Miniaturized autonomous unmanned aerial vehicles (UAVs) are an emerging and trending topic. With their form factor as big as the palm of one hand, they can reach spots otherwise inaccessible to bigger robots and safely operate in human surroundings. The simple electronics aboard such robots (sub-100 mW) make them particularly cheap and attractive but pose significant challenges in enabling onboard sophisticated intelligence. In this work, we leverage a novel neural architecture search (NAS) technique to automatically identify several Pareto-optimal convolutional neural networks (CNNs) for a visual pose estimation task. Our work demonstrates how reallife and field-tested robotics applications can concretely leverage NAS technologies to automatically and efficiently optimize CNNs for the specific hardware constraints of small UAVs. We deploy several NAS-optimized CNNs and run them in closed-loop aboard a 27-g Crazyflie nano-UAV equipped with a parallel ultra-low power System-on-Chip. Our results improve the State-of-the-Art by reducing the in-field control error of 32% while achieving a real-time onboard inference-rate of ~10Hz@10mW and ~50Hz@90mW.

Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs / Cereda, Elia; Crupi, Luca; Risso, Matteo; Burrello, Alessio; Benini, Luca; Giusti, Alessandro; Jahier Pagliari, Daniele; Palossi, Daniele. - ELETTRONICO. - (2023), pp. 6065-6071. (Intervento presentato al convegno 2023 IEEE International Conference on Robotics and Automation (ICRA) tenutosi a London (UK) nel 29 May 2023 - 02 June 2023) [10.1109/ICRA48891.2023.10160369].

Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs

Risso, Matteo;Burrello, Alessio;Benini, Luca;Jahier Pagliari, Daniele;
2023

Abstract

Miniaturized autonomous unmanned aerial vehicles (UAVs) are an emerging and trending topic. With their form factor as big as the palm of one hand, they can reach spots otherwise inaccessible to bigger robots and safely operate in human surroundings. The simple electronics aboard such robots (sub-100 mW) make them particularly cheap and attractive but pose significant challenges in enabling onboard sophisticated intelligence. In this work, we leverage a novel neural architecture search (NAS) technique to automatically identify several Pareto-optimal convolutional neural networks (CNNs) for a visual pose estimation task. Our work demonstrates how reallife and field-tested robotics applications can concretely leverage NAS technologies to automatically and efficiently optimize CNNs for the specific hardware constraints of small UAVs. We deploy several NAS-optimized CNNs and run them in closed-loop aboard a 27-g Crazyflie nano-UAV equipped with a parallel ultra-low power System-on-Chip. Our results improve the State-of-the-Art by reducing the in-field control error of 32% while achieving a real-time onboard inference-rate of ~10Hz@10mW and ~50Hz@90mW.
2023
979-8-3503-2365-8
File in questo prodotto:
File Dimensione Formato  
2303.01931.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 1.8 MB
Formato Adobe PDF
1.8 MB Adobe PDF Visualizza/Apri
Deep_Neural_Network_Architecture_Search_for_Accurate_Visual_Pose_Estimation_aboard_Nano-UAVs.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.95 MB
Formato Adobe PDF
1.95 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2980543