Robustifying the deployment of tinyML models for autonomous mini-vehicles

You are here: Homepage > Search

Robustifying the deployment of tinyML models for autonomous mini-vehicles

Free access

de Prado M. / Rusci M. / Donze R. / Capotondi A. / Monnerat S. / Benini L. / Pazos N.

Standard-size autonomous navigation vehicles have rapidly improved thanks to the breakthroughs of deep learning. However, scaling autonomous driving to low-power systems deployed on dynamic environments poses several challenges that prevent their adoption. To address them, we propose a closed-loop learning flow for autonomous driving mini-vehicles that includes the target environment in-the-loop. We leverage a family of compact and high-throughput tinyCNNs to control the mini-vehicle, which learn in the target environment by imitating a computer vision algorithm, i.e., the expert. Thus, the tinyCNNs, having only access to an on-board fast-rate linear camera, gain robustness to lighting conditions and improve over time. Further, we leverage GAP8, a parallel ultra-low-power RISC-V SoC, to meet the inference requirements. When running the family of CNNs, our GAP8's solution outperforms any other implementation on the STM32L4 and NXP k64f (Cortex-M4), reducing the latency by over 13x and the energy consummation by 92%.

Access

Download

Export, share and cite

Document information

Title :

Robustifying the deployment of tinyML models for autonomous mini-vehicles

Contributors:

de Prado M. (author) / Rusci M. (author) / Donze R. (author) / Capotondi A. (author) / Monnerat S. (author) / Benini L. (author) / Pazos N. (author) / de Prado, M. / Rusci, M. / Donze, R.

Publication date :

2021-01-01

DOI :

https://doi.org/10.1109/ISCAS51556.2021.9401154

Type of media :

Conference paper

Type of material :

Electronic Resource

Language :

English

Keywords :

Autonomous driving , Robustness , and Micro-controller , TinyML