A hierarchical prediction model for lane-changes based on combination of fuzzy C-means and adaptive neural network

•A hierarchical prediction model is proposed to predict steering angles.•The model combines fuzzy c-means and adaptive neural network.•A clustering learning method is adopted to optimize parameters of sub neural network.•Experiments are conducted in the driving simulator under different scenarios.•P...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Expert systems with applications Ročník 130; s. 265 - 275
Hlavní autori: Tang, Jinjun, Yu, Shaowei, Liu, Fang, Chen, Xinqiang, Huang, Helai
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Elsevier Ltd 15.09.2019
Elsevier BV
Predmet:
Adaptive algorithms
Advanced driver assistance systems
Artificial neural networks
Clustering
Computer simulation
Driving prediction
Driving simulation
Environmental impact
Fuzzy C-means algorithm
Fuzzy logic
Lane changes
Lane changing
Neural network
Neural networks
Supervised learning
Teaching methods
Vehicle safety
Driving simulation
Lane changes
Neural network
Fuzzy C-means algorithm
Driving prediction
ISSN:0957-4174, 1873-6793
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:•A hierarchical prediction model is proposed to predict steering angles.•The model combines fuzzy c-means and adaptive neural network.•A clustering learning method is adopted to optimize parameters of sub neural network.•Experiments are conducted in the driving simulator under different scenarios.•Prediction results show the model can achieve high performance. Lane changing behavior generally expresses uncertainty due to the impact of environmental factors, and unreasonable lane changes can cause serious collisions. High precision prediction of lane changing intent is helpful to enhance proactivity in driving safety protection. This study proposed a lane-changing prediction model based on Fuzzy C-means clustering algorithm and adaptive Neural Network (FCMNN), which introduced a new prediction process: (1) Unsupervised learning method: categorize original dataset into different clusters according to their distribution features; (2) Supervised learning method: optimize sub-Neural Network structures and weighting parameters for each cluster or pattern. Through comparing with several traditional methods under different simulation scenarios, the proposed model effectively improve the prediction performance and stability. The results obtained in this study will be helpful to deeply analyze the intent recognition of driving behavior, improve the safety of lane-changing behavior, and provide key technology in driving prediction of Advanced Driver Assistance System (ADAS).
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2019.04.032