Robustifying the deployment of tinyML models for autonomous mini-vehicles

de Prado, Miguel (School of Engineering – HE-Arc Ingénierie, HES-SO // University of Applied Sciences Western Switzerland ; ETH Zürich, Zürich, Switzerland) ; Rusci, Manuele (University of Bologna, Bologna, Italy) ; Capotondi, Alessandro (University of Modena and Reggio Emilia, Modena, Italy) ; Donze, Romain (School of Engineering – HE-Arc Ingénierie, HES-SO // University of Applied Sciences Western Switzerland) ; Benini, Luca (ETH Zürich, Zürich, Switzerland ; University of Bologna, Bologna, Switzerland) ; Pazos Escudero, Nuria (School of Engineering – HE-Arc Ingénierie, HES-SO // University of Applied Sciences Western Switzerland)

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%.


Keywords:
Article Type:
scientifique
Faculty:
Ingénierie et Architecture
School:
HE-Arc Ingénierie
Institute:
Aucun institut
Date:
2021-02
Pagination:
16 p.
Published in:
Sensors
Numeration (vol. no.):
2021, vol. 21, no. 4
DOI:
ISSN:
1424-8220
Appears in Collection:



 Record created 2021-04-21, last modified 2021-04-23

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)