Lane-changes prediction based on adaptive fuzzy neural network. (January 2018)

• Record Type: Journal Article
• Authors: Tang, Jinjun; Liu, Fang; Zhang, Wenhui; Ke, Ruimin; Zou, Yajie
• Is Part Of: Expert systems with applications. Volume 91(2018)
• Page Start: 452
• Page End: 463
• Publication Date: 2018-01
• Subjects: Lane changes -- Fuzzy neural network -- Steering prediction -- Driving simulation -- Adaptive learning algorithm; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2017.09.025
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: An Adaptive Fuzzy Neural Network is proposed to predict steering angles. Takagi–Sugeno fuzzy inference is applied in prediction model. An improved Least Squares Estimator is adopt to optimize parameters in model. An adaptive learning method is used to update membership functions and rule base. Prediction results show the model can accurately follow steering angle patterns. Abstract: Lane changing maneuver is one of the most important driving behaviors. Unreasonable lane changes can cause serious collisions and consequent traffic delays. High precision prediction of lane changing intent is helpful for improving driving safety. In this study, by fusing information from vehicle sensors, a lane changing predictor based on Adaptive Fuzzy Neural Network (AFFN) is proposed to predict steering angles. The prediction model includes two parts: fuzzy neural network based on Takagi–Sugeno fuzzy inference, in which an improved Least Squares Estimator (LSE) is adopt to optimize parameters; adaptive learning algorithm to update membership functions and rule base. Experiments are conducted in the driving simulator under scenarios with different speed levels of lead vehicle: 60 km/h, 80 km/h and 100 km/h. Prediction results show that the proposed method is able to accurately follow steering angle patterns. Furthermore, comparison of prediction performance with several machine learning methods further verifies the learning ability of the AFNN. Finally, a sensibility analysis indicates heading angles and acceleration of vehicle are also important factors for predicting lane changing behavior.