Abstract
This work presents a comparison between different Convolutional Neural Network models, testing its performance when it leads a self-driving car in a simulated environment. To do so, driving data has been obtained manually driving the simulator as ground truth and different network models with diverse complexity levels has been created and trained with the data previously obtained using end-to-end deep learning techniques. Once this CNNs are trained, they are tested in the driving simulator, checking their ability of minimizing the car distance to the center of the lane, its heading error and its RMSE. The neural networks will be evaluated according to these parameters. Finally, conclusions will be drawn about the performance of the different models according to the parameters mentioned before in order to find the optimum CNN for the developed application.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Society of Automotive Engineers self-driving vehicles classification. https://www.cnet.com/roadshow/news/self-driving-car-guide-autonomous-explanation/
Vehicle detection using machine learning and computer vision. https://towardsdatascience.com/teaching-cars-to-see-vehicle-detection-using-machine-learning-and-computer-vision-54628888079a
Bojarski, M., et al.: End to end learning for self-driving cars. NVIDIA (2017). arxiv.org/pdf/1604.07316.pdf
Europilot. Marsauto. https://github.com/marsauto/europilot
Udacity self-driving car simulator project. https://github.com/udacity/self-driving-car-sim
Keras documentation. https://keras.io/
Shao, Y.: End-to-end learning for self-driving cars (2017). https://github.com/ymshao/End-to-End-Learning-for-Self-Driving-Cars
Convolutional, Long Short-Term Memory, fully connected deep neural networks. https://static.googleusercontent.com/media/research.google.com/es//pubs/archive/43455.pdf
Chi, L., Mu, Y.: Deep steering: learning end-to-end driving model from spatial and temporal visual cues (2017). https://arxiv.org/pdf/1708.03798.pdf
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556 [cs], September 2014
Acknowledgment
This work has been partially funded by the Spanish MINECO/FEDER through the SmartElderlyCar project (TRA2015-70501-C2-1-R), the DGT through the SERMON project (SPIP2017-02305), and from the RoboCity2030-III-CM project (Robótica aplicada a la mejora de la calidad de vida de los ciudadanos, fase III; S2013/MIT-2748), funded by Programas de actividades I+D (CAM) and cofunded by EU Structural Funds.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
del Egio, J., Bergasa, L.M., Romera, E., Gómez Huélamo, C., Araluce, J., Barea, R. (2019). Self-driving a Car in Simulation Through a CNN. In: Fuentetaja Pizán, R., García Olaya, Á., Sesmero Lorente, M., Iglesias Martínez, J., Ledezma Espino, A. (eds) Advances in Physical Agents. WAF 2018. Advances in Intelligent Systems and Computing, vol 855. Springer, Cham. https://doi.org/10.1007/978-3-319-99885-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-99885-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-99884-8
Online ISBN: 978-3-319-99885-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)