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%.
Robustifying the deployment of tinyML models for autonomous mini-vehicles / de Prado M.; Rusci M.; Donze R.; Capotondi A.; Monnerat S.; Benini L.; Pazos N.. - ELETTRONICO. - 2021-:(2021), pp. 9401154.1-9401154.5. (Intervento presentato al convegno 53rd IEEE International Symposium on Circuits and Systems, ISCAS 2021 tenutosi a CONFlux and Hotel Inter-Burgo Daegu, kor nel 2021) [10.1109/ISCAS51556.2021.9401154].
Robustifying the deployment of tinyML models for autonomous mini-vehicles
Rusci M.;Capotondi A.;Benini L.;
2021
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%.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
