Aerial Gym Simulator：一种用于空中机器人高度并行化仿真的框架
Aerial Gym Simulator: A Framework for Highly Parallelized Simulation of Aerial Robots
AI总结：
本文提出基于NVIDIA Isaac Gym的高度并行化、模块化仿真框架Aerial Gym Simulator，支持多种驱动类型多旋翼仿真与GPU加速渲染，提供强化学习导航等任务示例，并验证了训练策略的sim2real迁移效果。
摘要：
本文提出了Aerial Gym Simulator，这是一种基于NVIDIA Isaac Gym的高度并行化、模块化框架，用于任意多旋翼平台的仿真与渲染。Aerial Gym支持欠驱动、全驱动和过驱动多旋翼的仿真，提供并行化几何控制器，并配有定制的GPU加速渲染框架，可通过光线投射从环境中捕获深度、分割和顶点级标注。该框架提供了多个关键任务示例，如基于深度信息的强化学习导航。框架内开发的综合工具集使其成为利用状态信息和外部传感器观测进行控制、规划和导航学习研究的强大资源。研究进行了广泛的仿真实验，并展示了训练策略的成功sim2real迁移。Aerial Gym Simulator已在以下网址开源：https://github.com/ntnu-arl/aerial_gym_simulator。
英文摘要：
This paper contributes the Aerial Gym Simulator, a highly parallelized, modular framework for simulation and rendering of arbitrary multirotor platforms based on NVIDIA Isaac Gym. Aerial Gym supports the simulation of under-, fully- and over-actuated multirotors offering parallelized geometric controllers, alongside a custom GPU-accelerated rendering framework for ray-casting capable of capturing depth, segmentation and vertex-level annotations from the environment. Multiple examples for key tasks, such as depth-based navigation through reinforcement learning are provided. The comprehensive set of tools developed within the framework makes it a powerful resource for research on learning for control, planning, and navigation using state information as well as exteroceptive sensor observations. Extensive simulation studies are conducted and successful sim2real transfer of trained policies is demonstrated. The Aerial Gym Simulator is open-sourced at: https://github.com/ntnu-arl/aerial_gym_simulator.
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。
