Cloning Safe Driving Behavior for Self-Driving Cars using Convolutional Neural Networks

Author(s): Wael Farag*.

Journal Name: Recent Patents on Computer Science

Volume 12 , Issue 2 , 2019

Become EABM
Become Reviewer

Graphical Abstract:


Abstract:

Background: In this paper, a Convolutional Neural Network (CNN) to learn safe driving behavior and smooth steering manoeuvring, is proposed as an empowerment of autonomous driving technologies. The training data is collected from a front-facing camera and the steering commands issued by an experienced driver driving in traffic as well as urban roads.

Methods: This data is then used to train the proposed CNN to facilitate what it is called “Behavioral Cloning”. The proposed Behavior Cloning CNN is named as “BCNet”, and its deep seventeen-layer architecture has been selected after extensive trials. The BCNet got trained using Adam’s optimization algorithm as a variant of the Stochastic Gradient Descent (SGD) technique.

Results: The paper goes through the development and training process in details and shows the image processing pipeline harnessed in the development.

Conclusion: The proposed approach proved successful in cloning the driving behavior embedded in the training data set after extensive simulations.

Keywords: Behavioral cloning, convolutional neural network, autonomous driving, machine learning, stochastic gradient descent, image processing.

[1]
K. Mansour, and W. Farag, AiroDiag: A Sophisticated Tool that Diagnoses and Updates Vehicles Software Over Air2012 IEEE Intern. Electric Vehicle Conference (IEVC) TD Convention Center Greenville, SC, USA,, pp. 1-7. 2012
[2]
W. Farag, "CANTrack: Enhancing automotive CAN bus security using intuitive encryption algorithms", In: 7th Inter. Conf. on Modeling, Simulation, and Applied Optimization (ICMSAO), Sharjah, UAE, 2017, pp. 1-5.
[3]
Á. Arcos-García, J.A. Álvarez-García, and L.M. Soria-Morillo, "Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods", Neural Netw., vol. 99, pp. 158-165, 2018.
[4]
W. Farag, and Z. Saleh, Traffic Signs Identification by Deep Learning for Autonomous DrivingIET Smart Cities Symposium (SCS'18), Zallaq, Bahrain, pp. 22-23 April. 2018
[5]
M. Bojarski, D. Del-Testa, D. Dworakowski, B. Firner, B. Flepp, P. Goyal, D. Jackel, M. Monfort, U. Muller, J. Zhang, X. Zhang, J. Zhao, and K. Zieba, "End to end learning for self-driving cars", Comput. Vision Pattern Recong., p. arXiv:1604.07316. 2016
[6]
Keras Documentation, Available from:, https://keras.io/
[7]
TensorFlow, Available from:, https://www.tensorflow.org/
[8]
"Python, Available from:", https://www.python.org/
[9]
Udacity Sample Training Data, Available from:, https://d17h27t6h515a5.cloudfront.net/topher/2016/December/584f6edd_data/data.zip
[10]
Udacity Simulator, Available from:, https://github.com/udacity/self-driving-car-sim
[11]
ShervineAmidi, Available from:, https://stanford.edu/~shervine/ blog/keras-how-to-generate-data-on-the-fly.html
[12]
M. Nagiub, and W. Farag, Automatic selection of compiler options using genetic techniques for embedded software designIEEE 14th Inter., Symposium on Comp. Intelligence and Informatics (CINTI), Budapest, Hungary, 2013, pp. 69-74.
[13]
D.P. Kingma, and J. Ba, Adam: A Method for Stochastic Optimization3rd International Conference for Learning Representations, San Diego, USA, 2015, pp. 1-13.
[14]
L. Bottou, Online Algorithms and Stochastic Approximations.Online Learning Neural Nets., Cambridge University Press: Cambridge, 1998.
[15]
S. Ruder, "An overview of gradient descent optimization algorithms", arXiv:1609.04747v2, 15th Jun, 2017.
[16]
W. Farag, Synthesis of intelligent hybrid systems for modelling and control., University of Waterloo: Canada, 1998.


Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 12
ISSUE: 2
Year: 2019
Page: [120 - 127]
Pages: 8
DOI: 10.2174/2213275911666181106160002
Price: $58

Article Metrics

PDF: 17
HTML: 3
EPUB: 1
PRC: 1