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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
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)
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)
Cereda, E., et al.: Deep neural network architecture search for accurate visual pose estimation aboard nano-UAVs. In: IEEE ICRA (2023)
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)
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)
Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
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)
Liu, H., Simonyan, K., Yang, Y.: Darts: differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)
Motetti, B.A., et al.: Adaptive deep learning for efficient visual pose estimation aboard ultra-low-power nano-drones. arXiv:2401.15236 (2024)
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)
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)
Risso, M., et al.: Lightweight neural architecture search for temporal convolutional networks at the edge. IEEE Trans. Comput. (2022)
Tan, M., et al.: Mnasnet: platform-aware neural architecture search for mobile. In: IEEE/CVF CVPR, pp. 2820–2828 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
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
DOI: https://doi.org/10.1007/978-3-031-76424-0_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-76423-3
Online ISBN: 978-3-031-76424-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)