Visual-Inertial Navigation Algorithm Development Using Photorealistic Camera Simulation in the Loop
Visual-Inertial Navigation Algorithm Development Using Photorealistic Camera Simulation in the Loop
复制标题
使用环路逼真相机模拟进行视觉惯性导航算法开发
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
S. Karaman
中科院分区：
文献类型：
--
作者：
Thomas Sayre;Winter Guerra;Amado Antonini;Jasper Arneberg;A. Brown;G. V. Cavalheiro;Yajun Fang;A. Gorodetsky;Dave McCoy;Sebastian Quilter;Fabian Riether;E. Tal;Yunus Terzioglu;L. Carlone;S. Karaman
快速、敏捷的微型无人机（UAV）的发展受到以下因素的限制：（i）机载计算硬件的限制；（ii）缺乏先进的基于视觉的感知以及视觉在环控制算法；（iii）缺乏能够快速、轻松地设计、实施和验证此类系统及算法的开发环境。在此，我们首先介绍一种新的微型无人机平台，它集成了高速摄像机、惯性传感器以及拥有256个GPU核心的英伟达Jetson Tegra X1片上系统计算模块。无人机的机械结构和电子设备是我们自行设计和制造的，并将进行详细描述。其次，我们提出一种新颖的“虚拟现实”开发环境，在无人机飞行过程中，该环境能够实时生成逼真渲染的合成机载摄像机图像。这种开发环境使我们能够利用真实的物理原理、真实的内感受传感器数据（例如来自机载惯性测量单元的数据）以及合成的外感受传感器数据（例如来自合成摄像机的数据），快速对计算和传感硬件以及感知和控制算法进行原型设计。第三，我们展示了利用在此环境中开发的基于视觉的闭环感知和控制算法进行的反复敏捷机动操作。
The development of fast, agile micro Unmanned Aerial Vehicles (UAVs) has been limited by (i) on-board computing hardware restrictions, (ii) the lack of sophisticated vision-based perception and vision-in-the-loop control algorithms, and (iii) the absence of development environments where such systems and algorithms can be rapidly and easily designed, implemented, and validated. Here, we first present a new micro UAV platform that integrates high-rate cameras, inertial sensors, and an NVIDIA Jetson Tegra X1 system-on-chip compute module that boasts 256 GPU cores. The UAV mechanics and electronics were designed and built in house, and are described in detail. Second, we present a novel “virtual reality” development environment, in which photorealistically-rendered synthetic on-board camera images are generated in real time while the UAV is in flight. This development environment allows us to rapidly prototype computing and sensing hardware as well as perception and control algorithms, using real physics, real interoceptive sensor data (e.g., from the on-board inertial measurement unit), and synthetic exteroceptive sensor data (e.g., from synthetic cameras). Third, we demonstrate repeated agile maneuvering with closed-loop vision-based perception and control algorithms, which we have developed using this environment.