Skip to main content
SpringerLink
Log in

Vehicle Deceleration Prediction Based on Deep Neural Network at Braking Conditions

  • Published:
International Journal of Automotive Technology Aims and scope Submit manuscript

Abstract

The smart regenerative braking system in electric vehicles implements automatic control of the regeneration torque of motor to improve driver’s comfort and energy efficiency. To apply this system, the accurate prediction of the vehicle deceleration states is the preliminary step to reflect the driver’s behaviors. In this paper, we proposed a vehicle deceleration prediction model via deep neural network, which consists of a sequential recurrent neural network model with long-short term memory cell and a two-layer conventional neural network model. This model accommodates the physical constraint to designate the vehicle stop location in front of the traffic signals. The model is trained by vehicle experiment data with three drivers through the hyper-parameter optimization method. Using this model, the deceleration characteristics are characterized by two explicit parameters such that deceleration point, maximum point according to the initial slope and the shape of the braking profile. Using these two parameters as clustering variables through a K-means clustering method, the deceleration types are classified. These deceleration types to the input to the prediction model results in higher prediction accuracy of the vehicle states. The driving style of the three drivers at braking situations is analyzed according to the deceleration types as well.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Abbreviations

x :

input vector of sequence model

h :

hidden state of sequence model

σ :

activation function of neural network

b :

bias parameters of neural network node

W :

weight parameters of neural network node

i :

input gate of LSTM cell

f :

forget gate of LSTM cell

o :

output gate of LSTM cell

c :

cell state of LSTM cell

y :

output value of prediction model

t :

prediction time, s

d :

relative distance to stop location, m

v :

vehicle velocity, m/s

a :

vehicle acceleration, m/s2

ts :

input data index at prediction start time

te :

input data index at prediction end time

ni :

number of input vector of sequence model

i :

input gate of LSTM cell

o :

output gate of LSTM cell

g :

gate of LSTM cell

ref :

reference acceleration

References

  • Agostinelli, F., Hoffman, M., Sadowski, P. and Baldi, P. (2014). Learning activation functions to improve deep neural networks. Proc. Int. Conf. Learning Representations, San Diego, California, USA.

  • Balasubramanian, B. and Huzefa, A. C. (2017). Development of regeneration braking model for electric vehicle range improvement. Proc. IEEE Transportation Electrification Conf. (ITEC-India), Pune, India.

  • Bengio, Y., Simard, P. and Frasconi, P. (1994). Learning long term dependencies with gradient descent is difficult. IEEE Trans. Neural Networks5, 2, 157–166.

    Article  Google Scholar 

  • Bergstra, J., Bardenet, R., Bengio, Y. and Kégl, B. (2011). Algorithms for hyper-parameter optimization. Proc. 24th Int. Conf. Neural Information Processing Systems, Granada, Spain.

  • Butakov, V. A. and Ioannou, P. (2016). Personalized driver assistance for signalized intersections using V2I communication. IEEE Trans. Intelligent Transportation Systems17, 7, 1910–1919.

    Article  Google Scholar 

  • Butakov, V. and Ioannou, P. (2015). Personalized driver/vehicle lane change models for ADAS. IEEE Trans. Vehicular Technology64, 10, 4422–4431.

    Article  Google Scholar 

  • Cui, Z., Ke, R. and Wang, Y. (2018). Deep bidirectional and unidirectional LSTM recurrent neural network for network-wide traffic speed prediction, 1–12.

  • Demir, M. and Çavuşoğlu, A. (2012). A new driver behavior model to create realistic urban traffic environment. Transportation Research Part F: Traffic Psychology and Behaviour15, 3, 289–296.

    Article  Google Scholar 

  • Duchi, J., Hazan, E. and Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. J. Machine Learning Research, 12, 2121–2159.

    MathSciNet  MATH  Google Scholar 

  • Huang, X., Sun, J. and Sun, J. (2018). A car-following model considering asymmetric driving behavior based on long short-term memory neural networks. Transportation Research Part C: Emerging Technologies, 95, 346–362.

    Article  Google Scholar 

  • Ilievski, I., Akhtar, T., Feng, J. and Shoemaker, C. A. (2016). Efficient hyperparameter optimization of deep learning algorithms using deterministic RBF surrogates, 822–829.

  • Jang, C., Cho, S., Jeong, S., Suhr, J. K., Jung, H. G. and Sunwoo, M. (2017). Traffic light recognition exploiting map and localization at every stage. Expert Systems with Applications, 88, 290–304.

    Article  Google Scholar 

  • Jo, K., Chu, K. and Sunwoo, M. (2013). GPS-bias correction for precise localization of autonomous vehicles. Proc. IEEE Intelligent Vehicles Symp. (IV), Gold Coast, Australia.

  • Jo, K., Jo, Y., Suhr, J. K., Jung, H. G. and Sunwoo, M. (2015). Precise localization of an autonomous car based on probabilistic noise models of road surface marker features using multiple cameras. IEEE Trans. Intelligent Transportation Systems16, 6, 3377–3392.

    Article  Google Scholar 

  • Karlik, B. and Olgac, A. V. (2011). Performance analysis of various activation functions in generalized MLP architectures of neural networks. Int. J. Artificial Intelligence and Expert Systems (IJAE)1, 4, 111–122.

    Google Scholar 

  • Khodayari, A., Ghaffari, A., Kazemi, R. and Braunstingl, R. (2012). A modified car-following model based on a neural network model of the human driver effects. IEEE Trans. Systems, Man, and Cybernetics — Part A: Systems and Humans42, 6, 1440–1449.

    Article  Google Scholar 

  • Kingma, D. P. and Ba, J. (2014). Adam: A method for stochastic optimization. Proc. 3rd Int. Conf. Learning Representations, California, USA.

  • Lang, D., Schmied, R. and Del Re, L. (2014). Prediction of preceding driver behavior for fuel efficient cooperative adaptive cruise control. SAE Int. J. Engines7, 1, 14–20.

    Article  Google Scholar 

  • Lee, S. H., Lee, S. and Kim, M. H. (2018). Development of a driving behavior-based collision warning system using a neural network. Int. J. Automotive Technology19, 5, 837–844.

    Article  Google Scholar 

  • Lemieux, J. and Ma, Y. (2015). Vehicle speed prediction using deep learning. Proc. IEEE Vehicle Power and Propulsion Conf. (VPPC), Montreal, Canada.

  • Liebner, M., Klanner, F., Baumann, M., Ruhhammer, C. and Stiller, C. (2013). Velocity-based driver intent inference at urban intersections in the presence of preceding vehicles. IEEE Intelligent Transportation Systems Magazine5, 2, 10–21.

    Article  Google Scholar 

  • Lipton, Z. C., Berkowitz, J. and Elkan, C. (2015). A critical review of recurrent neural networks for sequence learning. arXiv: 1506.00019.

  • Ma, X., Tao, Z., Wang, Y., Yu, H. and Wang, Y. (2015). Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transportation Research Part C: Emerging Technologies, 54, 187–197.

    Article  Google Scholar 

  • Malinauskas, R. (2014). The Intelligent Driver Model: Analysis and Application to Adaptive Cruise Control. M. S. Thesis. Clemson University. Clemson, South Carolina, USA.

    Google Scholar 

  • Mansour, C. and Clodic, D. (2012). Optimized energy management control for the Toyota hybrid system using dynamic programming on a predicted route with short computation time. Int. J. Automotive Technology13, 2, 309–324.

    Article  Google Scholar 

  • McCall, J. C. and Trivedi, M. M. (2007). Driver behavior and situation aware brake assistance for intelligent vehicles. Proc. IEEE95, 2, 374–387.

    Article  Google Scholar 

  • Morton, J., Wheeler, T. A. and Kochenderfer, M. J. (2017). Analysis of recurrent neural networks for probabilistic modeling of driver behavior. IEEE Trans. Intelligent Transportation Systems18, 5, 1289–1298.

    Article  Google Scholar 

  • Qi, Y., Xiang, C., Wang, W., Wen, B. and Ding, F. (2018). Model predictive coordinated control for dual-mode power-split hybrid electric vehicle. Int. J. Automotive Technology19, 2, 345–358.

    Article  Google Scholar 

  • Sapna, S. (2012). Backpropagation learning algorithm based on levenberg marquardt algorithm. Proc. 4th Int. Workshop on Computer Networks & Communications, Coimbatore, India.

  • Sun, C., Moura, S. J., Hu, X., Hedrick, J. K. and Sun, F. (2015). Dynamic traffic feedback data enabled energy management in plug-in hybrid electric vehicles. IEEE Trans. Control Systems Technology23, 3, 1075–1086.

    Article  Google Scholar 

  • Sutskever, I., Martens, J., Dahl, G. and Hinton, G. (2013). On the importance of initialization and momentum in deep learning. Proc. 30th Int. Conf. Machine Learning, Atlanta, Georgia, USA.

  • Treiber, M., Hennecke, A. and Helbing, D. (2000). Congested traffic states in empirical observations and microsopic simulations. Physical Review E62, 2, 1805–1824.

    Article  Google Scholar 

  • Vlahogianni, E. I., Karlaftis, M. G. and Golias, J. C. (2014). Short-term traffic forecasting: Where we are and where we’re going. Transportation Research Part C: Emerging Technologies43, Part 1, 3–19.

    Article  Google Scholar 

  • Wang, W., Zhao, D., Xi, J., Leblanc, D. J. and Hedrick, J. K. (2017). Development and evaluation of two learning-based personalized driver models for car-following behaviors. Proc. American Control Conf. (ACC), Seattle, Washington, D.C., USA.

  • Zhang, D., Xiao, Q., Wang, J. and Li, K. (2013). Driver curve speed model and its application to ACC speed control in curved roads. Int. J. Automotive Technology14, 2, 241–247.

    Article  Google Scholar 

  • Zheng, L. J., Tian, C., Sun, D. H. and Liu, W. N. (2012). A new car-following model with consideration of anticipation driving behavior. Nonlinear Dynamics70, 2, 1205–1211.

    Article  MathSciNet  Google Scholar 

  • Zhou, M., Qu, X. and Li, X. (2017). A recurrent neural network based microscopic car following model to predict traffic oscillation. Transportation Research Part C: Emerging Technologies, 84, 245–264.

    Article  Google Scholar 

Download references

Acknowledgement

This work was financially supported by the BK21 plus program (22A20130000045) under the Ministry of Education, Republic of Korea, the Industrial Strategy Technology Development Program of Ministry of Trade, Industry and Energy (No. 10039673), the Industrial Strategy Technology Development Program of Ministry of Trade, Industry and Energy (No. 10042633), This work was supported by the Energy Resource R&D program (2006ETR11P091C) under the Ministry of Knowledge Economy, Republic of Korea, and the Industrial Strategic Technology Development Program (10060068, “Development of Next Generation E/E Architecture and Body Domain Unit for Automotive Body Domain) funded by the Ministry of Trade, Industry & Energy (MOTIE, Korea).

Author information

Authors and Affiliations

  1. Department of Automotive Engineering, Hanyang University, Seoul, 04763, Korea

    Kyunghan Min, Kyuhwan Yeon, Yuhyeok Jo, Gyubin Sim & Myoungho Sunwoo

  2. Department of Mechanical and Automotive Engineering, Keimyung University, Daegu, 42601, Korea

    Manbae Han

Authors
  1. Kyunghan Min
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kyuhwan Yeon
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuhyeok Jo
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Gyubin Sim
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Myoungho Sunwoo
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Manbae Han
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Manbae Han.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Min, K., Yeon, K., Jo, Y. et al. Vehicle Deceleration Prediction Based on Deep Neural Network at Braking Conditions. Int.J Automot. Technol. 21, 91–102 (2020). https://doi.org/10.1007/s12239-020-0010-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12239-020-0010-2

Key Words

Search

Navigation