Show simple item record

dc.contributor.author
de Prado, Miguel
dc.contributor.author
Rusci, Manuele
dc.contributor.author
Capotondi, Alessandro
dc.contributor.author
Donze, Romain
dc.contributor.author
Benini, Luca
dc.contributor.author
Pazos, Nuria
dc.date.accessioned
2021-02-25T10:56:59Z
dc.date.available
2021-02-24T09:50:35Z
dc.date.available
2021-02-25T10:55:41Z
dc.date.available
2021-02-25T10:56:59Z
dc.date.issued
2021-02
dc.identifier.other
10.3390/s21041339
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/471291
dc.identifier.doi
10.3929/ethz-b-000471291
dc.description.abstract
Standard-sized autonomous vehicles have rapidly improved thanks to the breakthroughs of deep learning. However, scaling autonomous driving to mini-vehicles poses several challenges due to their limited on-board storage and computing capabilities. Moreover, autonomous systems lack robustness when deployed in dynamic environments where the underlying distribution is different from the distribution learned during training. To address these challenges, we propose a closed-loop learning flow for autonomous driving mini-vehicles that includes the target deployment environment in-the-loop. We leverage a family of compact and high-throughput tinyCNNs to control the mini-vehicle that learn by imitating a computer vision algorithm, i.e., the expert, in the target environment. Thus, the tinyCNNs, having only access to an on-board fast-rate linear camera, gain robustness to lighting conditions and improve over time. Moreover, we introduce an online predictor that can choose between different tinyCNN models at runtime—trading accuracy and latency—which minimises the inference’s energy consumption by up to 3.2×. Finally, we leverage GAP8, a parallel ultra-low-power RISC-V-based micro-controller unit (MCU), to meet the real-time inference requirements. When running the family of tinyCNNs, our solution running on GAP8 outperforms any other implementation on the STM32L4 and NXP k64f (traditional single-core MCUs), reducing the latency by over 13× and the energy consumption by 92%.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
MDPI
en_US
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
dc.subject
autonomous driving
en_US
dc.subject
tinyML
en_US
dc.subject
robustness
en_US
dc.subject
micro-controllers
en_US
dc.title
Robustifying the Deployment of tinyML Models for Autonomous Mini-Vehicles
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution 4.0 International
dc.date.published
2021-02-13
ethz.journal.title
Sensors
ethz.journal.volume
21
en_US
ethz.journal.issue
4
en_US
ethz.pages.start
1339
en_US
ethz.size
16 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Basel
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02636 - Institut für Integrierte Systeme / Integrated Systems Laboratory::03996 - Benini, Luca / Benini, Luca
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02636 - Institut für Integrierte Systeme / Integrated Systems Laboratory::03996 - Benini, Luca / Benini, Luca
ethz.date.deposited
2021-02-24T09:50:54Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2021-02-25T10:55:52Z
ethz.rosetta.lastUpdated
2022-03-29T05:27:36Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Robustifying%20the%20Deployment%20of%20tinyML%20Models%20for%20Autonomous%20Mini-Vehicles&rft.jtitle=Sensors&rft.date=2021-02&rft.volume=21&rft.issue=4&rft.spage=1339&rft.au=de%20Prado,%20Miguel&Rusci,%20Manuele&Capotondi,%20Alessandro&Donze,%20Romain&Benini,%20Luca&rft.genre=article&rft_id=info:doi/10.3390/s21041339&
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record