Affiliation:
1. Electrical Engineering Department, American University of the Middle East, Kuwait, Egypt
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.
Publisher
Bentham Science Publishers Ltd.
Reference16 articles.
1. Mansour K, Farag W.
2. Farag W. CANTrack: Enhancing automotive CAN bus security using intuitive encryption algorithms
3. Arcos-García Á, Álvarez-García JA, Soria-Morillo LM. Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods.
4. Farag W, Saleh Z.
5. Bojarski M, Del-Testa D, Dworakowski D, Firner B, Flepp B, Goyal P, Jackel D, Monfort M, Muller U, Zhang J, Zhang X, Zhao J, Zieba K. End to end learning for self-driving cars
Cited by
19 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献