Regular Papers

International Journal of Control, Automation, and Systems 2024; 22(7): 2301-2312

https://doi.org/10.1007/s12555-021-1113-x

© The International Journal of Control, Automation, and Systems

Method of Predicting Braking Intention Using LSTM-CNN-Attention With Hyperparameters Optimized by Genetic Algorithm

Wei Yang*, Yu Huang, Kongming Jiang, Zhen Zhang, Ketong Zong, and Qin Ruan

Chongqing University

Abstract

Prediction of a driver’s braking intention enables the advanced driver assistance system (ADAS) to intervene in the braking system as early as possible, which may shorten braking distance and improve driving safety. This paper proposes a novel deep learning model called LSTM-CNN-Attention that combines a long short-term memory (LSTM) neural network, convolutional neural network (CNN), and Attention mechanism for extracting spatiotemporal features of multi-sensor data to improve prediction accuracy. The proposed model inherits both temporal and spatial feature extraction abilities from LSTM and CNN. The LSTM-CNN-Attention model has a parallel architecture, which enhances the feature extraction ability of the model for multi-sensor time series data and improves the prediction accuracy of the driver’s braking intention before the braking action. Furthermore, a driving simulator is set up to sample driving data for training and evaluating the proposed method. According to the results of the experiment, the model obtains up to 3.16% higher accuracy than the baseline models such as LSTM, CNN, and bidirectional LTSM (Bi-LSTM). Additionally, the influence of sliding window size and prediction horizon on the performance of the method is investigated. A method of tuning hyperparameters using the genetic algorithm is presented. The results demonstrate that the prediction accuracy increases by about 2% after being optimized by GA.

Keywords Advanced driver assistance systems, attention mechanism, braking intention prediction, CNN, LTSM, parametric tuning by genetic algorithm.

Article

Regular Papers

International Journal of Control, Automation, and Systems 2024; 22(7): 2301-2312

Published online July 1, 2024 https://doi.org/10.1007/s12555-021-1113-x

Copyright © The International Journal of Control, Automation, and Systems.

Method of Predicting Braking Intention Using LSTM-CNN-Attention With Hyperparameters Optimized by Genetic Algorithm

Wei Yang*, Yu Huang, Kongming Jiang, Zhen Zhang, Ketong Zong, and Qin Ruan

Chongqing University

Abstract

Prediction of a driver’s braking intention enables the advanced driver assistance system (ADAS) to intervene in the braking system as early as possible, which may shorten braking distance and improve driving safety. This paper proposes a novel deep learning model called LSTM-CNN-Attention that combines a long short-term memory (LSTM) neural network, convolutional neural network (CNN), and Attention mechanism for extracting spatiotemporal features of multi-sensor data to improve prediction accuracy. The proposed model inherits both temporal and spatial feature extraction abilities from LSTM and CNN. The LSTM-CNN-Attention model has a parallel architecture, which enhances the feature extraction ability of the model for multi-sensor time series data and improves the prediction accuracy of the driver’s braking intention before the braking action. Furthermore, a driving simulator is set up to sample driving data for training and evaluating the proposed method. According to the results of the experiment, the model obtains up to 3.16% higher accuracy than the baseline models such as LSTM, CNN, and bidirectional LTSM (Bi-LSTM). Additionally, the influence of sliding window size and prediction horizon on the performance of the method is investigated. A method of tuning hyperparameters using the genetic algorithm is presented. The results demonstrate that the prediction accuracy increases by about 2% after being optimized by GA.

Keywords: Advanced driver assistance systems, attention mechanism, braking intention prediction, CNN, LTSM, parametric tuning by genetic algorithm.

IJCAS
July 2024

Vol. 22, No. 7, pp. 2055~2340

Stats or Metrics

Share this article on

  • line

Related articles in IJCAS

IJCAS

eISSN 2005-4092
pISSN 1598-6446