An improved learning-based LSTM approach for lane change intention prediction subject to imbalanced data

Lane change intention prediction is an essential component for motion planning of Autonomous Vehicles (AVs). In this work, we aim to achieve this task by using Long-Short Term Memory (LSTM) network. One critical challenge on this task is that the dataset used for training such a network is usually h...

Full description

Saved in:
Bibliographic Details
Published in:Transportation research. Part C, Emerging technologies Vol. 133; p. 103414
Main Authors: Shi, Qian, Zhang, Hui
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.12.2021
Subjects:
Autonomous Vehicles
Data imbalance
Ensemble learning
Lane change intention prediction
Long Short Term Memory (LSTM) network
Over-sampling method
Autonomous Vehicles
Ensemble learning
Lane change intention prediction
Long Short Term Memory (LSTM) network
Over-sampling method
Data imbalance
ISSN:0968-090X, 1879-2359
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Lane change intention prediction is an essential component for motion planning of Autonomous Vehicles (AVs). In this work, we aim to achieve this task by using Long-Short Term Memory (LSTM) network. One critical challenge on this task is that the dataset used for training such a network is usually highly imbalanced due to the fact that the size of left/right lane change data is much smaller than that of the lane keeping data. The imbalanced dateset would lead to trivial output of LSTM model. To deal with this problem, we propose a hierarchical over-sampling bagging method based on Grey Wolf Optimizer (GWO) algorithm and Synthetic Minority Over-sampling Technique (SMOTE). With the proposed method, more diverse and informative instances of minority classes can be generated for training LSTM model. Furthermore, we also propose a sampling technique to keep the temporal information and make the proposed method applicable to sequential data. Moreover, to further improve the prediction performance, we also take the interactions between neighboring vehicles into account by concatenating their trajectories when constructing features. We evaluate our method against several baseline algorithms over two benchmark datasets and the empirical results validate the effectiveness and efficiency of our method in terms of the indexes of prediction time, F1, and G-mean. •Taking the data imbalance into consideration when training the lane change intention predictor and modify the SMOTE method by GWO algorithm.•A modified oversampling method which can generate imbalanced trajectory sequence and keep the temporal information in the newly formed sequence.•Taking the influence of surrounding vehicles into consideration by mathematically integrating the features of surrounding vehicles and subject vehicle for training the prediction classifier of lane change intention.
ISSN:0968-090X
1879-2359
DOI:10.1016/j.trc.2021.103414