Autonomous navigation vehicles have rapidly improved thanks to the breakthroughs of Deep Learning. However, scaling autonomous driving to low-power and real-time systems deployed on dynamic environments poses several challenges that prevent their adoption. In this work, we show an end-to-end integration of data, algorithms, and deployment tools that enables the deployment of a family of tiny-CNNs on extra-low-power MCUs for autonomous driving mini-vehicles (image classification task). Our end-to-end environment enables a closed-loop learning system that allows the CNNs (learners) to learn through demonstration by imitating the original computer-vision algorithm (teacher) while doubling the throughput. Thereby, our CNNs gain robustness to lighting conditions and increase their accuracy up to 20% when deployed in the most challenging setup with a very fast-rate camera. Further, we leverage GAP8, a parallel ultra-low-power RISC-V SoC, to meet the real-time requirements. When running a family of CNN for an image classification task, GAP8 reduces their latency by over 20x compared to using an STM32L4 (Cortex-M4) or obtains +21.4% accuracy than an NXP k64f (Cortex-M4) solution with the same energy budget.

中文翻译：

---

使用 tinyML 实现自主微型车辆的稳健导航

由于深度学习的突破，自主导航车辆得到了迅速的改进。然而，将自动驾驶扩展到部署在动态环境中的低功耗和实时系统会带来一些阻碍其采用的挑战。在这项工作中，我们展示了数据、算法和部署工具的端到端集成，能够在用于自动驾驶微型车辆的超低功耗 MCU 上部署一系列微型 CNN（图像分类任务） . 我们的端到端环境实现了一个闭环学习系统，该系统允许 CNN（学习者）通过模仿原始计算机视觉算法（教师）的演示进行学习，同时将吞吐量加倍。从而，我们的 CNN 对光照条件具有鲁棒性，并且在使用速度非常快的相机部署在最具挑战性的设置中时，其准确度可提高 20%。此外，我们利用并行超低功耗 RISC-V SoC GAP8 来满足实时要求。在为图像分类任务运行一系列 CNN 时，与使用 STM32L4 (Cortex-M4) 相比，GAP8 将其延迟减少了 20 倍以上，或者在相同能量预算下获得了比 NXP k64f (Cortex-M4) 解决方案 +21.4% 的准确度.