Many emerging applications of nano-sized unmanned aerial vehicles (UAVs), with a few cm(2) form-factor, revolve around safely interacting with humans in complex scenarios, for example, monitoring their activities or looking after people needing care. Such sophisticated autonomous functionality must be achieved while dealing with severe constraints in payload, battery, and power budget (similar to 100 mW). In this work, we attack a complex task going from perception to control: to estimate and maintain the nano-UAV's relative 3-D pose with respect to a person while they freely move in the environment-a task that, to the best of our knowledge, has never previously been targeted with fully onboard computation on a nano-sized UAV. Our approach is centered around a novel vision-based deep neural network (DNN), called Frontnet, designed for deployment on top of a parallel ultra-low power (PULP) processor aboard a nano-UAV. We present a vertically integrated approach starting from the DNN model design, training, and dataset augmentation down to 8-bit quantization and deployment in-field. PULP-Frontnet can operate in real-time (up to 135 frame/s), consuming less than 87 mW for processing at peak throughput and down to 0.43 mJ/frame in the most energy-efficient operating point. Field experiments demonstrate a closed-loop top-notch autonomous navigation capability, with a tiny 27-g Crazyflie 2.1 nano-UAV. Compared against an ideal sensing setup, onboard pose inference yields excellent drone behavior in terms of median absolute errors, such as positional (onboard: 41 cm, ideal: 26 cm) and angular (onboard: 3.7 degrees, ideal: 4.1 degrees). We publicly release videos and the source code of our work.

Fully Onboard AI-Powered Human-Drone Pose Estimation on Ultralow-Power Autonomous Flying Nano-UAVs / Palossi, D; Zimmerman, N; Burrello, A; Conti, F; Muller, H; Gambardella, Lm; Benini, L; Giusti, A; Guzzi, J. - In: IEEE INTERNET OF THINGS JOURNAL. - ISSN 2327-4662. - 9:3(2022), pp. 1913-1929. [10.1109/JIOT.2021.3091643]

Fully Onboard AI-Powered Human-Drone Pose Estimation on Ultralow-Power Autonomous Flying Nano-UAVs

Burrello, A;
2022

Abstract

Many emerging applications of nano-sized unmanned aerial vehicles (UAVs), with a few cm(2) form-factor, revolve around safely interacting with humans in complex scenarios, for example, monitoring their activities or looking after people needing care. Such sophisticated autonomous functionality must be achieved while dealing with severe constraints in payload, battery, and power budget (similar to 100 mW). In this work, we attack a complex task going from perception to control: to estimate and maintain the nano-UAV's relative 3-D pose with respect to a person while they freely move in the environment-a task that, to the best of our knowledge, has never previously been targeted with fully onboard computation on a nano-sized UAV. Our approach is centered around a novel vision-based deep neural network (DNN), called Frontnet, designed for deployment on top of a parallel ultra-low power (PULP) processor aboard a nano-UAV. We present a vertically integrated approach starting from the DNN model design, training, and dataset augmentation down to 8-bit quantization and deployment in-field. PULP-Frontnet can operate in real-time (up to 135 frame/s), consuming less than 87 mW for processing at peak throughput and down to 0.43 mJ/frame in the most energy-efficient operating point. Field experiments demonstrate a closed-loop top-notch autonomous navigation capability, with a tiny 27-g Crazyflie 2.1 nano-UAV. Compared against an ideal sensing setup, onboard pose inference yields excellent drone behavior in terms of median absolute errors, such as positional (onboard: 41 cm, ideal: 26 cm) and angular (onboard: 3.7 degrees, ideal: 4.1 degrees). We publicly release videos and the source code of our work.
File in questo prodotto:
File Dimensione Formato  
IoTJ_________PULP_Frontnet.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 24.22 MB
Formato Adobe PDF
24.22 MB Adobe PDF Visualizza/Apri
Fully_Onboard_AI-Powered_Human-Drone_Pose_Estimation_on_Ultralow-Power_Autonomous_Flying_Nano-UAVs.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 6.19 MB
Formato Adobe PDF
6.19 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/11583/2978558