打造可并行模拟多旋翼机器人的开源框架，支持强化学习导航与真实世界迁移。
Aerial Gym Simulator: A Framework for Highly Parallelized Simulation of Aerial Robots
- 基于NVIDIA Isaac Gym构建模块化并行仿真系统，支持各类多旋翼构型。
- 自研GPU加速渲染，实时输出深度、分割与顶点级标注数据。
- 已验证策略成功从仿真迁移到真实无人机，适合机器人控制与感知研究者。
本文提出Aerial Gym Simulator，一个基于NVIDIA Isaac Gym的高并行化、模块化多旋翼机器人仿真与渲染框架。该框架支持欠驱动、全驱动及过驱动多旋翼平台的仿真，配备并行化的几何控制器，并集成自研的GPU加速射线追踪渲染系统，可生成环境的深度图、分割图和顶点级标注信息。文中提供了多个典型任务示例，如基于深度图的强化学习导航。框架内置工具全面，适用于利用状态信息或外感受器观测进行控制、规划与导航的学习研究。通过大量仿真实验，验证了训练策略的仿真到现实（sim2real）迁移能力。项目已在GitHub开源：https://github.com/ntnu-arl/aerial_gym_simulator。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。