基于机载全卷积网络的高通量视觉纳米无人机间相对定位
High-throughput Visual Nano-drone to Nano-drone Relative Localization using Onboard Fully Convolutional Networks
AI总结：
本研究针对资源受限的纳米无人机，提出基于视觉的全卷积神经网络垂直集成系统，仅靠机载低功耗硬件实现高精度相对定位，在精度和续航上均优于现有最先进方案。
摘要：
无人机间相对定位是所有集群作业的基础组成模块。我们针对直径10厘米的微型纳米无人机场景开展该任务研究——这类无人机因小巧外形带来的全新用例而受到越来越多的关注。其多功能性的代价是机载资源（传感器、处理单元和内存）有限，这限制了机载算法的复杂度。克服这些限制的传统方案是直接部署在纳米无人机上的轻量级深度学习模型。本研究仅使用灰度低分辨率相机和机载搭载的超低功耗片上系统（SoC），解决纳米无人机之间具有挑战性的相对位姿估计问题。我们提出了一种垂直集成系统，该系统基于新型的基于视觉的全卷积神经网络（FCNN），在搭载GWT GAP8 SoC扩展的Crazyflie纳米无人机上，该网络以39Hz的频率运行，功耗为101mW。我们将所提出的FCNN与三种最先进（SoA）系统进行了对比。在包含3万张图像的真实数据集上，相较于性能最优的现有SoA方法，我们的模型在水平图像坐标上的决定系数（R-squared）从32%提升至47%，在垂直图像坐标上从18%提升至55%。最后，我们的实地测试表明，与此前的SoA研究相比，平均跟踪误差降低了37%，且续航性能可达整段电池寿命的4分钟。
英文摘要：
Relative drone-to-drone localization is a fundamental building block for any swarm operations. We address this task in the context of miniaturized nano-drones, i.e., 10cm in diameter, which show an ever-growing interest due to novel use cases enabled by their reduced form factor. The price for their versatility comes with limited onboard resources, i.e., sensors, processing units, and memory, which limits the complexity of the onboard algorithms. A traditional solution to overcome these limitations is represented by lightweight deep learning models directly deployed aboard nano-drones. This work tackles the challenging relative pose estimation between nano-drones using only a gray-scale low-resolution camera and an ultra-low-power System-on-Chip (SoC) hosted onboard. We present a vertically integrated system based on a novel vision-based fully convolutional neural network (FCNN), which runs at 39Hz within 101mW onboard a Crazyflie nano-drone extended with the GWT GAP8 SoC. We compare our FCNN against three State-of-the-Art (SoA) systems. Considering the best-performing SoA approach, our model results in an R-squared improvement from 32 to 47% on the horizontal image coordinate and from 18 to 55% on the vertical image coordinate, on a real-world dataset of 30k images. Finally, our in-field tests show a reduction of the average tracking error of 37% compared to a previous SoA work and an endurance performance up to the entire battery lifetime of 4 minutes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
