; Hajjaji, Ahmed El

doi:10.1080/00423114.2011.642806

Cited by 59 publications

(31 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The TLC-based algorithm has been widely reported in the literature and used on production vehicles. These systems estimate the lane states [9], [17] (i.e., lane markers, lane width, and lane curvature, etc.) and vehicle states based on visionbased equipment, and then calculate the TLC online using a variety of algorithms [14].…”

Section: A Time To Lane Crossing (Tlc)mentioning

confidence: 99%

A Learning-Based Approach for Lane Departure Warning Systems With a Personalized Driver Model

Wang

Zhao

Han

et al. 2018

IEEE Trans. Veh. Technol.

104

View full text Add to dashboard Cite

Misunderstanding of driver correction behaviors (DCB) is the primary reason for false warnings of lane-departureprediction systems. We propose a learning-based approach to predicting unintended lane-departure behaviors (LDB) and the chance for drivers to bring the vehicle back to the lane. First, in this approach, a personalized driver model for lanedeparture and lane-keeping behavior is established by combining the Gaussian mixture model and the hidden Markov model. Second, based on this model, we develop an online model-based prediction algorithm to predict the forthcoming vehicle trajectory and judge whether the driver will demonstrate an LDB or a DCB. We also develop a warning strategy based on the model-based prediction algorithm that allows the lane-departure warning system to be acceptable for drivers according to the predicted trajectory. In addition, the naturalistic driving data of 10 drivers is collected through the University of Michigan Safety Pilot Model Deployment program to train the personalized driver model and validate this approach. We compare the proposed method with a basic time-to-lane-crossing (TLC) method and a TLC-directional sequence of piecewise lateral slopes (TLC-DSPLS) method. The results show that the proposed approach can reduce the falsewarning rate to 3.07%.Index Terms-Learning-based approach, lane departure warning system, Gaussian mixture model, hidden Markov model, personalized driver model

show abstract

Section: A Time To Lane Crossing (Tlc)mentioning

confidence: 99%

A Learning-Based Approach for Lane Departure Warning Systems With a Personalized Driver Model

Wang

Zhao

Han

et al. 2018

IEEE Trans. Veh. Technol.

104

View full text Add to dashboard Cite

show abstract

“…In this context, algorithms are often designed to detect, re-identify, count, track or classify vehicles (Bas, Tekalp, & Salman, 2007;Hsieh, 2006;Zhou, Gao, & Zhang, 2007), while others are designed to improve the safety of the driver (Aouaouda, Chadli, Boukhnifer, & Karimi, 2014;Dahmani, Chadli, Rabhi, & El Hajjaji, 2013;Saifia, Chadli, Karimi, & Labiod, 2014). We tackle the specific tracking and classification tasks presenting a unified system for the online tracking and classification of vehicles.…”

Section: Introductionmentioning

confidence: 99%

An integrated system for vehicle tracking and classification

Battiato

Farinella

Furnari

et al. 2015

Expert Systems with Applications

View full text Add to dashboard Cite

“…However, the P&O method can easily produce continuous oscillation around the maximum power point; therefore, a nonlinear control method, named fuzzy control, is added based on the traditional P&O method. Fuzzy control can simplify the system design and is particularly useful for a nonlinear, hysteretic, time-varying, and model-incomplete system owing to its excellent robust performance [1,2]. Bououden et al added an ant-colony intelligent optimization algorithm to fuzzy control, which can not only deal with nonlinearity but also reduce the parameter randomization of the algorithm [3].…”

Section: Introductionmentioning

confidence: 99%

Application of Fuzzy Control in a Photovoltaic Grid-Connected Inverter

Zheng

Zhang

Xue

2018

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

To realize the maximum power output of a grid-connected inverter, the MPPT (maximum power point tracking) control method is needed. The perturbation and observation (P&O) method can cause the inverter operating point to oscillate near the maximum power. In this paper, the fuzzy control P&O method is proposed, and the fuzzy control algorithm is applied to the disturbance observation method. The simulation results of the P&O method with fuzzy control and the traditional P&O method prove that not only can the new method reduce the power loss caused by inverter oscillation during maximum power point tracking, but also it has the advantage of speed. Inductive loads in the post-grid-connected stage cause grid-connected current distortion. A fuzzy control algorithm is added to the traditional deadbeat grid-connected control method to improve the quality of the system's grid-connected operation. The fuzzy deadbeat control method is verified by experiments, and the harmonic current of the grid-connected current is less than 3%.

show abstract

Road curvature estimation for vehicle lane departure detection using a robust Takagi–Sugeno fuzzy observer

Cited by 59 publications

References 14 publications

A Learning-Based Approach for Lane Departure Warning Systems With a Personalized Driver Model

A Learning-Based Approach for Lane Departure Warning Systems With a Personalized Driver Model

An integrated system for vehicle tracking and classification

Application of Fuzzy Control in a Photovoltaic Grid-Connected Inverter

Contact Info

Product

Resources

About