Skip to main content

Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones

  • Conference paper
  • First Online:
European Robotics Forum 2024 (ERF 2024)

Part of the book series: Springer Proceedings in Advanced Robotics ((SPAR,volume 32))

Included in the following conference series:

  • 64 Accesses

Abstract

Miniaturized autonomous unmanned aerial vehicles (UAVs) are gaining popularity due to their small size, enabling new tasks such as indoor navigation or people monitoring. Nonetheless, their size and simple electronics pose severe challenges in implementing advanced onboard intelligence. This work proposes a new automatic optimization pipeline for visual pose estimation tasks using Deep Neural Networks (DNNs). The pipeline leverages two different Neural Architecture Search (NAS) algorithms to pursue a vast complexity-driven exploration in the DNNs’ architectural space. The obtained networks are then deployed on an off-the-shelf nano-drone equipped with a parallel ultra-low power System-on-Chip leveraging a set of novel software kernels for the efficient fused execution of critical DNN layer sequences. Our results improve the state-of-the-art reducing inference latency by up to 3.22\(\times \) at iso-error.

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

References

  1. Burrello, A., et al.: DORY: automatic end-to-end deployment of real-world DNNs on low-cost IoT MCUs. IEEE Trans. Comput. 1253–1268 (2021)

    Google Scholar 

  2. Burrello, A., et al.: Enhancing neural architecture search with multiple hardware constraints for deep learning model deployment on tiny IoT devices. IEEE Trans. Emerg. Top. Comput. 1–15 (2023)

    Google Scholar 

  3. Cereda, E., et al.: Deep neural network architecture search for accurate visual pose estimation aboard nano-UAVs. In: IEEE ICRA (2023)

    Google Scholar 

  4. Flamand, E., et al.: GAP-8: A RISC-V SoC for AI at the edge of the IoT. In: IEEE 29th ASAP, pp. 1–4 (2018)

    Google Scholar 

  5. Garofalo, A., et al.: Pulp-NN: a computing library for quantized neural network inference at the edge on RISC-V based parallel ultra low power clusters. In: 26th IEEE ICECS, pp. 33–36. IEEE (2019)

    Google Scholar 

  6. Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)

  7. Jahier Pagliari, D., et al.: Plinio: a user-friendly library of gradient-based methods for complexity-aware DNN optimization. In: FDL, pp. 1–8 (2023)

    Google Scholar 

  8. Liu, H., Simonyan, K., Yang, Y.: Darts: differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)

  9. Motetti, B.A., et al.: Adaptive deep learning for efficient visual pose estimation aboard ultra-low-power nano-drones. arXiv:2401.15236 (2024)

  10. Palossi, D., et al.: An open source and open hardware deep learning-powered visual navigation engine for autonomous nano-UAVs. In: 15th DCOSS, pp. 604–611 (2019)

    Google Scholar 

  11. Palossi, D., et al.: Fully onboard AI-powered human-drone pose estimation on ultralow-power autonomous flying nano-UAVs. IEEE IoTJ 9(3), 1913–1929 (2022)

    MATH  Google Scholar 

  12. Risso, M., et al.: Lightweight neural architecture search for temporal convolutional networks at the edge. IEEE Trans. Comput. (2022)

    Google Scholar 

  13. Tan, M., et al.: Mnasnet: platform-aware neural architecture search for mobile. In: IEEE/CVF CVPR, pp. 2820–2828 (2019)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Matteo Risso .

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

Risso, M. et al. (2024). Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones. In: Secchi, C., Marconi, L. (eds) European Robotics Forum 2024. ERF 2024. Springer Proceedings in Advanced Robotics, vol 32. Springer, Cham. https://doi.org/10.1007/978-3-031-76424-0_54

Download citation

Publish with us

Policies and ethics