Skip to main content
Erschienen in:
Buchtitelbild

2017 | Supplement | Buchkapitel

Making the Case for Safety of Machine Learning in Highly Automated Driving

verfasst von : Simon Burton, Lydia Gauerhof, Christian Heinzemann

Erschienen in: Computer Safety, Reliability, and Security

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

This paper describes the challenges involved in arguing the safety of highly automated driving functions which make use of machine learning techniques. An assurance case structure is used to highlight the systems engineering and validation considerations when applying machine learning methods for highly automated driving. Particular focus is placed on addressing functional insufficiencies in the perception functions based on convolutional neural networks and possible types of evidence that can be used to mitigate against such risks.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete problems in AI safety. arXiv e-prints, June 2016 Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete problems in AI safety. arXiv e-prints, June 2016
2.
Zurück zum Zitat Attenberg, J., Ipeirotis, P., Provost, F.: Beat the machine: challenging humans to find a predictive model’s “unknown unknowns”. ACM J. Data Inf. Qual. 1(1), 1–17 (2014) Attenberg, J., Ipeirotis, P., Provost, F.: Beat the machine: challenging humans to find a predictive model’s “unknown unknowns”. ACM J. Data Inf. Qual. 1(1), 1–17 (2014)
3.
Zurück zum Zitat Bergenhem, C., Johansson, R., Söderberg, A., Nilsson, J., Tryggvesson, J., Törngren, M., Ursing, S.: How to reach complete safety requirement refinement for autonomous vehicles. Technical report, CARS 2015 - Critical Automotive applications: Robustness & Safety, September 2015, Paris, France (2015) Bergenhem, C., Johansson, R., Söderberg, A., Nilsson, J., Tryggvesson, J., Törngren, M., Ursing, S.: How to reach complete safety requirement refinement for autonomous vehicles. Technical report, CARS 2015 - Critical Automotive applications: Robustness & Safety, September 2015, Paris, France (2015)
4.
Zurück zum Zitat Binder, A., Bach, S., Montavon, G., Müller, K.R., Samek, W.: Layer-wise relevance propagation for deep neural network architectures. In: Kim, K., Joukov, N. (eds.) Information Science and Applications (ICISA). LNEE, vol. 376, pp. 913–922. Springer, Singapore (2016). doi:10.1007/978-981-10-0557-2_87 Binder, A., Bach, S., Montavon, G., Müller, K.R., Samek, W.: Layer-wise relevance propagation for deep neural network architectures. In: Kim, K., Joukov, N. (eds.) Information Science and Applications (ICISA). LNEE, vol. 376, pp. 913–922. Springer, Singapore (2016). doi:10.​1007/​978-981-10-0557-2_​87
6.
Zurück zum Zitat Chen, C., Seff, A., Kornhauser, A., Xiao, J.: Deepdriving: learning affordance for direct perception in autonomous driving. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2722–2730. IEEE (2015) Chen, C., Seff, A., Kornhauser, A., Xiao, J.: Deepdriving: learning affordance for direct perception in autonomous driving. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2722–2730. IEEE (2015)
7.
Zurück zum Zitat Christmann, A., Steinwart, I.: Support Vector Machines. Springer, Heidelberg (2008)MATH Christmann, A., Steinwart, I.: Support Vector Machines. Springer, Heidelberg (2008)MATH
8.
9.
Zurück zum Zitat Feinberg, E.A., Shwartz, A. (eds.): International Series in Operations Research & Management Science, vol. 40. Springer, Heidelberg (2002) Feinberg, E.A., Shwartz, A. (eds.): International Series in Operations Research & Management Science, vol. 40. Springer, Heidelberg (2002)
10.
Zurück zum Zitat Friedman, N., Geiger, D., Goldszmidt, M.: Bayesian network classifiers. Mach. Learn. 29(2), 131–163 (1997)CrossRefMATH Friedman, N., Geiger, D., Goldszmidt, M.: Bayesian network classifiers. Mach. Learn. 29(2), 131–163 (1997)CrossRefMATH
11.
Zurück zum Zitat Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)MATH Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)MATH
12.
13.
Zurück zum Zitat Heckemann, K., Gesell, M., Pfister, T., Berns, K., Schneider, K., Trapp, M.: Safe automotive software. In: König, A., Dengel, A., Hinkelmann, K., Kise, K., Howlett, R.J., Jain, L.C. (eds.) KES 2011. LNCS, vol. 6884, pp. 167–176. Springer, Heidelberg (2011). doi:10.1007/978-3-642-23866-6_18 CrossRef Heckemann, K., Gesell, M., Pfister, T., Berns, K., Schneider, K., Trapp, M.: Safe automotive software. In: König, A., Dengel, A., Hinkelmann, K., Kise, K., Howlett, R.J., Jain, L.C. (eds.) KES 2011. LNCS, vol. 6884, pp. 167–176. Springer, Heidelberg (2011). doi:10.​1007/​978-3-642-23866-6_​18 CrossRef
15.
Zurück zum Zitat IEEE: IEEE standard adoption of ISO/IEC 15026–1 - systems and software engineering - systems and software assurance (2014) IEEE: IEEE standard adoption of ISO/IEC 15026–1 - systems and software engineering - systems and software assurance (2014)
16.
Zurück zum Zitat ISO: ISO 26262: Road vehicles - functional safety (2011) ISO: ISO 26262: Road vehicles - functional safety (2011)
17.
Zurück zum Zitat Kaufman, S., Rosset, S., Perlich, C.: Leakage in data mining: Formulation, detection, and avoidance. In: Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 556–563. ACM (2011) Kaufman, S., Rosset, S., Perlich, C.: Leakage in data mining: Formulation, detection, and avoidance. In: Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 556–563. ACM (2011)
19.
Zurück zum Zitat 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) 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)
20.
Zurück zum Zitat Mohan, N., Törngren, M., Izosimov, V., Kaznov, V., Roos, P., Svahn, J., Gustavsson, J., Nesic, D.: Challenges in architecting fully automated driving; with an emphasis on heavy commercial vehicles. In: 2016 Workshop on Automotive Systems/Software Architectures (2016) Mohan, N., Törngren, M., Izosimov, V., Kaznov, V., Roos, P., Svahn, J., Gustavsson, J., Nesic, D.: Challenges in architecting fully automated driving; with an emphasis on heavy commercial vehicles. In: 2016 Workshop on Automotive Systems/Software Architectures (2016)
21.
Zurück zum Zitat Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, pp. 427–436 (2015) Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, pp. 427–436 (2015)
22.
Zurück zum Zitat Piziali, A.: Functional Verification Coverage Measurement and Analysis. Springer, Heidelberg (2008) Piziali, A.: Functional Verification Coverage Measurement and Analysis. Springer, Heidelberg (2008)
23.
Zurück zum Zitat Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)MATH Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)MATH
24.
25.
Zurück zum Zitat SAE: J3016, taxonomy and definitions for terms related to on-road motor vehicle automated driving systems (2013) SAE: J3016, taxonomy and definitions for terms related to on-road motor vehicle automated driving systems (2013)
26.
Zurück zum Zitat Tas, Ö.S., Kuhnt, F., Zöllner, J.M., Stiller, C.: Functional system architectures towards fully automated driving. In: 2016 IEEE Intelligent Vehicles Symposium. IEEE (2016) Tas, Ö.S., Kuhnt, F., Zöllner, J.M., Stiller, C.: Functional system architectures towards fully automated driving. In: 2016 IEEE Intelligent Vehicles Symposium. IEEE (2016)
27.
Zurück zum Zitat Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., Chaudhary, V., Young, M., Crespo, J.F. Dennison, D.: Hidden technical debt in machine learning systems. Advances in Neural Information Processing Systems, 28 (NIPS 2015) (2015) Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., Chaudhary, V., Young, M., Crespo, J.F. Dennison, D.: Hidden technical debt in machine learning systems. Advances in Neural Information Processing Systems, 28 (NIPS 2015) (2015)
28.
Zurück zum Zitat Shalev-Shwartz, S., Shashua, A.: On the sample complexity of end-to-end training vs. semantic abstraction training. In: arXiv:1604.06915 (2016) Shalev-Shwartz, S., Shashua, A.: On the sample complexity of end-to-end training vs. semantic abstraction training. In: arXiv:​1604.​06915 (2016)
29.
Zurück zum Zitat Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: arXiv:1312.6034 (2014) Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: arXiv:​1312.​6034 (2014)
30.
Zurück zum Zitat Kelly, T., Weaver, R.: The goal structuring notation - a safety argument notation. In: Proceedings of the DSN 2004 Workshop on Assurance Cases (2004) Kelly, T., Weaver, R.: The goal structuring notation - a safety argument notation. In: Proceedings of the DSN 2004 Workshop on Assurance Cases (2004)
31.
Zurück zum Zitat Varshney, K.: Engineering safety in machine learning. ArXiv e-prints, January 2016 Varshney, K.: Engineering safety in machine learning. ArXiv e-prints, January 2016
Metadaten
Titel
Making the Case for Safety of Machine Learning in Highly Automated Driving
verfasst von
Simon Burton
Lydia Gauerhof
Christian Heinzemann
Copyright-Jahr
2017
DOI
https://doi.org/10.1007/978-3-319-66284-8_1

Premium Partner