Il full-text non è disponibile per scelta dell'autore.
(
Contatta l'autore)
Abstract
Miniaturized flying robotic platforms, called nano-drones, have the potential to revolutionize
the autonomous robots industry sector thanks to their very small form factor.
The nano-drones’ limited payload only allows for a sub-100mW microcontroller unit for
the on-board computations. Therefore, traditional computer vision and control algorithms
are too computationally expensive to be executed on board these palm-sized robots, and
we are forced to rely on artificial intelligence to trade off accuracy in favor of lightweight
pipelines for autonomous tasks.
However, relying on deep learning exposes us to the problem of generalization since the
deployment scenario of a convolutional neural network (CNN) is often composed by different
visual cues and different features from those learned during training, leading to poor inference performances.
Our objective is to develop and deploy and adaptation algorithm, based on the concept
of latent replays, that would allow us to fine-tune a CNN to work in new and diverse
deployment scenarios.
To do so we start from an existing model for visual human pose estimation, called PULPFrontnet,
which is used to identify the pose of a human subject in space through its 4
output variables, and we present the design of our novel adaptation algorithm, which
features automatic data gathering and labeling and on-device deployment.
We therefore showcase the ability of our algorithm to adapt PULP-Frontnet to new deployment
scenarios, improving the R2 scores of the four network outputs, with respect to
an unknown environment, from approximately [−0.2, 0.4, 0.0,−0.7] to [0.25, 0.45, 0.2, 0.1].
Finally we demonstrate how it is possible to fine-tune our neural network in real time
(i.e., under 76 seconds), using the target parallel ultra-low power GAP 8 System-on-Chip
on board the nano-drone, and we show how all adaptation operations can take place using
less than 2mWh of energy, a small fraction of the available battery power.
Abstract
Miniaturized flying robotic platforms, called nano-drones, have the potential to revolutionize
the autonomous robots industry sector thanks to their very small form factor.
The nano-drones’ limited payload only allows for a sub-100mW microcontroller unit for
the on-board computations. Therefore, traditional computer vision and control algorithms
are too computationally expensive to be executed on board these palm-sized robots, and
we are forced to rely on artificial intelligence to trade off accuracy in favor of lightweight
pipelines for autonomous tasks.
However, relying on deep learning exposes us to the problem of generalization since the
deployment scenario of a convolutional neural network (CNN) is often composed by different
visual cues and different features from those learned during training, leading to poor inference performances.
Our objective is to develop and deploy and adaptation algorithm, based on the concept
of latent replays, that would allow us to fine-tune a CNN to work in new and diverse
deployment scenarios.
To do so we start from an existing model for visual human pose estimation, called PULPFrontnet,
which is used to identify the pose of a human subject in space through its 4
output variables, and we present the design of our novel adaptation algorithm, which
features automatic data gathering and labeling and on-device deployment.
We therefore showcase the ability of our algorithm to adapt PULP-Frontnet to new deployment
scenarios, improving the R2 scores of the four network outputs, with respect to
an unknown environment, from approximately [−0.2, 0.4, 0.0,−0.7] to [0.25, 0.45, 0.2, 0.1].
Finally we demonstrate how it is possible to fine-tune our neural network in real time
(i.e., under 76 seconds), using the target parallel ultra-low power GAP 8 System-on-Chip
on board the nano-drone, and we show how all adaptation operations can take place using
less than 2mWh of energy, a small fraction of the available battery power.
Tipologia del documento
Tesi di laurea
(Laurea magistrale)
Autore della tesi
Borgatti, Bruno
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Ordinamento Cds
DM270
Parole chiave
nano-drones,continual learning,artificial intelligence,neural network,convolutional neural network,parallel ultra low power,UAV,PULP,system on chip,embedded system
Data di discussione della Tesi
2 Febbraio 2023
URI
Altri metadati
Tipologia del documento
Tesi di laurea
(NON SPECIFICATO)
Autore della tesi
Borgatti, Bruno
Relatore della tesi
Correlatore della tesi
Scuola
Corso di studio
Ordinamento Cds
DM270
Parole chiave
nano-drones,continual learning,artificial intelligence,neural network,convolutional neural network,parallel ultra low power,UAV,PULP,system on chip,embedded system
Data di discussione della Tesi
2 Febbraio 2023
URI
Gestione del documento: