Skip to main content

Continuous Integration of Neural Networks in Autonomous Systems

  • Conference paper
  • First Online:
Engineering of Computer-Based Systems (ECBS 2023)

Abstract

The perception of the autonomous driving software of the FS223, a low-level sensor fusion of Lidar and Camera data requires the use of a neural network for image classification. To keep the neural network up to date with updates in the training data, we introduce a Continuous Integration (CI) pipeline to re-train the network. The network is then automatically validated and integrated into the code base of the autonomous system. The introduction of proper CI methods in these high-speed embedded software applications is an application of state-of-the-art MLOps techniques that aim to provide rapid generation of production-ready models. It further serves the purpose of professionalizing the otherwise script-based software production, which is re-done almost completely every year as the teams change from one year to the next.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    SAE international is a standards developing organization for engineers, see: https://www.sae.org/.

  2. 2.

    GET racing participates annually in the events since 2005, see https://www.get-racing.de/.

  3. 3.

    GitLab is a DevOps platform that aims to assist software developers with project management, versioning, etc. See https://about.gitlab.com/company/.

  4. 4.

    Coral offers hardware and software platforms for embedded systems. Our accelerator: https://coral.ai/products/pcie-accelerator.

References

  1. Fowler, M., Foemmel, M.: Continuous integration (2006)

    Google Scholar 

  2. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)

    Google Scholar 

  3. Kabzan, J., et al.: AMZ driverless: the full autonomous racing system. J. Field Robot. 37(7), 1267–1294 (2020)

    Article  Google Scholar 

  4. Karamitsos, I., Albarhami, S., Apostolopoulos, C.: Applying DevOps practices of continuous automation for machine learning. Information 11(7), 363 (2020)

    Article  Google Scholar 

  5. Kreuzberger, D., Kühl, N., Hirschl, S.: Machine learning operations (mlops): overview, definition, and architecture. IEEE Access (2023)

    Google Scholar 

  6. Lever, J., Krzywinski, M., Altman, N.: N. model selection and overfitting. Nat. Methods (2016). https://doi.org/10.1038/nmeth.3968

  7. Lu, D., Weng, Q.: A survey of image classification methods and techniques for improving classification performance. Int. J. Remote Sens. 28(5), 823–870 (2007). https://doi.org/10.1080/01431160600746456

    Article  Google Scholar 

  8. Meyer, M.: Continuous integration and its tools. IEEE Softw. 31(3), 14–16 (2014). https://doi.org/10.1109/MS.2014.58

    Article  Google Scholar 

  9. Salecker, J.: Whitepaper-tesla-floating-formats, November 2021

    Google Scholar 

  10. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: inverted residuals and linear bottlenecks (2019)

    Google Scholar 

  11. Stathakis, D., Vasilakos, A.: Comparison of computational intelligence based classification techniques for remotely sensed optical image classification. IEEE Trans. Geosci. Remote Sens. 44(8), 2305–2318 (2006). https://doi.org/10.1109/TGRS.2006.872903

    Article  Google Scholar 

  12. Steffen, B., Zohren, J., Pazarci, U., Kullmann, F., Weißenfels, H.: Gitlab Demo Project for Paper “Continuous Integration of Neural Networks in Autonomous Systems”, September 2023. https://doi.org/10.5281/zenodo.8370907

  13. Vödisch, N., Dodel, D., Schötz, M.: Fsoco: the formula student objects in context dataset. arXiv preprint arXiv:2012.07139 (2020)

  14. Wei, P., Cagle, L., Reza, T., Ball, J., Gafford, J.: Lidar and camera detection fusion in a real-time industrial multi-sensor collision avoidance system. Electronics 7(6), 84 (2018). https://doi.org/10.3390/electronics7060084

  15. Wirth, R., Hipp, J.: Crisp-DM: towards a standard process model for data mining. In: Proceedings of the 4th International Conference on the Practical Applications of Knowledge Discovery and Data Mining, vol. 1, pp. 29–39. Manchester (2000)

    Google Scholar 

  16. Ying, X.: An overview of overfitting and its solutions. J. Phys. Conf. Ser. 1168, 022022. IOP Publishing (2019)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Bruno Steffen .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Steffen, B., Zohren, J., Pazarci, U., Kullmann, F., Weißenfels, H. (2024). Continuous Integration of Neural Networks in Autonomous Systems. In: Kofroň, J., Margaria, T., Seceleanu, C. (eds) Engineering of Computer-Based Systems. ECBS 2023. Lecture Notes in Computer Science, vol 14390. Springer, Cham. https://doi.org/10.1007/978-3-031-49252-5_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-49252-5_21

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-49251-8

  • Online ISBN: 978-3-031-49252-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics