English

Robustifying the Deployment of tinyML Models for Autonomous mini-vehicles

Computer Vision and Pattern Recognition 2021-06-01 v2 Machine Learning Robotics Systems and Control Signal Processing Systems and Control

Abstract

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%.

Keywords

Cite

@article{arxiv.2007.00302,
  title  = {Robustifying the Deployment of tinyML Models for Autonomous mini-vehicles},
  author = {Miguel de Prado and Manuele Rusci and Romain Donze and Alessandro Capotondi and Serge Monnerat and Luca Benini and and Nuria Pazos},
  journal= {arXiv preprint arXiv:2007.00302},
  year   = {2021}
}
R2 v1 2026-06-23T16:45:41.470Z