论文标题
Flightmare：灵活的四型模拟器
Flightmare: A Flexible Quadrotor Simulator
论文作者
论文摘要
最先进的四极管模拟器具有刚性且高度特殊的结构：它们要么非常快，身体准确，要么是真实的。在这项工作中，我们提出了一个新颖的四型模拟器：FlightMare。 FlightMare由两个主要组成部分组成：一个基于Unity的可配置渲染引擎和用于动力学模拟的灵活的物理引擎。这两个组件完全分离，可以彼此独立运行。这使我们的模拟器非常快：渲染可实现高达230 Hz的速度，而物理模拟在笔记本电脑上的仿真速度最高为200,000 Hz。此外，Flighmare还具有几个理想的功能：（i）一个大型多模式传感器套件，包括一个界面来提取场景的3D点云； （ii）一种用于增强学习的API，可以并行模拟数百个四肢； （iii）与虚拟现实耳机的集成，以与模拟环境相互作用。我们通过将其用于两个不同的机器人任务来证明飞行模具的灵活性：使用深度强化学习和在复杂的3D环境中使用无碰撞的路径计划的四摩托控制。
State-of-the-art quadrotor simulators have a rigid and highly-specialized structure: either are they really fast, physically accurate, or photo-realistic. In this work, we propose a novel quadrotor simulator: Flightmare. Flightmare is composed of two main components: a configurable rendering engine built on Unity and a flexible physics engine for dynamics simulation. Those two components are totally decoupled and can run independently of each other. This makes our simulator extremely fast: rendering achieves speeds of up to 230 Hz, while physics simulation of up to 200,000 Hz on a laptop. In addition, Flightmare comes with several desirable features: (i) a large multi-modal sensor suite, including an interface to extract the 3D point-cloud of the scene; (ii) an API for reinforcement learning which can simulate hundreds of quadrotors in parallel; and (iii) integration with a virtual-reality headset for interaction with the simulated environment. We demonstrate the flexibility of Flightmare by using it for two different robotic tasks: quadrotor control using deep reinforcement learning and collision-free path planning in a complex 3D environment.
