[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-microsoft--AirSim":3,"tool-microsoft--AirSim":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",152630,2,"2026-04-12T23:33:54",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",108322,"2026-04-10T11:39:34",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":67,"readme_en":68,"readme_zh":69,"quickstart_zh":70,"use_case_zh":71,"hero_image_url":72,"owner_login":73,"owner_name":74,"owner_avatar_url":75,"owner_bio":76,"owner_company":77,"owner_location":77,"owner_email":78,"owner_twitter":79,"owner_website":80,"owner_url":81,"languages":82,"stars":122,"forks":123,"last_commit_at":124,"license":125,"difficulty_score":126,"env_os":127,"env_gpu":128,"env_ram":129,"env_deps":130,"category_tags":138,"github_topics":140,"view_count":32,"oss_zip_url":77,"oss_zip_packed_at":77,"status":17,"created_at":158,"updated_at":159,"faqs":160,"releases":186},7026,"microsoft\u002FAirSim","AirSim","Open source simulator for autonomous vehicles built on Unreal Engine \u002F Unity, from Microsoft AI & Research","AirSim 是由微软研发的一款开源模拟器，专为无人机、汽车等自动驾驶载具打造。它基于虚幻引擎（Unreal Engine）构建，并提供实验性的 Unity 版本，旨在为人工智能研究提供一个高保真、跨平台的虚拟测试环境。\n\n在自动驾驶技术落地前，实地测试往往面临高昂成本与安全风险。AirSim 通过生成物理和视觉上都极度逼真的场景，有效解决了这一痛点。它支持“软件在环”与“硬件在环”仿真，能够无缝对接 PX4、ArduPilot 等主流飞控系统，让算法在虚拟世界中即可得到充分验证，大幅降低了研发门槛与试错成本。\n\n这款工具特别适合 AI 研究人员、算法开发者以及自动驾驶领域的工程师使用。无论是探索深度学习、计算机视觉，还是训练强化学习模型，AirSim 都能提供丰富的数据接口，让用户以平台无关的方式灵活控制车辆并获取传感器数据。\n\n值得注意的是，微软已宣布将推出升级版\"Project AirSim\"以满足航空航天业日益增长的需求，原版仓库虽将逐步归档停止更新，但其代码依然开放可用，继续作为社区宝贵的学习与实验资源存在。对于希望低成本入门自动驾驶仿真或验证新想法的创作者而言，AirSim","AirSim 是由微软研发的一款开源模拟器，专为无人机、汽车等自动驾驶载具打造。它基于虚幻引擎（Unreal Engine）构建，并提供实验性的 Unity 版本，旨在为人工智能研究提供一个高保真、跨平台的虚拟测试环境。\n\n在自动驾驶技术落地前，实地测试往往面临高昂成本与安全风险。AirSim 通过生成物理和视觉上都极度逼真的场景，有效解决了这一痛点。它支持“软件在环”与“硬件在环”仿真，能够无缝对接 PX4、ArduPilot 等主流飞控系统，让算法在虚拟世界中即可得到充分验证，大幅降低了研发门槛与试错成本。\n\n这款工具特别适合 AI 研究人员、算法开发者以及自动驾驶领域的工程师使用。无论是探索深度学习、计算机视觉，还是训练强化学习模型，AirSim 都能提供丰富的数据接口，让用户以平台无关的方式灵活控制车辆并获取传感器数据。\n\n值得注意的是，微软已宣布将推出升级版\"Project AirSim\"以满足航空航天业日益增长的需求，原版仓库虽将逐步归档停止更新，但其代码依然开放可用，继续作为社区宝贵的学习与实验资源存在。对于希望低成本入门自动驾驶仿真或验证新想法的创作者而言，AirSim 依然是一个功能强大且友好的起点。","## Project AirSim announcement\r\n\r\nMicrosoft and IAMAI collaborated to advance high-fidelity autonomy simulations through Project AirSim—the evolution of AirSim— released under the MIT license as part of a DARPA-supported initiative.  IAMAI is proud to have contributed to these efforts and has published its version of the Project AirSim repository at [github.com\u002Fiamaisim\u002FProjectAirSim](https:\u002F\u002Fgithub.com\u002Fiamaisim\u002FProjectAirSim).\r\n\r\n## AirSim announcement: This repository will be archived in the coming year \r\n\r\nIn 2017 Microsoft Research created AirSim as a simulation platform for AI research and experimentation. Over the span of five years, this research project has served its purpose—and gained a lot of ground—as a common way to share research code and test new ideas around aerial AI development and simulation. Additionally, time has yielded advancements in the way we apply technology to the real world, particularly through aerial mobility and autonomous systems. For example, drone delivery is no longer a sci-fi storyline—it’s a business reality, which means there are new needs to be met. We’ve learned a lot in the process, and we want to thank this community for your engagement along the way. \r\n\r\nIn the spirit of forward momentum, we will be releasing a new simulation platform in the coming year and subsequently archiving the original 2017 AirSim. Users will still have access to the original AirSim code beyond that point, but no further updates will be made, effective immediately. Instead, we will focus our efforts on a new product, Microsoft Project AirSim, to meet the growing needs of the aerospace industry. Project AirSim will provide an end-to-end platform for safely developing and testing aerial autonomy through simulation. Users will benefit from the safety, code review, testing, advanced simulation, and AI capabilities that are uniquely available in a commercial product. As we get closer to the release of Project AirSim, there will be learning tools and features available to help you migrate to the new platform and to guide you through the product. To learn more about building aerial autonomy with the new Project AirSim, visit [https:\u002F\u002Faka.ms\u002Fprojectairsim](https:\u002F\u002Faka.ms\u002Fprojectairsim).\r\n\r\n# Welcome to AirSim\r\n\r\nAirSim is a simulator for drones, cars and more, built on [Unreal Engine](https:\u002F\u002Fwww.unrealengine.com\u002F) (we now also have an experimental [Unity](https:\u002F\u002Funity3d.com\u002F) release). It is open-source, cross platform, and supports software-in-the-loop simulation with popular flight controllers such as PX4 & ArduPilot and hardware-in-loop with PX4 for physically and visually realistic simulations. It is developed as an Unreal plugin that can simply be dropped into any Unreal environment. Similarly, we have an experimental release for a Unity plugin.\r\n\r\nOur goal is to develop AirSim as a platform for AI research to experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles. For this purpose, AirSim also exposes APIs to retrieve data and control vehicles in a platform independent way.\r\n\r\n**Check out the quick 1.5 minute demo**\r\n\r\nDrones in AirSim\r\n\r\n[![AirSim Drone Demo Video](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_bcd774ebf0eb.png)](https:\u002F\u002Fyoutu.be\u002F-WfTr1-OBGQ)\r\n\r\nCars in AirSim\r\n\r\n[![AirSim Car Demo Video](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_d0c91bb3be6c.png)](https:\u002F\u002Fyoutu.be\u002Fgnz1X3UNM5Y)\r\n\r\n\r\n## How to Get It\r\n\r\n### Windows\r\n[![Build Status](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_windows.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_windows.yml)\r\n* [Download binaries](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FAirSim\u002Freleases)\r\n* [Build it](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fbuild_windows)\r\n\r\n### Linux\r\n[![Build Status](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_ubuntu.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_ubuntu.yml)\r\n* [Download binaries](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FAirSim\u002Freleases)\r\n* [Build it](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fbuild_linux)\r\n\r\n### macOS\r\n[![Build Status](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_macos.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_macos.yml)\r\n* [Build it](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fbuild_macos)\r\n\r\nFor more details, see the [use precompiled binaries](docs\u002Fuse_precompiled.md) document. \r\n\r\n## How to Use It\r\n\r\n### Documentation\r\n\r\nView our [detailed documentation](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002F) on all aspects of AirSim.\r\n\r\n### Manual drive\r\n\r\nIf you have remote control (RC) as shown below, you can manually control the drone in the simulator. For cars, you can use arrow keys to drive manually.\r\n\r\n[More details](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fremote_control)\r\n\r\n![record screenshot](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_07fc1a889ca2.gif)\r\n\r\n![record screenshot](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_771d355cea5e.gif)\r\n\r\n\r\n### Programmatic control\r\n\r\nAirSim exposes APIs so you can interact with the vehicle in the simulation programmatically. You can use these APIs to retrieve images, get state, control the vehicle and so on. The APIs are exposed through the RPC, and are accessible via a variety of languages, including C++, Python, C# and Java.\r\n\r\nThese APIs are also available as part of a separate, independent cross-platform library, so you can deploy them on a companion computer on your vehicle. This way you can write and test your code in the simulator, and later execute it on the real vehicles. Transfer learning and related research is one of our focus areas.\r\n\r\nNote that you can use [SimMode setting](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fsettings#simmode) to specify the default vehicle or the new [ComputerVision mode](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fimage_apis#computer-vision-mode-1) so you don't get prompted each time you start AirSim.\r\n\r\n[More details](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fapis)\r\n\r\n### Gathering training data\r\n\r\nThere are two ways you can generate training data from AirSim for deep learning. The easiest way is to simply press the record button in the lower right corner. This will start writing pose and images for each frame. The data logging code is pretty simple and you can modify it to your heart's content.\r\n\r\n![record screenshot](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_eec3f706a62f.png)\r\n\r\nA better way to generate training data exactly the way you want is by accessing the APIs. This allows you to be in full control of how, what, where and when you want to log data.\r\n\r\n### Computer Vision mode\r\n\r\nYet another way to use AirSim is the so-called \"Computer Vision\" mode. In this mode, you don't have vehicles or physics. You can use the keyboard to move around the scene, or use APIs to position available cameras in any arbitrary pose, and collect images such as depth, disparity, surface normals or object segmentation.\r\n\r\n[More details](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fimage_apis)\r\n\r\n### Weather Effects\r\n\r\nPress F10 to see various options available for weather effects. You can also control the weather using [APIs](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fapis#weather-apis). Press F1 to see other options available.\r\n\r\n![record screenshot](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_05d2c57f9f39.png)\r\n\r\n## Tutorials\r\n\r\n- [Video - Setting up AirSim with Pixhawk Tutorial](https:\u002F\u002Fyoutu.be\u002F1oY8Qu5maQQ) by Chris Lovett\r\n- [Video - Using AirSim with Pixhawk Tutorial](https:\u002F\u002Fyoutu.be\u002FHNWdYrtw3f0) by Chris Lovett\r\n- [Video - Using off-the-self environments with AirSim](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=y09VbdQWvQY) by Jim Piavis\r\n- [Webinar - Harnessing high-fidelity simulation for autonomous systems](https:\u002F\u002Fnote.microsoft.com\u002FMSR-Webinar-AirSim-Registration-On-Demand.html) by Sai Vemprala\r\n- [Reinforcement Learning with AirSim](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Freinforcement_learning) by Ashish Kapoor\r\n- [The Autonomous Driving Cookbook](https:\u002F\u002Faka.ms\u002FAutonomousDrivingCookbook) by Microsoft Deep Learning and Robotics Garage Chapter\r\n- [Using TensorFlow for simple collision avoidance](https:\u002F\u002Fgithub.com\u002Fsimondlevy\u002FAirSimTensorFlow) by Simon Levy and WLU team\r\n\r\n## Participate\r\n\r\n### Paper\r\n\r\nMore technical details are available in [AirSim paper (FSR 2017 Conference)](https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.05065). Please cite this as:\r\n```\r\n@inproceedings{airsim2017fsr,\r\n  author = {Shital Shah and Debadeepta Dey and Chris Lovett and Ashish Kapoor},\r\n  title = {AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles},\r\n  year = {2017},\r\n  booktitle = {Field and Service Robotics},\r\n  eprint = {arXiv:1705.05065},\r\n  url = {https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.05065}\r\n}\r\n```\r\n\r\n### Contribute\r\n\r\nPlease take a look at [open issues](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fairsim\u002Fissues) if you are looking for areas to contribute to.\r\n\r\n* [More on AirSim design](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fdesign)\r\n* [More on code structure](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fcode_structure)\r\n* [Contribution Guidelines](CONTRIBUTING.md)\r\n\r\n### Who is Using AirSim?\r\n\r\nWe are maintaining a [list](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fwho_is_using) of a few projects, people and groups that we are aware of. If you would like to be featured in this list please [make a request here](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fairsim\u002Fissues).\r\n\r\n## Contact\r\n\r\nJoin our [GitHub Discussions group](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fdiscussions) to stay up to date or ask any questions.\r\n\r\nWe also have an AirSim group on [Facebook](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002F1225832467530667\u002F). \r\n\r\n\r\n## What's New\r\n\r\n* [Cinematographic Camera](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3949)\r\n* [ROS2 wrapper](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3976)\r\n* [API to list all assets](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3940)\r\n* [movetoGPS API](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3746)\r\n* [Optical flow camera](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3938)\r\n* [simSetKinematics API](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F4066)\r\n* [Dynamically set object textures from existing UE material or texture PNG](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3992)\r\n* [Ability to spawn\u002Fdestroy lights and control light parameters](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3991)\r\n* [Support for multiple drones in Unity](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3128)\r\n* [Control manual camera speed through the keyboard](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpulls?page=6&q=is%3Apr+is%3Aclosed+sort%3Aupdated-desc#:~:text=1-,Control%20manual%20camera%20speed%20through%20the%20keyboard,-%233221%20by%20saihv) \r\n\r\nFor complete list of changes, view our [Changelog](docs\u002FCHANGELOG.md)\r\n\r\n## FAQ\r\n\r\nIf you run into problems, check the [FAQ](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Ffaq) and feel free to post issues in the  [AirSim](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FAirSim\u002Fissues) repository.\r\n\r\n## Code of Conduct\r\n\r\nThis project has adopted the [Microsoft Open Source Code of Conduct](https:\u002F\u002Fopensource.microsoft.com\u002Fcodeofconduct\u002F). For more information see the [Code of Conduct FAQ](https:\u002F\u002Fopensource.microsoft.com\u002Fcodeofconduct\u002Ffaq\u002F) or contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.\r\n\r\n\r\n## License\r\n\r\nThis project is released under the MIT License. Please review the [License file](LICENSE) for more details.\r\n\r\n\r\n","## Project AirSim 公告\n\n微软与 IAMAI 携手合作，通过 Project AirSim——AirSim 的演进版本——推进高保真度的自主系统仿真。该项目以 MIT 许可证发布，是 DARPA 支持的一项计划的一部分。IAMAI 为能参与这一努力深感自豪，并已在 [github.com\u002Fiamaisim\u002FProjectAirSim](https:\u002F\u002Fgithub.com\u002Fiamaisim\u002FProjectAirSim) 上发布了其版本的 Project AirSim 代码库。\n\n## AirSim 公告：本仓库将于明年归档\n\n2017 年，微软研究院创建了 AirSim，作为人工智能研究与实验的仿真平台。在过去的五年里，这一研究项目已完成了其使命，并取得了显著进展，成为分享研究代码、测试空中 AI 开发与仿真相关新想法的常用方式。此外，随着时间推移，我们在将技术应用于现实世界方面也取得了长足进步，尤其是在空中出行和自主系统领域。例如，无人机配送已不再是科幻情节，而是切实可行的商业实践，这也意味着出现了新的需求亟待满足。在此过程中，我们学到了许多宝贵的经验，也衷心感谢社区伙伴们一路以来的积极参与。\n\n本着不断向前的精神，我们将在明年推出全新的仿真平台，并随后归档最初的 2017 年版 AirSim。此后，用户仍可访问原始的 AirSim 代码，但自即日起将不再进行任何更新。取而代之的是，我们将把精力集中在新产品 Microsoft Project AirSim 上，以满足航空航天行业日益增长的需求。Project AirSim 将提供一个端到端的平台，用于通过仿真安全地开发和测试空中自主系统。用户将受益于商业产品所独有的安全性、代码审查、测试、高级仿真以及人工智能功能。随着 Project AirSim 的发布日益临近，我们将推出一系列学习工具和功能，帮助您迁移到新平台，并为您提供使用指导。如需了解更多关于如何利用全新 Project AirSim 构建空中自主系统的信息，请访问 [https:\u002F\u002Faka.ms\u002Fprojectairsim](https:\u002F\u002Faka.ms\u002Fprojectairsim)。\n\n# 欢迎来到 AirSim\n\nAirSim 是一款基于 [Unreal Engine](https:\u002F\u002Fwww.unrealengine.com\u002F) 构建的无人机、汽车等模拟器（我们现在也有实验性的 [Unity](https:\u002F\u002Funity3d.com\u002F) 版本）。它采用开源、跨平台设计，支持与 PX4 和 ArduPilot 等主流飞行控制器结合的软件在环仿真，以及与 PX4 结合的硬件在环仿真，从而实现物理和视觉上高度逼真的模拟效果。AirSim 是一个 Unreal 插件，可轻松集成到任何 Unreal 环境中。同样地，我们也提供了 Unity 插件的实验性版本。\n\n我们的目标是将 AirSim 打造为一个人工智能研究平台，用于试验深度学习、计算机视觉和强化学习算法在自动驾驶车辆中的应用。为此，AirSim 还提供了独立于平台的 API，用于获取数据和控制车辆。\n\n**请观看这段 1 分 30 秒的快速演示**\n\nAirSim 中的无人机\n\n[![AirSim 无人机演示视频](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_bcd774ebf0eb.png)](https:\u002F\u002Fyoutu.be\u002F-WfTr1-OBGQ)\n\nAirSim 中的汽车\n\n[![AirSim 汽车演示视频](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_d0c91bb3be6c.png)](https:\u002F\u002Fyoutu.be\u002Fgnz1X3UNM5Y)\n\n\n## 如何获取\n\n### Windows\n[![构建状态](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_windows.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_windows.yml)\n* [下载二进制文件](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FAirSim\u002Freleases)\n* [自行编译](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fbuild_windows)\n\n### Linux\n[![构建状态](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_ubuntu.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_ubuntu.yml)\n* [下载二进制文件](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FAirSim\u002Freleases)\n* [自行编译](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fbuild_linux)\n\n### macOS\n[![构建状态](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_macos.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Factions\u002Fworkflows\u002Ftest_macos.yml)\n* [自行编译](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fbuild_macos)\n\n更多详细信息，请参阅 [使用预编译二进制文件](docs\u002Fuse_precompiled.md) 文档。\n\n## 如何使用\n\n### 文档\n\n请查阅我们的 [详细文档](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002F)，了解 AirSim 的各个方面。\n\n### 手动驾驶\n\n如果您拥有如下所示的遥控设备，便可在模拟器中手动控制无人机。对于汽车，则可以使用方向键进行手动驾驶。\n\n[更多信息](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fremote_control)\n\n![记录截图](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_07fc1a889ca2.gif)\n\n![记录截图](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_771d355cea5e.gif)\n\n\n### 编程控制\n\nAirSim 提供了 API，使您可以以编程方式与模拟中的车辆交互。您可以使用这些 API 来获取图像、状态信息、控制车辆等。这些 API 通过 RPC 暴露，并支持多种语言，包括 C++、Python、C# 和 Java。\n\n这些 API 也可作为独立的跨平台库使用，因此您可以将其部署在车辆上的配套计算机上。这样，您就可以先在模拟器中编写和测试代码，然后再将其部署到真实车辆上运行。迁移学习及相关研究是我们关注的重点之一。\n\n请注意，您可以使用 [SimMode 设置](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fsettings#simmode) 来指定默认车辆，或启用新的 [ComputerVision 模式](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fimage_apis#computer-vision-mode-1)，以便在每次启动 AirSim 时无需重复选择。\n\n[更多信息](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fapis)\n\n### 收集训练数据\n\n您可以通过两种方式从 AirSim 中生成用于深度学习的训练数据。最简单的方法是直接点击右下角的录制按钮。这将开始记录每一帧的姿态和图像。数据记录代码非常简单，您可以根据需要随意修改。\n\n![记录截图](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_eec3f706a62f.png)\n\n另一种更精确地按您的需求生成训练数据的方式是直接调用 API。这种方式可以让您完全掌控数据记录的时间、内容、位置和方式。\n\n### 计算机视觉模式\n\n使用 AirSim 的另一种方式是所谓的“计算机视觉”模式。在这种模式下，没有车辆和物理引擎。您可以使用键盘在场景中自由移动，也可以通过 API 将可用的摄像头放置在任意姿态，从而采集深度图、视差图、表面法线图或物体分割图等图像。\n\n[更多信息](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fimage_apis)\n\n### 天气效果\n\n按 F10 键可查看天气效果的各种选项。您还可以使用 [API](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fapis#weather-apis) 来控制天气。按 F1 键可查看其他可用选项。\n\n![记录截图](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_readme_05d2c57f9f39.png)\n\n## 教程\n\n- [视频 - 使用 Pixhawk 设置 AirSim 教程](https:\u002F\u002Fyoutu.be\u002F1oY8Qu5maQQ) 由 Chris Lovett 制作\n- [视频 - 使用 Pixhawk 的 AirSim 教程](https:\u002F\u002Fyoutu.be\u002FHNWdYrtw3f0) 由 Chris Lovett 制作\n- [视频 - 在 AirSim 中使用现成环境](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=y09VbdQWvQY) 由 Jim Piavis 制作\n- [网络研讨会 - 利用高保真仿真支持自主系统](https:\u002F\u002Fnote.microsoft.com\u002FMSR-Webinar-AirSim-Registration-On-Demand.html) 由 Sai Vemprala 主讲\n- [使用 AirSim 进行强化学习](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Freinforcement_learning) 由 Ashish Kapoor 编写\n- [自动驾驶烹饪手册](https:\u002F\u002Faka.ms\u002FAutonomousDrivingCookbook) 由微软深度学习与机器人车库分会编写\n- [使用 TensorFlow 实现简单的避障功能](https:\u002F\u002Fgithub.com\u002Fsimondlevy\u002FAirSimTensorFlow) 由 Simon Levy 和 WLU 团队共同开发\n\n## 参与\n\n### 论文\n\n更多技术细节请参阅 [AirSim 论文（FSR 2017 大会）](https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.05065)。引用格式如下：\n``` \n@inproceedings{airsim2017fsr,\n  author = {Shital Shah and Debadeepta Dey and Chris Lovett and Ashish Kapoor},\n  title = {AirSim: 高保真视觉与物理仿真平台，用于自动驾驶车辆},\n  year = {2017},\n  booktitle = {野外与服务机器人},\n  eprint = {arXiv:1705.05065},\n  url = {https:\u002F\u002Farxiv.org\u002Fabs\u002F1705.05065}\n}\n```\n\n### 贡献\n\n如果您希望参与贡献，请查看 [未解决的问题](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fairsim\u002Fissues)。\n\n* [关于 AirSim 设计的更多信息](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fdesign)\n* [关于代码结构的更多信息](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fcode_structure)\n* [贡献指南](CONTRIBUTING.md)\n\n### 谁在使用 AirSim？\n\n我们维护着一份[列表](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fwho_is_using)，其中列出了我们所了解的一些项目、个人和组织。如果您希望被列入该列表，请在此处提交[请求](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fairsim\u002Fissues)。\n\n## 联系方式\n\n加入我们的 [GitHub 讨论组](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fdiscussions)，以获取最新信息或提出任何问题。\n\n我们还在 [Facebook](https:\u002F\u002Fwww.facebook.com\u002Fgroups\u002F1225832467530667\u002F) 上设有 AirSim 社区群组。\n\n## 最新动态\n\n* [电影级相机](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3949)\n* [ROS2 封装](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3976)\n* [列出所有资产的 API](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3940)\n* [movetoGPS API](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3746)\n* [光流相机](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3938)\n* [simSetKinematics API](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F4066)\n* [从现有 UE 材质或纹理 PNG 动态设置对象纹理](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3992)\n* [生成\u002F销毁光源并控制光源参数的功能](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3991)\n* [Unity 中支持多架无人机](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpull\u002F3128)\n* [通过键盘控制手动相机速度](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fpulls?page=6&q=is%3Apr+is%3Aclosed+sort%3Aupdated-desc#:~=text=1-,Control%20manual%20camera%20speed%20through%20the%20keyboard,-%233221%20by%20saihv) \n\n有关完整变更列表，请参阅我们的 [更改日志](docs\u002FCHANGELOG.md)。\n\n## 常见问题解答\n\n如果您遇到问题，请查阅 [常见问题解答](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Ffaq)，并随时在 [AirSim](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FAirSim\u002Fissues) 仓库中提交问题。\n\n## 行为准则\n\n本项目已采纳 [微软开源行为准则](https:\u002F\u002Fopensource.microsoft.com\u002Fcodeofconduct\u002F)。如需更多信息，请参阅 [行为准则常见问题解答](https:\u002F\u002Fopensource.microsoft.com\u002Fcodeofconduct\u002Ffaq\u002F) 或发送邮件至 [opencode@microsoft.com](mailto:opencode@microsoft.com) 提出任何进一步的问题或意见。\n\n\n## 许可证\n\n本项目采用 MIT 许可证发布。请查阅 [许可证文件](LICENSE) 以获取更多详细信息。","# AirSim 快速上手指南\n\n> **重要提示**：微软已宣布原 AirSim 仓库即将归档，未来将转向商业化的 **Project AirSim**。本指南基于当前可用的开源版本（2017 版），适合学习与研究使用。生产环境建议关注 [Project AirSim](https:\u002F\u002Faka.ms\u002Fprojectairsim) 的最新动态。\n\nAirSim 是一个基于虚幻引擎（Unreal Engine）的高保真模拟器，支持无人机、汽车等自主车辆的 AI 研究，提供深度学习、计算机视觉和强化学习算法的实验平台。\n\n## 环境准备\n\n### 系统要求\n- **操作系统**：Windows 10\u002F11, Linux (Ubuntu 18.04+), macOS (仅支持编译，无官方二进制包)\n- **硬件**：\n  - CPU: 多核处理器（推荐 i7 或同等性能）\n  - GPU: 支持 DirectX 11\u002F12 或 Vulkan 的独立显卡（NVIDIA GTX 1060 或更高推荐）\n  - 内存：8GB 以上（推荐 16GB+）\n  - 磁盘空间：至少 10GB 可用空间\n\n### 前置依赖\n- **Windows**: \n  - Visual Studio 2019\u002F2022 (含 C++ 桌面开发组件)\n  - Unreal Engine 4.27+ (如需自行编译)\n- **Linux**: \n  - GCC\u002FG++, CMake, Make\n  - Unreal Engine 4.27+ (如需自行编译)\n  - `sudo apt-get install build-essential cmake git`\n- **Python API 依赖** (用于程序控制):\n  ```bash\n  pip install airsim-python-api\n  ```\n\n## 安装步骤\n\n### 方案一：下载预编译二进制包（推荐新手）\n直接运行无需编译，最快上手。\n\n1. 访问 [Releases 页面](https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FAirSim\u002Freleases)。\n2. 下载对应系统的最新压缩包（例如 `AirSimNH.zip` 包含无人机和汽车场景）。\n   > *注：国内用户若下载缓慢，可尝试使用代理加速或寻找国内镜像源。*\n3. 解压到任意目录（路径中不要包含中文或空格）。\n4. 双击运行 `AirSimNH.exe` (Windows) 或对应的可执行文件。\n\n### 方案二：源码编译（高级用户）\n如需修改引擎或插件，请选择此方式。\n\n**Windows 编译示例:**\n```powershell\ngit clone https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FAirSim.git\ncd AirSim\n# 确保已安装 Unreal Engine 并配置好环境变量\n# 具体详细步骤请参考官方文档：https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fbuild_windows\n```\n\n**Linux 编译示例:**\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FAirSim.git\ncd AirSim\n# 参考官方文档配置 UE4 环境：https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fbuild_linux\n```\n\n## 基本使用\n\n### 1. 手动驾驶体验\n启动模拟器后：\n- **无人机模式**：使用键盘 `W, A, S, D` 控制前后左右，`Q\u002FE` 控制升降，`Space` 起飞\u002F降落。也可连接真实的 RC 遥控器。\n- **汽车模式**：使用方向键 `↑ ↓ ← →` 控制车辆行驶。\n- **切换天气\u002F视角**：按 `F10` 打开天气菜单，`F1` 查看其他选项。\n\n### 2. 程序化控制 (Python 示例)\nAirSim 核心功能是通过 API 进行编程控制。以下是一个最简单的 Python 连接与控制示例：\n\n**步骤：**\n1. 启动 AirSim 模拟器。\n2. 创建 `test_drive.py` 文件，写入以下代码：\n\n```python\nimport airsim\nimport time\n\n# 连接到模拟器 (默认端口 41451)\nclient = airsim.MultirotorClient()\nclient.confirmConnection()\n\n# 解锁并起飞 (无人机示例)\nprint(\"Arming...\")\nclient.enableApiControl(True)\nclient.armDisarm(True)\n\nprint(\"Taking off...\")\nclient.takeoffAsync().join()\n\n# 悬停 5 秒\ntime.sleep(5)\n\n# 获取相机图像 (深度图示例)\nresponses = client.simGetImages([\n    airsim.ImageRequest(\"0\", airsim.ImageType.DepthVis, True, False)])\nresponse = responses[0]\n\n# 保存图像\nairsim.write_depth_png_to_file(response.image_data_float, response.width, response.height, \"depth.png\")\nprint(\"Depth image saved to depth.png\")\n\n# 降落\nprint(\"Landing...\")\nclient.landAsync().join()\nclient.armDisarm(False)\nclient.enableApiControl(False)\n```\n\n3. 运行脚本：\n```bash\npython test_drive.py\n```\n\n### 3. 数据采集模式\n- **快速录制**：在模拟器界面右下角点击 \"Record\" 按钮，即可自动记录每一帧的位姿和图像数据。\n- **计算机视觉模式 (Computer Vision Mode)**：\n  若只需采集图像数据而无需物理仿真，可在 `settings.json` 中设置 `\"SimMode\": \"ComputerVision\"`。此模式下无飞行器物理限制，可自由通过 API 调整相机位置采集深度、分割、法线等数据。\n\n### 4. 配置文件 (settings.json)\n在项目根目录或 `Documents\u002FAirSim` 下创建 `settings.json` 可自定义行为，例如默认开启计算机视觉模式：\n```json\n{\n  \"SeeDocsAt\": \"https:\u002F\u002Fgithub.com\u002FMicrosoft\u002FAirSim\u002Fblob\u002Fmain\u002Fdocs\u002Fsettings.md\",\n  \"SettingsVersion\": 1.2,\n  \"SimMode\": \"ComputerVision\"\n}\n```","某无人机物流初创团队正在开发城市环境下的自动避障与精准投递算法，急需在真实飞行前验证系统的安全性。\n\n### 没有 AirSim 时\n- **测试成本高昂且风险大**：每次迭代算法都需实地试飞，不仅消耗昂贵的硬件设备，还面临炸机伤人或损坏周边设施的巨大安全风险。\n- **极端场景难以复现**：无法安全地模拟暴雨、强风、传感器故障或突发行人闯入等极端边缘案例，导致算法在复杂现实中的鲁棒性存疑。\n- **数据获取效率低下**：缺乏带有精确真值（Ground Truth）的深度图像、分割掩码和雷达数据，团队需耗费数周时间手动标注实拍视频才能训练模型。\n- **硬件依赖性强**：开发进度被飞行控制器调试和硬件组装卡住，软件工程师无法在无实物情况下并行开展核心算法研发。\n\n### 使用 AirSim 后\n- **零风险高频迭代**：基于虚幻引擎构建的高保真物理环境中，团队每天可进行数百次虚拟试飞，即使发生严重碰撞也无需承担任何实体损失。\n- **一键生成极端工况**：通过 API 轻松动态调整天气、光照及突发障碍，快速验证算法在暴雨夜航或 GPS 信号丢失等极端条件下的表现。\n- **自动化真值数据流**：直接调用接口实时获取像素级语义分割、深度图和三维位置信息，将模型训练数据的准备时间从数周缩短至几分钟。\n- **软硬件解耦开发**：支持软件在环（SITL）仿真，算法工程师可在无无人机实物的情况下，基于标准协议（如 PX4）完成全部逻辑开发与调试。\n\nAirSim 让团队在零安全事故的前提下，将自动驾驶算法的研发周期缩短了 70%，并显著提升了系统在复杂现实场景中的可靠性。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fmicrosoft_AirSim_bcd774eb.png","microsoft","Microsoft","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fmicrosoft_4900709c.png","Open source projects and samples from Microsoft",null,"opensource@microsoft.com","OpenAtMicrosoft","https:\u002F\u002Fopensource.microsoft.com","https:\u002F\u002Fgithub.com\u002Fmicrosoft",[83,87,91,95,99,103,107,111,115,119],{"name":84,"color":85,"percentage":86},"C++","#f34b7d",73.6,{"name":88,"color":89,"percentage":90},"C#","#178600",15.6,{"name":92,"color":93,"percentage":94},"Python","#3572A5",5.1,{"name":96,"color":97,"percentage":98},"C","#555555",4.2,{"name":100,"color":101,"percentage":102},"CMake","#DA3434",0.6,{"name":104,"color":105,"percentage":106},"Shell","#89e051",0.4,{"name":108,"color":109,"percentage":110},"Batchfile","#C1F12E",0.3,{"name":112,"color":113,"percentage":114},"ShaderLab","#222c37",0.1,{"name":116,"color":117,"percentage":118},"PowerShell","#012456",0,{"name":120,"color":121,"percentage":118},"Dockerfile","#384d54",18106,4874,"2026-04-12T14:13:12","NOASSERTION",4,"Windows, Linux, macOS","未说明（基于 Unreal Engine 和 Unity，通常建议具备支持 DirectX 11\u002F12 或 Vulkan 的独立显卡）","未说明",{"notes":131,"python":132,"dependencies":133},"AirSim 是构建在 Unreal Engine（主要）和 Unity（实验性）上的模拟器插件。支持软件在环（SITL）和硬件在环（HITL）仿真，兼容 PX4 和 ArduPilot 飞控。该仓库已宣布将在未来一年内归档，微软将转向新的商业产品 'Project AirSim'。用户可通过预编译二进制文件直接使用，也可从源码构建。","未说明（支持通过 API 使用 Python、C++、C# 和 Java）",[134,135,136,137],"Unreal Engine","Unity (实验性)","PX4","ArduPilot",[13,15,14,139],"其他",[141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157],"drones","ai","self-driving-car","autonomous-vehicles","autonomous-quadcoptor","research","computer-vision","artificial-intelligence","deeplearning","deep-reinforcement-learning","control-systems","pixhawk","cross-platform","platform-independent","airsim","unreal-engine","simulator","2026-03-27T02:49:30.150509","2026-04-13T13:34:52.990572",[161,166,171,176,181],{"id":162,"question_zh":163,"answer_zh":164,"source_url":165},31623,"AirSim 是否有新的 Linux 发布计划？如何修复 PX4 稳定性问题？","是的，最近有一个大型 PR 合并，修复了大多数 PX4 稳定性问题。如果您使用的是 Windows Subsystem for Linux version 2 (WSL2)，请参阅相关文档。以下是适用于 PX4 SITL 的有效配置设置：\n\n```json\n{\n  \"SettingsVersion\": 1.2,\n  \"SimMode\": \"Multirotor\",\n  \"ClockType\": \"SteppableClock\",\n  \"Vehicles\": {\n      \"PX4\": {\n          \"VehicleType\": \"PX4Multirotor\",\n          \"UseSerial\": false,\n          \"UseTcp\": true,\n          \"TcpPort\": 4560,\n          \"ControlPortLocal\": 14540,\n          \"ControlPortRemote\": 14580,\n          \"ControlIp\": \"localhost\",\n          \"Sensors\": {\n              \"Barometer\": {\n                  \"SensorType\": 1,\n                  \"Enabled\": true,\n                  \"PressureFactorSigma\": 0.0001825\n              }\n          },\n          \"Parameters\": {\n              \"NAV_RCL_ACT\": 0,\n              \"NAV_DLL_ACT\": 0\n          }\n      }\n  }\n}\n```","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fissues\u002F2477",{"id":167,"question_zh":168,"answer_zh":169,"source_url":170},31624,"四旋翼无人机在 AirSim 仿真中无法起飞怎么办？","如果无人机可以解锁（arm）但无法起飞，或者收到 'drone hasn't came to expected z' 或 'rpclib function takeoff threw an exception' 等错误，通常是因为固件版本不兼容或参数配置不当。\n\n解决方案：\n1. 尝试使用社区验证过的固件版本（例如 px4fmu-v2_default）。\n2. 检查并校准无线电遥控器 trim 值，建议使用 QGroundControl 进行校准。\n3. 确保仿真帧率稳定（如 70fps），低帧率可能导致控制异常。\n4. 对比并调整参数文件，确保与推荐配置一致。","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fissues\u002F138",{"id":172,"question_zh":173,"answer_zh":174,"source_url":175},31625,"在 Linux (Ubuntu) 上编译 AirSim 时遇到 'moving a local object in a return statement' 错误如何解决？","该错误通常出现在使用 clang 编译器时，因为将 `-Werror` 和 `-Wpessimizing-move` 警告视为错误处理。这是因为代码中使用了 `return std::move(config);`。\n\n解决方法：\n1. 更新到最新的 AirSim 代码库，维护者可能已经修复了此问题或更新了 rpclib。\n2. 如果是旧版本，可以手动修改源码，移除 `std::move` 调用，直接返回对象以允许拷贝省略（copy elision）：\n   将 `return std::move(config);` 改为 `return config;`。\n3. 确保安装了必要的依赖库（如 libjsoncpp0），尽管这主要影响链接而非此特定编译错误。","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fissues\u002F112",{"id":177,"question_zh":178,"answer_zh":179,"source_url":180},31626,"如何在 AirSim 中同时控制两架无人机？","可以通过修改 `settings.json` 文件来配置多无人机场景。虽然键盘直接控制多架无人机较为复杂，但推荐使用 Python API 进行编程控制。\n\n步骤：\n1. 在 `settings.json` 中定义多个飞行器配置。\n2. 使用 Python 脚本（如 `multi_agent_drone.py` 示例）通过 API 分别控制每架无人机。\n3. 确认应用程序能正常运行多智能体脚本，无需依赖键盘快捷键即可实现复杂协同控制。","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fissues\u002F2698",{"id":182,"question_zh":183,"answer_zh":184,"source_url":185},31627,"运行 Hello Drone 示例时遇到构建错误或 joystick 控制弹窗如何处理？","如果在运行 Hello Drone 示例时遇到构建错误或关于 joystick 控制的弹窗，请检查以下几点：\n1. 确认使用的 Unreal Engine 版本（如 4.26）与 AirSim 版本兼容。\n2. 检查是否所有必要的包都已正确安装。\n3. 如果弹出对话框询问是否继续使用之前的成功构建，选择“是”通常会启用 joystick 控制并允许无人机飞行。\n4. 注意：Hello Drone 程序本身主要是为了演示连接和控制，若需自动飞行通常需要编写额外的 Python 脚本发送指令，或者依赖 joystick 进行手动辅助飞行。\n5. 如果问题持续，请提供具体的 commit 版本以便进一步排查。","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Fissues\u002F3550",[187,192,197,202,207,211,216,220,225,229,234,239,244,249,254,259,264,269,274,279],{"id":188,"version":189,"summary_zh":190,"released_at":191},238864,"v1.8.1","#### 新增内容\n请查看我们的[变更日志](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002FCHANGELOG\u002F)，了解此版本中新增的功能。\n\n#### 环境列表\n目前可用的环境如下：\n\n1. AbandonedPark  \n2. Africa（地形不平且有动画动物）  \n3. AirSimNH（小型城市街区）  \n4. Blocks  \n5. Building_99  \n6. LandscapeMountains  \n7. MSBuild2018（足球场）  \n8. TrapCamera  \n9. ZhangJiajie  \n\n下载您所需的环境压缩包，解压到任意位置并运行 `run.bat`。有关如何使用汽车或无人机模型，请参阅[文档](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F)。\n\n#### 下载大型环境\nTrapCamera 是一个较大的环境，因此被拆分为两个文件。下载 001 和 002 两个文件后，请执行 `cat TrapCamera.zip.00* > TrapCamera.zip` 命令将其合并。\n\n#### 网络连接较慢或不稳定？\n您可以尝试使用 [uMap 下载管理器](http:\u002F\u002Fugetdm.com\u002F)。它支持断点续传和多线程下载，能够显著提升下载速度。\n\n## 关于环境源代码开放性的说明\n发布二进制文件中提供的环境使用了专有资源，因此我们无法公开这些环境的源代码及项目文件。部分环境可在 [虚幻引擎商城](https:\u002F\u002Funrealengine.com\u002Fmarketplace\u002Fen-US\u002Fstore) 购买。","2022-07-18T20:11:48",{"id":193,"version":194,"summary_zh":195,"released_at":196},238865,"v1.8.1-windows","#### 新增内容\n请查看我们的[变更日志](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002FCHANGELOG\u002F)，了解此版本中新增的功能。\n\n#### 环境列表\n目前提供以下环境：\n\n1. AbandonedPark  \n2. Africa（不平坦地形及动画动物）  \n3. AirSimNH（小型城市街区）  \n4. Blocks  \n5. Building_99  \n6. CityEnviron  \n7. Coastline  \n8. LandscapeMountains  \n9. MSBuild2018（足球场）  \n10. TrapCamera  \n11. ZhangJiajie  \n\n下载您所需的环境压缩包，解压到任意位置，然后运行`run.bat`。有关如何使用汽车或无人机模型的说明，请参阅[文档](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F)。\n\n#### 下载大型环境\nCityEnviron、Coastline 和 TrapCamera 是大型环境，因此被拆分为多个文件。下载 001、002 和 003 文件后，请使用 [7zip](http:\u002F\u002Fwww.7-zip.org\u002Fdownload.html) 等软件，右键单击 001 文件并选择解压选项。7zip 会自动检测并合并所有相关文件进行解压。\n\n#### 网络连接较慢或不稳定？\n您可以尝试使用 [uMap 下载管理器](http:\u002F\u002Fugetdm.com\u002F)。它支持断点续传和多线程下载，能够显著提升下载速度。\n\n## 关于环境源代码可用性的说明\n发布二进制文件中提供的环境使用了专有资源，因此我们无法分发这些环境的源代码和项目文件。部分环境可在 [虚幻引擎商城](https:\u002F\u002Funrealengine.com\u002Fmarketplace\u002Fen-US\u002Fstore) 购买。","2022-07-18T01:34:37",{"id":198,"version":199,"summary_zh":200,"released_at":201},238866,"v1.8.0-linux","#### 新增内容\n请查看我们的[变更日志](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002FCHANGELOG\u002F)，了解此版本中新增的功能。\n\n#### 环境列表\n目前可用的环境如下：\n\n1. AbandonedPark\n2. Africa（地形不平整，并包含动画动物）\n3. AirSimNH（小型城市街区）\n4. Blocks\n5. Building_99\n6. LandscapeMountains\n7. MSBuild2018（足球场）\n8. TrapCamera\n9. ZhangJiajie\n\n下载您所需的环境压缩包，将其解压到任意位置，然后运行`run.bat`。有关如何使用汽车或无人机模型的详细说明，请参阅[文档](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F)。\n\n#### 下载大型环境\nTrapCamera是一个较大的环境，因此被拆分为两个文件。下载完`001`和`002`两个文件后，请执行命令`cat TrapCamera.zip.00* > TrapCamera.zip`，以将它们合并为一个完整的压缩包。\n\n#### 网络连接较慢或不稳定？\n您可以尝试使用[uMap下载管理器](http:\u002F\u002Fugetdm.com\u002F)。该工具支持断点续传和多线程下载，能够显著提升下载速度。\n\n## 关于环境源代码可用性的说明\n发布二进制文件中提供的环境使用了专有资源，因此我们无法公开这些环境的源代码和项目文件。部分环境可在[虚幻引擎商城](https:\u002F\u002Funrealengine.com\u002Fmarketplace\u002Fen-US\u002Fstore)购买。","2022-06-13T07:21:39",{"id":203,"version":204,"summary_zh":205,"released_at":206},238867,"v1.8.0-windows","#### 新增内容\n请查看我们的[变更日志](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002FCHANGELOG\u002F)，了解此版本中新增的功能。\n\n#### 环境列表\n目前提供以下环境：\n\n1. AbandonedPark  \n2. Africa（不平坦地形及动画动物）  \n3. AirSimNH（小型城市街区）  \n4. Blocks  \n5. Building_99  \n6. CityEnviron  \n7. Coastline  \n8. LandscapeMountains  \n9. MSBuild2018（足球场）  \n10. TrapCamera  \n11. ZhangJiajie  \n\n下载您所需的环境压缩包，解压到任意位置，然后运行`run.bat`。有关如何使用汽车或无人机模型的详细说明，请参阅[文档](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F)。\n\n#### 下载大型环境\nCityEnviron、Coastline 和 TrapCamera 是大型环境，因此被拆分为多个文件。下载 001、002 和 003 文件后，请使用 [7zip](http:\u002F\u002Fwww.7-zip.org\u002Fdownload.html) 等软件，右键单击 001 文件并选择解压选项。7zip 会自动识别并合并所有相关文件进行解压。\n\n#### 网络连接较慢或不稳定？\n您可以尝试使用 [uMap 下载管理器](http:\u002F\u002Fugetdm.com\u002F)。它支持断点续传和多线程下载，能够显著提升下载速度。\n\n## 关于环境源代码可用性的说明\n发布二进制文件中提供的环境使用了专有资源，因此我们无法分发这些环境的源代码和项目文件。其中部分环境可在 [虚幻引擎商城](https:\u002F\u002Funrealengine.com\u002Fmarketplace\u002Fen-US\u002Fstore) 购买。","2022-06-13T07:21:01",{"id":208,"version":209,"summary_zh":190,"released_at":210},238868,"v1.7.0-linux","2022-01-13T17:22:36",{"id":212,"version":213,"summary_zh":214,"released_at":215},238869,"v1.7.0-windows","#### 新增内容\n请参阅我们的[变更日志](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002FCHANGELOG\u002F)，了解此版本中新增的功能。\n\n#### 环境列表\n目前提供以下环境：\n\n1. AbandonedPark  \n2. Africa（不平整地形及动画动物）  \n3. AirSimNH（小型城市街区）  \n4. Blocks  \n5. Building_99  \n6. CityEnviron  \n7. Coastline  \n8. LandscapeMountains  \n9. MSBuild2018（足球场）  \n10. TrapCamera  \n11. ZhangJiajie  \n\n下载您所需的环境压缩包，解压到任意位置，然后运行`run.bat`。有关如何使用汽车或无人机模型的详细说明，请参阅[文档](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F)。\n\n#### 下载大型环境\nCityEnviron、Coastline 和 TrapCamera 是较大的环境，因此被拆分为多个文件。下载 001、002 和 003 文件后，请使用 [7zip](http:\u002F\u002Fwww.7-zip.org\u002Fdownload.html) 等软件，右键单击 001 文件并选择解压选项。7zip 会自动识别并合并所有相关文件进行解压。\n\n#### 网络连接较慢或不稳定？\n您可以尝试使用 [uMap 下载管理器](http:\u002F\u002Fugetdm.com\u002F)。它支持断点续传和多线程下载，从而加快下载速度。\n\n## 关于环境源代码可用性的说明\n发布二进制文件中提供的环境使用了专有资源，因此我们无法公开这些环境的源代码和项目文件。部分环境可在 [虚幻引擎商城](https:\u002F\u002Funrealengine.com\u002Fmarketplace\u002Fen-US\u002Fstore) 购买。","2022-01-07T12:45:55",{"id":217,"version":218,"summary_zh":214,"released_at":219},238870,"v1.6.0-windows","2021-08-24T16:34:02",{"id":221,"version":222,"summary_zh":223,"released_at":224},238871,"v1.6.0-linux","#### 新增内容\n请查看我们的[变更日志](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002FCHANGELOG\u002F)，了解此版本中新增的功能。\n\n#### 环境列表\n目前可用的环境如下：\n\n1. AbandonedPark\n2. Africa（地形不平整，并包含动画动物）\n3. AirSimNH（小型城市街区）\n4. Blocks\n5. Building_99\n6. LandscapeMountains\n7. MSBuild2018（足球场）\n8. TrapCamera\n9. ZhangJiajie\n\n下载您所需的环境压缩包，将其解压到任意位置，然后运行`run.bat`。有关如何使用汽车或无人机模型的详细说明，请参阅[文档](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F)。\n\n#### 下载大型环境\nTrapCamera是一个较大的环境，因此被拆分为两个文件。下载完`001`和`002`两个文件后，请执行命令`cat TrapCamera.zip.00* > TrapCamera.zip`以将它们合并为一个完整的压缩包。\n\n#### 网络连接较慢或不稳定？\n您可以尝试使用[uMap下载管理器](http:\u002F\u002Fugetdm.com\u002F)。该工具支持断点续传和多线程下载，能够显著提升下载速度。\n\n## 关于环境源代码开放性的说明\n发布二进制文件中提供的环境使用了专有资源，因此我们无法公开这些环境的源代码及项目文件。部分环境可在[虚幻引擎商城](https:\u002F\u002Funrealengine.com\u002Fmarketplace\u002Fen-US\u002Fstore)购买。","2021-08-24T16:28:26",{"id":226,"version":227,"summary_zh":214,"released_at":228},238872,"v1.5.0-windows","2021-05-19T16:14:25",{"id":230,"version":231,"summary_zh":232,"released_at":233},238873,"v1.5.0-linux","#### 新增内容\n请参阅我们的[变更日志](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002FCHANGELOG\u002F)，了解此版本中新增的功能。\n\n#### 环境列表\n目前可用的环境如下：\n\n1. AbandonedPark\n1. Africa（地形不平且有动画动物）\n1. AirSimNH（小型城市街区）\n1. Blocks\n1. Building_99\n1. LandscapeMountains\n1. MSBuild2018（足球场）\n1. TrapCamera\n1. ZhangJiajie\n\n下载您所需的环境压缩包，解压到任意位置，然后运行`run.bat`。有关如何使用汽车或无人机模型，请参阅[文档](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F)。\n\n#### 下载大型环境\nTrapCamera是一个较大的环境，因此被拆分为两个文件。下载完`001`和`002`两个文件后，请使用如[7zip](http:\u002F\u002Fwww.7-zip.org\u002Fdownload.html)之类的软件，右键点击`001`文件并选择其中一个解压选项。7zip会自动识别并同时使用这两个文件进行解压。\n\n#### 网络连接较慢或不稳定？\n您可以尝试使用[uMap下载管理器](http:\u002F\u002Fugetdm.com\u002F)。它支持断点续传和多线程下载，从而加快下载速度。\n\n## 关于环境源代码可用性的说明\n发布二进制文件中提供的环境使用了专有资源，因此我们无法分发这些环境的源代码和项目文件。其中部分环境可在[虚幻引擎商城](https:\u002F\u002Funrealengine.com\u002Fmarketplace\u002Fen-US\u002Fstore)购买。","2021-05-19T16:13:27",{"id":235,"version":236,"summary_zh":237,"released_at":238},238874,"v1.4.0-linux","#### What's new\r\nSee the entries in our [changelog](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002FCHANGELOG\u002F) for what's been added in this release.\r\n\r\n#### Environments\r\nThese are the following environments available:\r\n\r\n1. AbandonedPark 🆕\r\n1. Africa (uneven terrain and animated animals)\r\n1. AirSimNH  (small urban neighborhood block)\r\n1. Blocks\r\n1. Building_99\r\n1. LandscapeMountains \r\n1. MSBuild2018 (soccer field)\r\n1. TrapCamera\r\n1. ZhangJiajie\r\n\r\nDownload the zip file for the environment you want, extract it somewhere and run the run.bat. Please see [docs](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F) for how to use the car or drone model.\r\n\r\n#### Downloading large environments\r\nTrapCamera is a big environment so it's divided into two files.  After downloading both 001 and 002 files, please use software such as [7zip](http:\u002F\u002Fwww.7-zip.org\u002Fdownload.html) to right click on 001 file and chose one of the extract options. 7zip will automatically detect and use both files.\r\n\r\n#### Slow \u002F unreliable Internet connection?\r\nTry [uMap download manager](http:\u002F\u002Fugetdm.com\u002F). This allows resume and multiple connections to speed things up.","2021-01-14T15:46:44",{"id":240,"version":241,"summary_zh":242,"released_at":243},238875,"v1.4.0-windows","#### What's new\r\nSee the entries in our [changelog](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002FCHANGELOG\u002F) for what's been added in this release.\r\n\r\n#### Environments\r\nThere are the following environments available:\r\n\r\n1. AbandonedPark 🆕\r\n1. Africa (uneven terrain and animated animals)\r\n1. AirSimNH  (small urban neighborhood block)\r\n1. Blocks\r\n1. Building_99\r\n1. CityEnviron (large city environment with moving vehicles and pedestrians)\r\n1. Coastline\r\n1. LandscapeMountains \r\n1. MSBuild2018 (soccer field)\r\n1. TrapCamera\r\n1. ZhangJiajie\r\n\r\nDownload the zip file for the environment you want, extract it somewhere and run the run.bat. Please see [docs](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F) for how to use the car or drone model.\r\n\r\n#### Downloading large environments\r\nCityEnviron, Coastline, and TrapCamera are big environments so they are divided into multiple files.  After downloading the 001, 002, and 003 files, please use software such as [7zip](http:\u002F\u002Fwww.7-zip.org\u002Fdownload.html) to right click on 001 file and chose one of the extract options. The 7zip automatically will detect and use all files.\r\n\r\n#### Slow \u002F unreliable Internet connection?\r\nTry [uMap download manager](http:\u002F\u002Fugetdm.com\u002F). This allows resume and multiple connections to speed things up.","2021-01-13T22:12:47",{"id":245,"version":246,"summary_zh":247,"released_at":248},238876,"v1.3.1-linux","#### Python package\r\n- [airsim](https:\u002F\u002Fpypi.org\u002Fproject\u002Fairsim\u002F)  v1.2.8\r\n\r\n#### Master commit ID\r\n- Release with master at [671a75f](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Ftree\u002F671a75f9217c42b48560e76576d493a7048bf7b1)\r\n\r\n#### Environments\r\n- Africa\r\n- Blocks\r\n- Building 99\r\n- Landscape Mountains\r\n- Neighborhood\r\n- Soccer Field\r\n- TrapCam\r\n- Zhangjiajie\r\n\r\nNote: We're releasing environments incrementally, and will be adding more binaries in this release soon.  ","2020-04-08T23:46:54",{"id":250,"version":251,"summary_zh":252,"released_at":253},238877,"v1.3.1-windows","#### Python package\r\n- [airsim](https:\u002F\u002Fpypi.org\u002Fproject\u002Fairsim\u002F)  v1.2.8\r\n\r\n#### Master commit ID\r\n- Release with master at [671a75f](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Ftree\u002F671a75f9217c42b48560e76576d493a7048bf7b1)\r\n\r\n#### Environments\r\n- Blocks\r\n- Landscape Mountains\r\n- Coastline\r\n- City\r\n\r\nNote: We're releasing environments incrementally, and will be adding more binaries in this release soon.  ","2020-04-08T23:46:48",{"id":255,"version":256,"summary_zh":257,"released_at":258},238878,"v1.3.0-Windows","#### Python package\r\n- [airsim](https:\u002F\u002Fpypi.org\u002Fproject\u002Fairsim\u002F)  v1.2.6\r\n\r\n#### Master commit ID\r\n- Release with master at [35a55e81](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Ftree\u002F35a55e817efda445099cf6d56e972e901c68a9af)\r\n\r\n#### Environments\r\n- Africa\r\n- Blocks\r\n- Neighborhood\r\n\r\nNote: We're releasing environments incrementally, and will be adding more binaries in this release soon.  ","2020-03-31T01:16:18",{"id":260,"version":261,"summary_zh":262,"released_at":263},238879,"v1.3.0-linux","#### Python package\r\n- [airsim](https:\u002F\u002Fpypi.org\u002Fproject\u002Fairsim\u002F)  v1.2.6\r\n\r\n#### Master commit ID\r\n- Release with master at [35a55e81](https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FAirSim\u002Ftree\u002F35a55e817efda445099cf6d56e972e901c68a9af)\r\n\r\n#### Environments\r\n- Blocks\r\n- Neighborhood\r\n\r\nNote: We're releasing environments incrementally, and will be adding more binaries in this release soon.  ","2020-03-31T01:16:37",{"id":265,"version":266,"summary_zh":267,"released_at":268},238880,"v.1.2.2","Following environments available:\r\n1. Africa\r\n1. Blocks\r\n1. CityEnviron (large environment with moving vehicles and pedestrians)\r\n1. Coastline\r\n1. Forest\r\n1. LandscapeMountains\r\n1. Plains\r\n1. Neighborhood\r\n1. SimpleMaze\r\n1. SubT\r\n1. TrapCam\r\n1. ZhangJiaJie\r\n\r\n#### Larger Environments\r\nBig environments are divided into two files.  After downloading both 001 and 002 files, please use software such as [7zip](http:\u002F\u002Fwww.7-zip.org\u002Fdownload.html) to right click on 001 file and chose one of the extract options. The 7zip automatically will detect and use both files.\r\n*Note:* City environment is under heavy development with more updates coming soon.\r\n\r\n#### Slow Internet Connection?\r\nTry [uMap download manager](http:\u002F\u002Fugetdm.com\u002F). This allows resume and multiple connections to speed things up.","2019-05-15T16:57:55",{"id":270,"version":271,"summary_zh":272,"released_at":273},238881,"v1.2.0Linux","**These are experimental Linux binaries for Ubuntu 16.04**\r\n\r\nFollowing environments are available:\r\n1. Africa (safari-like environment with moving animals and poachers)\r\n1. Blocks\r\n1. City (large environment with moving vehicles and pedestrians)\r\n1. Forest\r\n1. LandscapeMountains\r\n1. Neighborhood  (small urban neighbourhood block)\r\n1. SimpleMaze\r\n1. SubT\r\n1. TrapCam (hunting trap camera simulator with large and small game)\r\n1. Warehouse\r\n1. ZhangJiaJie\r\n\r\nDownload the zip file for the environment you want, extract it, run `.\u002FNameOfEnvironment.sh`. \r\n\r\nFor example, for `Blocks.zip`, you will    \r\n- `$ unzip Blocks.zip`\r\n- `$ .\u002FBlocks\u002FBlocks.sh`\r\n\r\nSimilarly, for `AirSimNH.zip`, you will    \r\n- `$ unzip AirSimNH.zip`\r\n- `$ .\u002FAirSimNH\u002FAirSimNH.sh`\r\n\r\nPlease see [docs](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F) for how to use the car or drone model.\r\n\r\n\r\n#### Files for large environments\r\nBig environments are divided into two files.  After downloading both 001 and 002 files, please use software such as [7zip](http:\u002F\u002Fwww.7-zip.org\u002Fdownload.html) to right click on 001 file and chose one of the extract options. The 7zip automatically will detect and use both files.\r\n*Note:* City environment is under heavy development with more updates coming soon.\r\n\r\nlinux zip tool will search for all zip files with a matching name and unzip them accordingly.\r\n\r\n#### Slow Internet Connection?\r\nTry [uMap download manager](http:\u002F\u002Fugetdm.com\u002F). This allows resume and multiple connections to speed things up.","2019-01-12T01:25:22",{"id":275,"version":276,"summary_zh":277,"released_at":278},238882,"v1.2.1","Following environments available:\r\n\r\n1. Blocks\r\n2. AirSimNH  (small urban neighbourhood block)\r\n3. CityEnviron (large environment with moving vehicles and pedestrians)\r\n4. ZhangJiaJie (Zhangjiajie mountains in China)\r\n5. Forest (dense Redwood forest)\r\n6. Warehouse (with forklifts)\r\n7. TrapCam (dynamic forest environment for cameras detection of animals)\r\n8. Plains (Windmill farm)\r\n9. Coastline (short segment similar to Maui's Hana road)\r\n10. Africa (uneven terrain and animated animals)\r\n11. TalkingHeads (Human head controllable via AirSim Character APIs)\r\n12. SimpleMaze (maze for car or drone)\r\n13. Mountain Landscape (with power lines)\r\n\r\nDownload the zip file for the environment you want, extract it somewhere and run the run.bat. Please see [docs](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F) for how to use the car or drone model.\r\n\r\n#### Larger Environments\r\nBig environments are divided into two files.  After downloading both 001 and 002 files, please use software such as [7zip](http:\u002F\u002Fwww.7-zip.org\u002Fdownload.html) to right click on 001 file and chose one of the extract options. The 7zip automatically will detect and use both files.\r\n*Note:* City environment is under heavy development with more updates coming soon.\r\n\r\n#### Slow Internet Connection?\r\nTry [uMap download manager](http:\u002F\u002Fugetdm.com\u002F). This allows resume and multiple connections to speed things up.","2019-01-23T19:13:52",{"id":280,"version":281,"summary_zh":282,"released_at":283},238883,"v1.2.0","There are following environments available:\r\n\r\n1. City (large environment with moving vehicles and pedestrians)\r\n2. Neighbourhood  (small urban neighbourhood block)\r\n3. Mountain Landscape \r\n4. Africa (uneven terrain and animated animals)\r\n5. ZhangJiaJie (Zhangjiajie mountains in China)\r\n6. Warehouse\r\n7. SimpleMaze\r\n8. Coastline (short segment similar to Maui's Hana road)\r\n\r\nDownload the zip file for the environment you want, extract it somewhere and run the run.bat. Please see [docs](https:\u002F\u002Fmicrosoft.github.io\u002FAirSim\u002Fuse_precompiled\u002F) for how to use the car or drone model.\r\n\r\n#### Files for City Environment\r\nThis is a big environment so it's divided into two files.  After downloading both 001 and 002 files, please use software such as [7zip](http:\u002F\u002Fwww.7-zip.org\u002Fdownload.html) to right click on 001 file and chose one of the extract options. The 7zip automatically will detect and use both files.\r\n*Note:* City environment is under heavy development with more updates coming soon.\r\n\r\n#### Slow Internet Connection?\r\nTry [uMap download manager](http:\u002F\u002Fugetdm.com\u002F). This allows resume and multiple connections to speed things up.","2018-06-20T23:25:01"]