Abstract
The interest of the automotive industry in deep-learning-based technology is growing and related applications are going to be pervasively used in the modern automobiles. Automotive is a domain where different standards addressing the software development process apply, as Automotive SPICE and, for functional safety relevant products, ISO 26262. So, in the automotive software engineering community, the awareness of the need to integrate deep-learning-based development with development approaches derived from these standards is growing, at the technical, methodological, and cultural levels. This paper starts from a lifecycle for deep-learning-based development defined by the authors, called W-model, and addresses the issue of the applicability of Automotive SPICE to deep-learning-based developments. A conceptual mapping between Automotive SPICE and the deep learning lifecycles phases is provided in this paper with the aim of highlighting the open issues related to the applicability of automotive software development standards to deep learning.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Falcini, F., Lami, G., Costanza, A.M.: Deep learning in automotive software. IEEE Softw. 34(3), 56–63 (2017). doi:10.1109/MS.2017.79
Levinson, J., et al.: Towards fully autonomous driving: systems and algorithms. In: Proceedings of 2011 IEEE Intelligent Vehicles Symposium (IV11) (2011). ieeexplore.ieee.org/document/5940562
Parlak, A., et al.: Application of artificial neural network to predict specific fuel consumption and exhaust temperature for a diesel engine. Appl. Therm. Eng. 26(8–9), 824–828 (2006)
Kang, M.-J., Kang, J.-W.: Intrusion detection system using deep neural network for in-vehicle network security. PLoS ONE, 11(6), e0155781 (2016). journals.plos.org/plosone/article?id=10.1371/journal.pone.0155781
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. J. 61, 85–117 (2015)
Haykin, S.: Neural Networks and Learning Machines. Prentice-Hall, New York (2009)
Credi, J.: Traffic sign classification with deep convolutional neural networks. Master’s thesis, Department of Applied Mechanics, Chalmers University of Technology (2016)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Miao, H., et al.: ModelHub: lifecycle management for deep learning. University of Maryland (2015). www.cs.umd.edu/class/spring2016/cmsc396h/downloads/modelhub.pdf
Automotive SPICE Process Assessment/Reference Model, ver. 3.0, Verband der Automobilindustrie (2015). www.automotivespice.com/leadmin/software-download/Automotive_SPICE_PAM_30.pdf
ISO 26262—Road Vehicles—Functional Safety—Part 1: Vocabulary, Int’l Standard Org. (2011)
ISO/AWI PAS 21448—Road Vehicles—Safety of the Intended Functionality, Int’l Standard Org. (2016)
Pressman, M.: Inside Nvidia’s New Self-Driving Supercomputer Powering Tesla’s Autopilot. CleanTechnica, 25 October 2016. cleantechnica.com/2016/10/25/inside-nvidias-new-self-driving-supercomputer-powering-teslas-autopilot
CEVA and AdasWorks to Demonstrate Free Space Detection for Autonomous Driving at AutoSens Conference 2016, CEVA, 15 September 2016. ceva-dsp.mediaroom.com/2016-09-15-CEVA-and-AdasWorks-to-Demonstrate-Free-Space-Detection-for-Autonomous-Driving-at-AutoSens-Conference-2016
De Ambroggi, L.: Artificial Intelligence Systems for Autonomous Driving on the Rise, IHS Says, IHS, 13 June 2016. technology.ihs.com/579746artficial-intelligence-systems-for-autonomous-drivingon-the-rise-ihs-says
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Falcini, F., Lami, G. (2017). Deep Learning in Automotive: Challenges and Opportunities. In: Mas, A., Mesquida, A., O'Connor, R., Rout, T., Dorling, A. (eds) Software Process Improvement and Capability Determination. SPICE 2017. Communications in Computer and Information Science, vol 770. Springer, Cham. https://doi.org/10.1007/978-3-319-67383-7_21
Download citation
DOI: https://doi.org/10.1007/978-3-319-67383-7_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67382-0
Online ISBN: 978-3-319-67383-7
eBook Packages: Computer ScienceComputer Science (R0)