用于纳米无人机载精确视觉位姿估计的深度神经网络架构搜索
摘要
微型自主无人 aerial vehicles(UAVs)是一个新兴且热门的话题。它们只有手掌大小,能够到达较大机器人无法到达的地点,并在人类周围安全作业。此类机器人上简单的电子器件(低于100mW)使它们特别廉价且具吸引力,但在实现机载复杂智能方面提出了重大挑战。在这项工作中,我们利用一种新颖的神经架构搜索(NAS)技术,自动为视觉位姿估计任务识别多个帕累托最优卷积神经网络(CNNs)。我们的工作展示了现实中和经现场测试的机器人应用如何具体利用NAS技术,针对小型UAV的特定硬件约束自动且高效地优化CNN。我们部署了多个NAS优化的CNN,并在配备并行超低功耗片上系统的27克Crazyflie纳米无人机上以闭环运行。我们的结果将State-of-the-Art降低了32%的现场控制误差,同时实现了~10Hz@10mW与~50Hz@90mW的实时机载推理速率。
引用
@article{arxiv.2303.01931,
title = {Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs},
author = {Elia Cereda and Luca Crupi and Matteo Risso and Alessio Burrello and Luca Benini and Alessandro Giusti and Daniele Jahier Pagliari and Daniele Palossi},
journal= {arXiv preprint arXiv:2303.01931},
year = {2023}
}
备注
\c{opyright} 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works