[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-lgsvl--simulator":3,"tool-lgsvl--simulator":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},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。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},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",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},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。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":79,"owner_email":79,"owner_twitter":80,"owner_website":81,"owner_url":82,"languages":83,"stars":121,"forks":122,"last_commit_at":123,"license":124,"difficulty_score":10,"env_os":125,"env_gpu":126,"env_ram":127,"env_deps":128,"category_tags":131,"github_topics":132,"view_count":152,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":153,"updated_at":154,"faqs":155,"releases":186},601,"lgsvl\u002Fsimulator","simulator","A ROS\u002FROS2 Multi-robot Simulator for Autonomous Vehicles","SVL Simulator 是一款基于 ROS 和 ROS2 系统的自动驾驶车辆仿真平台，专注于为智能驾驶技术提供高保真的虚拟测试环境。它有效解决了在真实道路测试自动驾驶算法时存在的安全风险和资金成本问题，允许用户在可控的虚拟场景中构建复杂交通流，验证感知、规划及控制模块的性能。\n\n该平台非常适合自动驾驶领域的工程师、科研人员以及高校实验室使用。其技术亮点包括支持多机器人协同仿真、丰富的传感器模型以及灵活的云边端架构，能够帮助团队快速迭代算法。\n\n值得注意的是，LG 公司已于 2022 年 1 月停止了对 SVL Simulator 的活跃开发，不再推送新代码或修复 Bug。尽管如此，项目源代码仍保留在 GitHub 上供社区自由 fork 和修改。当前版本运行依赖 WISE 云服务来获取资产和配置集群。虽然官方维护已结束，但对于希望基于现有框架进行二次开发或离线部署的研究者而言，它依然是一个值得参考的开源项目。","\u003Ch1 align=\"center\">SVL Simulator:  An Autonomous Vehicle Simulator\u003C\u002Fh1>\n\n\u003Cdiv align=\"center\">\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Flatest\">\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Frelease-pre\u002Flgsvl\u002Fsimulator.svg\" alt=\"Github release\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"\">\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Flgsvl\u002Fsimulator\u002Ftotal.svg\" alt=\"Release downloads\" \u002F>\u003C\u002Fa>\n\u003C\u002Fdiv>\n\u003Cdiv align=\"center\">\n  \u003Ch4>\n    \u003Ca href=\"https:\u002F\u002Fsvlsimulator.com\" style=\"text-decoration: none\">\n    Website\u003C\u002Fa>\n    \u003Cspan> | \u003C\u002Fspan>\n    \u003Ca href=\"https:\u002F\u002Fsvlsimulator.com\u002Fdocs\" style=\"text-decoration: none\">\n    Documentation\u003C\u002Fa>\n    \u003Cspan> | \u003C\u002Fspan>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Flatest\" style=\"text-decoration: none\">\n    Download\u003C\u002Fa>\n  \u003C\u002Fh4>\n\u003C\u002Fdiv>\n\n## Sunsetting SVL Simulator\n\n### LG has made the difficult decision to suspend active development of SVL Simulator, as of January 1, 2022.\n\nThere are no plans for any new or bugfix releases of SVL Simulator in 2022. There will be no new source code changes pushed to GitHub, and there will be no reviews or merging of Pull Requests submitted on GitHub for SVL Simulator or any of its related plug-ins. There will be no new simulator assets built and shared nor updates made to existing assets by the SVL Simulator team.\n\nWe will make a reasonable effort to keep the [wise.svlsimulator.com](https:\u002F\u002Fwise.svlsimulator.com) website up and running through at least Thursday, June 30, 2022, and will also maintain the [SVLSimulator.com](https:\u002F\u002FSVLSimulator.com) web site including the [simulator documentation](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002F) pages through at least Thursday, June 30, 2022.\n\nAt this time we do not plan to remove the [SVL Simulator source code](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator) (and related plug-in) projects from GitHub. The open source project and source code will remain available for anyone who wants to build (or modify) SVL Simulator.\n\nWe apologize for any inconvenience this may cause and appreciate your understanding.\n\nSincerely,\n\nThe SVL Simulator team\n\n\u003Cbr\u002F>\n\n### Questions\n\n##### **Q: Will SVL Simulator run locally without the [wise.svlsimulator.com](https:\u002F\u002Fwise.svlsimulator.com) web site?**\n\nA: The latest released version of SVL (2021.3) requires the use of the WISE (web user interface) cloud service to download assets, configure simulation clusters, and create and launch simulations. It may be possible to remove this dependency (e.g. in a fork; see below) and then build and launch a local simulator instance.\n\n##### **Q: Will LG release the source code for the WISE (web user interface) cloud service?**\n\nA: There are no plans at this time to release the source code for WISE.\n\n##### **Q: Would LG be interested in transferring the SVL Simulator project to someone interested in taking over the project?**\n\nA: There are no plans at this time to transfer the SVL Simulator project (or the WISE cloud service).\n\n##### **Q: Will the Simulator Software License Agreement be changed?**\n\nA: There are no plans at this time to change the [Simulator Software License Agreement](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fblob\u002Fmaster\u002FLICENSE).\n\n##### **Q: Can users share source code changes and forks of SVL Simulator?**\n\nA: As a GitHub project, anyone is able to create their own fork; in fact, there are already over 500 such forks of the [SVL Simulator project](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator). Users can then make changes and even submit pull requests back to the original (parent) project. While we have no plans to review or merge such changes into the main project, users are free to review open PRs and create their own local build from their own or any other public fork.\n\n##### **Q: Can users share new builds of SVL Simulator?**\n\nA: The [Simulator Software License Agreement](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fblob\u002Fmaster\u002FLICENSE) allows you to “modify or create derivative works of the Licensed Materials” and only restricts their commercial use. Therefore, it is ok for users to share new builds of SVL Simulator as long as such builds are not sold or otherwise used for commercial purposes.\n\n##### **Q: What about the SVL Simulator Premium product and\u002For cloud simulation service?**\n\nA: There are no plans at this time to offer a SVL Simulator Premium product or cloud service.\n\n##### **Q: Can users still post technical questions on GitHub?**\n\nA: Technical questions may be posted to the [SVL Simulator Issues](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fissues) page on GitHub but may not be answered by the SVL Simulator team. We encourage users to help each other with questions or issues that are posted.\n\n##### **Q: What if there are other questions not addressed in this document?**\n\nA: Other questions may be posted to the [SVL Simulator Issues](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fissues) page on GitHub.\n\n\u003Cbr\u002F>\n\n------ \n# Project README\n\n## Stay Informed\n\nCheck out our latest [news](https:\u002F\u002Fwww.svlsimulator.com\u002Fnews\u002F) and subscribe to our [mailing list](http:\u002F\u002Feepurl.com\u002FhtlRjH) to get the latest updates.\n\n\n## Introduction\n\nLG Electronics America R&D Lab has developed an HDRP Unity-based multi-robot simulator for autonomous vehicle developers. \nWe provide an out-of-the-box solution which can meet the needs of developers wishing to focus on testing their autonomous vehicle algorithms. \nIt currently has integration with The Autoware Foundation's [Autoware.auto](https:\u002F\u002Fgitlab.com\u002Fautowarefoundation\u002Fautoware.auto\u002FAutowareAuto) and Baidu's [Apollo](https:\u002F\u002Fgithub.com\u002FApolloAuto\u002Fapollo) platforms, can generate HD maps, and can be immediately used for testing and validation of a whole system with little need for custom integrations. \nWe hope to build a collaborative community among robotics and autonomous vehicle developers by open sourcing our efforts. \n\n*To use the simulator with Apollo 6.0 or master, first download the simulator binary, then follow our [Running with latest Apollo](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fsystem-under-test\u002Fapollo-master-instructions\u002F) docs.*\n\n*To use the simulator with Autoware.auto, first download the simulator binary, then follow the guide on our [Autoware.auto](https:\u002F\u002Fautowarefoundation.gitlab.io\u002Fautoware.auto\u002FAutowareAuto\u002Flgsvl.html).*\n\nFor users in China, you can view our latest videos [here](https:\u002F\u002Fspace.bilibili.com\u002F412295691) and download our simulator releases [here](https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1M33ysJYZfi4vya41gmB0rw) (code: 6k91).\n对于中国的用户，您也可在[哔哩哔哩](https:\u002F\u002Fspace.bilibili.com\u002F412295691)上观看我们最新发布的视频，从[百度网盘](https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1M33ysJYZfi4vya41gmB0rw)(提取码: 6k91)上下载使用我们的仿真器。\n\n\n## Paper\nIf you are using SVL Simulator for your research paper, please cite our ITSC 2020 paper:\n[LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.03778)\n\n```\n@article{rong2020lgsvl,\n  title={LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving},\n  author={Rong, Guodong and Shin, Byung Hyun and Tabatabaee, Hadi and Lu, Qiang and Lemke, Steve and Mo{\\v{z}}eiko, M{\\=a}rti{\\c{n}}{\\v{s}} and Boise, Eric and Uhm, Geehoon and Gerow, Mark and Mehta, Shalin and others},\n  journal={arXiv preprint arXiv:2005.03778},\n  year={2020}\n}\n```\n\n\n\n## Getting Started\n\nYou can find complete and the most up-to-date guides on our [documentation website](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs).\n\nRunning the simulator with reasonable performance and frame rate (for perception related tasks) requires a high performance desktop. Below is the recommended system for running the simulator at high quality. We are currently working on performance improvements for a better experience. \n\n**Recommended system:**\n\n- 4 GHz Quad Core CPU\n- Nvidia GTX 1080, 8GB GPU memory\n- Windows 10 64 Bit\n\nThe easiest way to get started with running the simulator is to download our [latest release](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Flatest) and run as a standalone executable.\n\nCurrently, running the simulator in Windows yields better performance than running on Linux. \n\n### Downloading and starting simulator\n\n1. Download the latest release of the SVL Simulator for your supported operating system (Windows or Linux) here: [https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Flatest](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Flatest)\n2. Unzip the downloaded folder and run the executable.\n\nSee the full installation guide [here](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Finstallation-guide\u002Finstalling-simulator).\n\n### Building and running from source\n\nIf you would like to customize the simulator, build simulation content, or access specific features available in [Developer Mode](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Frunning-simulations\u002Fdeveloper-mode), you can clone the project with Unity Editor, and build the project from source.\n\nCheck out our instructions for getting started with building from source [here](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Finstallation-guide\u002Fbuild-instructions).\n**Note:** Please checkout the \"release-*\" branches or release tags for stable (ready features) and \"master\" branch for unstable (preview of work in progress).\n\n\n## Simulator Instructions (from 2021.1 release onwards)\n\n1. After starting the simulator, you should see a button to \"Link to Cloud\".\n2. Use this button to link your local simulator instance to a [cluster](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Fclusters-tab) on our [web user interface](https:\u002F\u002Fwise.svlsimulator.com).\n3. Now create a [random traffic](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fcreating-scenarios\u002Frandom-traffic-scenarios\u002F) simulation. For a standard setup, select \"BorregasAve\" for map and \"Jaguar2015XE with Apollo 5.0 sensor configuration\" for vehicle. Click \"Run\" to begin.\n4. The vehicle should spawn inside the map environment that was selected.\n5. Read [here](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fkeyboard-shortcuts\u002F) for an explanation of all current keyboard shortcuts and controls.\n6. Follow the guides on our respective [Autoware](https:\u002F\u002Fgithub.com\u002Flgsvl\u002FAutoware) and [Apollo 5.0](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fapollo-5.0) repositories for instructions on running the platforms with the simulator.\n\n**NOTE**: If using a release older than \"2021.1\", please follow the instructions on our documentation [archives](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Farchive\u002F).\n\n### Guide to simulator functionality\n\nLook [here](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs) for a guide to currently available functionality and features.\n\n\n\n## Contact\n\nPlease feel free to provide feedback or ask questions by creating a Github issue. For inquiries about collaboration, please email us at [contact@svlsimulator.com](mailto:contact@svlsimulator.com).\n\n\n\n## Copyright and License\n\nCopyright (c) 2019-2021 LG Electronics, Inc.\n\nThis software contains code licensed as described in LICENSE.\n","\u003Ch1 align=\"center\">SVL 模拟器：一个自动驾驶车辆模拟器\u003C\u002Fh1>\n\n\u003Cdiv align=\"center\">\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Flatest\">\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Frelease-pre\u002Flgsvl\u002Fsimulator.svg\" alt=\"GitHub 发布版本\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"\">\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Flgsvl\u002Fsimulator\u002Ftotal.svg\" alt=\"发布下载量\" \u002F>\u003C\u002Fa>\n\u003C\u002Fdiv>\n\u003Cdiv align=\"center\">\n  \u003Ch4>\n    \u003Ca href=\"https:\u002F\u002Fsvlsimulator.com\" style=\"text-decoration: none\">\n    官网\u003C\u002Fa>\n    \u003Cspan> | \u003C\u002Fspan>\n    \u003Ca href=\"https:\u002F\u002Fsvlsimulator.com\u002Fdocs\" style=\"text-decoration: none\">\n    文档\u003C\u002Fa>\n    \u003Cspan> | \u003C\u002Fspan>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Flatest\" style=\"text-decoration: none\">\n    下载\u003C\u002Fa>\n  \u003C\u002Fh4>\n\u003C\u002Fdiv>\n\n## SVL 模拟器停止维护\n\n### LG 已做出艰难决定，自 2022 年 1 月 1 日起暂停 SVL 模拟器的活跃开发。\n\n2022 年没有 SVL 模拟器的任何新功能或错误修复版本发布计划。不会有新的源代码更改推送到 GitHub，也不会审查或合并提交给 GitHub 的 SVL 模拟器或其相关插件的拉取请求 (Pull Requests)。SVL 模拟器团队将不再构建和共享新的模拟器资源，也不会更新现有资源。\n\n我们将尽合理努力确保 [wise.svlsimulator.com](https:\u002F\u002Fwise.svlsimulator.com) 网站至少在 2022 年 6 月 30 日星期四之前正常运行，并将维持 [SVLSimulator.com](https:\u002F\u002FSVLSimulator.com) 网站，包括 [模拟器文档](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002F) 页面，至少在 2022 年 6 月 30 日星期四之前。\n\n目前，我们计划不从 GitHub 上删除 [SVL 模拟器源代码](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator)（及相关插件）项目。开源项目和源代码将继续可供任何想要构建（或修改）SVL 模拟器的人使用。\n\n对于由此可能造成的任何不便，我们深表歉意，并感谢您的理解。\n\n此致，\n\nSVL 模拟器团队\n\n\u003Cbr\u002F>\n\n### 常见问题\n\n##### **问：SVL 模拟器是否可以在没有 [wise.svlsimulator.com](https:\u002F\u002Fwise.svlsimulator.com) 网站的情况下本地运行？**\n\n答：最新发布的 SVL 版本（2021.3）需要使用 WISE（Web 用户界面）云服务来下载资源、配置模拟集群以及创建和启动模拟。有可能移除这种依赖关系（例如在分支中；见下文），然后构建和启动本地模拟器实例。\n\n##### **问：LG 会发布 WISE（Web 用户界面）云服务的源代码吗？**\n\n答：目前暂无发布 WISE 源代码的计划。\n\n##### **问：LG 是否有兴趣将 SVL 模拟器项目移交给有兴趣接手该项目的人？**\n\n答：目前暂无移交 SVL 模拟器项目（或 WISE 云服务）的计划。\n\n##### **问：模拟器软件许可协议会更改吗？**\n\n答：目前暂无更改 [模拟器软件许可协议](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fblob\u002Fmaster\u002FLICENSE) 的计划。\n\n##### **问：用户可以分享 SVL 模拟器的源代码更改和分支吗？**\n\n答：作为一个 GitHub 项目，任何人都可以创建自己的分支；事实上，目前已有超过 500 个 [SVL 模拟器项目](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator) 的分支。用户可以随后进行修改，甚至向原始（父）项目提交拉取请求。虽然我们目前没有计划审查或将此类更改合并到主项目中，但用户可以自由地审查开放的 PR，并从他们自己的或任何其他公共分支创建自己的本地构建。\n\n##### **问：用户可以分享 SVL 模拟器的新版本构建吗？**\n\n答：[模拟器软件许可协议](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fblob\u002Fmaster\u002FLICENSE) 允许您“修改或创建授权材料的衍生作品”，仅限制其商业使用。因此，只要这些构建不用于销售或其他商业目的，用户可以分享 SVL 模拟器的新版本构建。\n\n##### **问：关于 SVL 模拟器高级产品和\u002F或云模拟服务呢？**\n\n答：目前暂无提供 SVL 模拟器高级产品或云服务的计划。\n\n##### **问：用户仍然可以在 GitHub 上发布技术问题吗？**\n\n答：技术问题可以发布到 GitHub 上的 [SVL 模拟器问题](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fissues) 页面，但 SVL 模拟器团队可能不会回答。我们鼓励用户互相帮助解决发布的问题。\n\n##### **问：如果还有其他未在本文件中解决的问题怎么办？**\n\n答：其他问题可以发布到 GitHub 上的 [SVL 模拟器问题](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fissues) 页面。\n\n\u003Cbr\u002F>\n\n------ \n# 项目 README\n\n## 保持关注\n\n查看我们最新的 [新闻](https:\u002F\u002Fwww.svlsimulator.com\u002Fnews\u002F) 并订阅我们的 [邮件列表](http:\u002F\u002Feepurl.com\u002FhtlRjH) 以获取最新更新。\n\n\n## 简介\n\nLG 电子美国研发中心为自动驾驶汽车开发者开发了一款基于 HDRP（高清渲染管线）Unity 的多机器人模拟器。\n我们提供开箱即用的解决方案，可以满足希望专注于测试其自动驾驶汽车算法的开发者的需求。\n它目前集成了 Autoware 基金会的 [Autoware.auto](https:\u002F\u002Fgitlab.com\u002Fautowarefoundation\u002Fautoware.auto\u002FAutowareAuto) 和百度的 [Apollo](https:\u002F\u002Fgithub.com\u002FApolloAuto\u002Fapollo) 平台，可以生成高精地图 (HD Maps)，并且几乎不需要自定义集成即可立即用于整个系统的测试和验证。\n我们希望通过开源我们的工作，在机器人和自动驾驶汽车开发者之间建立一个协作社区。 \n\n*要使用模拟器配合 Apollo 6.0 或 master 版本，请先下载模拟器二进制文件，然后遵循我们的 [与最新版 Apollo 运行](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fsystem-under-test\u002Fapollo-master-instructions\u002F) 文档。*\n\n*要使用模拟器配合 Autoware.auto，请先下载模拟器二进制文件，然后遵循我们 [Autoware.auto](https:\u002F\u002Fautowarefoundation.gitlab.io\u002Fautoware.auto\u002FAutowareAuto\u002Flgsvl.html) 上的指南。*\n\n对于中国的用户，您也可在 [哔哩哔哩](https:\u002F\u002Fspace.bilibili.com\u002F412295691) 上观看我们最新发布的视频，从 [百度网盘](https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1M33ysJYZfi4vya41gmB0rw)(提取码：6k91) 上下载使用我们的仿真器。\n\n## 论文\n如果您在研究论文中使用 SVL Simulator，请引用我们的 ITSC 2020 论文：\n[LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2005.03778)\n\n```\n@article{rong2020lgsvl,\n  title={LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving},\n  author={Rong, Guodong and Shin, Byung Hyun and Tabatabaee, Hadi and Lu, Qiang and Lemke, Steve and Mo{\\v{z}}eiko, M{\\=a}rti{\\c{n}}{\\v{s}} and Boise, Eric and Uhm, Geehoon and Gerow, Mark and Mehta, Shalin and others},\n  journal={arXiv preprint arXiv:2005.03778},\n  year={2020}\n}\n```\n\n\n\n## 入门指南\n\n您可以在我们的 [文档网站](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs) 上找到完整且最新的指南。\n\n以合理的性能和帧率（用于感知相关任务）运行模拟器需要一台高性能台式机。以下是高质量运行模拟器的推荐系统配置。我们目前正在努力进行性能改进，以获得更好的体验。 \n\n**推荐系统：**\n\n- 4 GHz 四核 CPU\n- Nvidia GTX 1080，8GB GPU 显存\n- Windows 10 64 位\n\n开始使用模拟器最简单的方法是下载我们的 [最新发行版](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Flatest) 并作为独立可执行文件运行。\n\n目前，在 Windows 上运行模拟器比在 Linux 上运行能获得更好的性能。 \n\n### 下载和启动模拟器\n\n1. 在此处下载适用于您支持的操作系统（Windows 或 Linux）的 SVL Simulator 最新发行版：[https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Flatest](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Flatest)\n2. 解压下载的文件夹并运行可执行文件。\n\n请参阅完整的安装指南 [这里](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Finstallation-guide\u002Finstalling-simulator)。\n\n### 从源代码构建和运行\n\n如果您想自定义模拟器、构建仿真内容或访问 [开发者模式](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Frunning-simulations\u002Fdeveloper-mode) 中提供的特定功能，您可以使用 Unity Editor 克隆项目并从源代码构建。\n\n查看我们从源代码构建的入门说明 [这里](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Finstallation-guide\u002Fbuild-instructions)。\n**注意：** 对于稳定版本（已就绪功能），请检出 \"release-*\" 分支或发布标签；对于不稳定版本（进行中工作的预览），请检出 \"master\" 分支。\n\n\n## 模拟器使用说明（2021.1 发行版及以后）\n\n1. 启动模拟器后，您应该能看到一个“链接到云端”的按钮。\n2. 使用此按钮将您的本地模拟器实例链接到我们 [Web 用户界面](https:\u002F\u002Fwise.svlsimulator.com) 上的 [集群](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Fclusters-tab)。\n3. 现在创建一个 [随机交通](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fcreating-scenarios\u002Frandom-traffic-scenarios\u002F) 仿真。对于标准设置，选择\"BorregasAve\"作为地图，选择\"Jaguar2015XE with Apollo 5.0 sensor configuration\"作为车辆。点击“运行”开始。\n4. 车辆应生成在您选择的地图环境中。\n5. 阅读 [此处](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fkeyboard-shortcuts\u002F) 了解所有当前键盘快捷键和控制功能的说明。\n6. 按照我们各自的 [Autoware](https:\u002F\u002Fgithub.com\u002Flgsvl\u002FAutoware) 和 [Apollo 5.0](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fapollo-5.0) 仓库中的指南，了解如何在模拟器中运行这些平台。\n\n**注意**：如果使用早于 \"2021.1\" 的发行版，请遵循我们文档 [存档](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Farchive\u002F) 中的说明。\n\n### 模拟器功能指南\n\n查看 [这里](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs) 了解当前可用的功能和特性指南。\n\n\n\n## 联系方式\n\n欢迎通过创建 Github Issue 提供反馈或提问。关于合作事宜，请发送邮件至 [contact@svlsimulator.com](mailto:contact@svlsimulator.com)。\n\n\n\n## 版权与许可\n\nCopyright (c) 2019-2021 LG Electronics, Inc.\n\n本软件包含的代码按 LICENSE 中所述进行许可。","# SVL Simulator 快速上手指南\n\n> ⚠️ **项目状态提示**：SVL Simulator 已于 2022 年 1 月 1 日停止活跃开发，不再发布新版本或修复 Bug。但开源代码及现有资产仍可供社区构建和使用。\n\n## 1. 环境准备\n\n为了获得合理的性能和帧率（特别是感知相关任务），建议使用高性能桌面电脑。官方推荐配置如下：\n\n- **操作系统**：Windows 10 64 Bit（性能优于 Linux）\n- **CPU**：4 GHz Quad Core CPU\n- **GPU**：Nvidia GTX 1080 或更高（显存 8GB 以上）\n- **依赖**：无需额外安装，二进制版本可直接运行；若需修改源码则需 Unity Editor。\n\n## 2. 安装步骤\n\n### 方式一：下载预编译版本（推荐）\n\n对于大多数用户，直接下载并运行可执行文件是最快的方式。\n\n1. **下载模拟器**\n   - **国内用户（推荐）**：访问百度网盘链接，提取码为 `6k91`\n     ```text\n     https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1M33ysJYZfi4vya41gmB0rw\n     ```\n   - **国际用户**：访问 GitHub Release 页面\n     ```text\n     https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Flatest\n     ```\n\n2. **解压与启动**\n   - 解压下载的文件夹。\n   - 运行目录内的可执行文件（Executable）。\n\n### 方式二：从源码构建（仅限高级用户）\n\n如需自定义模拟器功能或访问开发者模式，可克隆项目并使用 Unity Editor 构建。\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator.git\n```\n*注：请检出 \"release-*\" 分支或标签以获取稳定版本，\"master\" 分支包含未稳定的预览功能。*\n\n详细构建说明请参考：[Build Instructions](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Finstallation-guide\u002Fbuild-instructions)\n\n## 3. 基本使用\n\n启动模拟器后，请按以下步骤创建仿真场景：\n\n1. **连接云端服务**\n   点击界面上的 **\"Link to Cloud\"** 按钮，将本地实例连接到 [WISE Web UI](https:\u002F\u002Fwise.svlsimulator.com)。\n   *注意：最新版本（2021.3）需要此云服务来下载资产、配置集群和启动仿真。*\n\n2. **创建场景**\n   - 选择 **\"Random Traffic\"** 仿真类型。\n   - **地图 (Map)**：选择 `BorregasAve`。\n   - **车辆 (Vehicle)**：选择 `Jaguar2015XE with Apollo 5.0 sensor configuration`。\n   - 点击 **\"Run\"** 开始。\n\n3. **运行验证**\n   车辆将生成在选定的地图环境中。此时可进行自动驾驶算法的测试与验证。\n\n4. **快捷键控制**\n   查看键盘快捷键说明：[Keyboard Shortcuts](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fkeyboard-shortcuts\u002F)\n\n### 集成其他平台\n- **Apollo**：参考 [Apollo 5.0 仓库指南](https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fapollo-5.0)\n- **Autoware.auto**：参考 [Autoware.auto 文档](https:\u002F\u002Fautowarefoundation.gitlab.io\u002Fautoware.auto\u002FAutowareAuto\u002Flgsvl.html)","某自动驾驶初创团队正在开发 L4 级无人车感知算法，急需海量极端路况数据来验证模型安全性。\n\n### 没有 simulator 时\n- 实地测试成本高昂，难以复现暴雨、冰雪或夜间等危险工况，且存在安全隐患。\n- 真实道路测试效率低下，每天仅能积累几十公里有效数据，无法满足深度学习需求。\n- 缺乏多车交互环境，无法模拟复杂交通流中的车辆博弈与协同驾驶逻辑。\n- 硬件资源浪费严重，传感器标定和调试需长期占用实车，导致研发进度滞后。\n\n### 使用 simulator 后\n- 在 simulator 中快速构建高保真虚拟城市，一键生成各类极端天气与突发事故场景。\n- 支持大规模并行仿真，单日可积累数万公里的训练数据，测试效率提升数百倍。\n- 内置 ROS\u002FROS2 多机器人通信协议，完美还原多车博弈与协同驾驶的复杂交互。\n- 无需实车即可验证核心代码，大幅降低硬件损耗与测试风险，加速算法迭代。\n\nsimulator 通过高保真虚拟环境，成功将自动驾驶算法的迭代周期从数月缩短至数周。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Flgsvl_simulator_1223a125.png","lgsvl","LG Silicon Valley Lab","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Flgsvl_607056be.png","",null,"svlsimulator","https:\u002F\u002Fwww.svlsimulator.com\u002F","https:\u002F\u002Fgithub.com\u002Flgsvl",[84,88,92,96,100,104,107,111,115,118],{"name":85,"color":86,"percentage":87},"C#","#178600",85.3,{"name":89,"color":90,"percentage":91},"HLSL","#aace60",9.4,{"name":93,"color":94,"percentage":95},"ShaderLab","#222c37",3.6,{"name":97,"color":98,"percentage":99},"C","#555555",1,{"name":101,"color":102,"percentage":103},"GLSL","#5686a5",0.2,{"name":105,"color":106,"percentage":103},"Go","#00ADD8",{"name":108,"color":109,"percentage":110},"Shell","#89e051",0.1,{"name":112,"color":113,"percentage":114},"C++","#f34b7d",0,{"name":116,"color":117,"percentage":114},"Dockerfile","#384d54",{"name":119,"color":120,"percentage":114},"Batchfile","#C1F12E",2439,790,"2026-04-02T08:37:31","NOASSERTION","Windows, Linux","需要 NVIDIA GPU，推荐 GTX 1080，显存 8GB，CUDA 版本未说明","未说明",{"notes":129,"python":127,"dependencies":130},"1. 项目已于 2022 年 1 月停止活跃开发，仅保留源码；2. 最新版本（2021.3）需连接 WISE 云服务下载资产和配置；3. 源码构建需使用 Unity Editor；4. Windows 运行性能优于 Linux；5. macOS 未提及支持",[],[15,13,53,14,51,54],[67,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151],"unity","game-engine","autonomous","self-driving-car","csharp","3d","machine-learning","tensorflow","api","unreal-engine","carla","airsim","artificial-intelligence","computer-vision","deep-learning","reinforcement-learning","autoware","baidu","ros",7,"2026-03-27T02:49:30.150509","2026-04-06T05:35:32.407732",[156,161,166,171,176,181],{"id":157,"question_zh":158,"answer_zh":159,"source_url":160},2469,"开发者模式下集群主节点连接失败怎么办？","检查 Windows 防火墙的高级安全设置。确保没有阻止当前运行的 Unity Editor 版本的入站规则（Inbound Rules）。清除阻止规则通常可以解决远程客户端无法连接到 Editor 作为主节点的问题。","https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fissues\u002F1567",{"id":162,"question_zh":163,"answer_zh":164,"source_url":165},2470,"在 Unity 中构建模拟器时遇到错误且无法启动怎么办？","检查 Unity 编辑器的控制台设置，可能开启了“暂停于错误”（Pause on Errors）。关闭该设置或确保正确按下播放按钮（Play）即可解决。如果按了播放键后游戏编辑器处于暂停状态，请取消暂停。","https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fissues\u002F1547",{"id":167,"question_zh":168,"answer_zh":169,"source_url":170},2471,"如何在 LGSVL 中添加自定义回调以响应特定传感器数据？","可以在模拟器端创建传感器插件（Sensor Plugin），接收来自 Dreamview 的回调，然后发送自定义 API 回调或发布 Topic。参考官方文档了解如何创建传感器插件，并使用 Unity API（如射线检测或测量距离到 NPC）来获取结果并输出到 Topic 或可视化方法。","https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fissues\u002F1211",{"id":172,"question_zh":173,"answer_zh":174,"source_url":175},2472,"添加行人（Pedestrian）代理时报错或找不到资源包如何解决？","行人包含在同一个二进制文件中，只需从该二进制文件移动到对应的文件夹即可。如果是 NPC 资源包问题，需确认 Assets\u002FExternal\u002FNPCs 下是否有 DefaultNPC 文件夹，并确保模拟器构建文件夹的 AssetBundles 中包含 NPCS 文件夹。","https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fissues\u002F1246",{"id":177,"question_zh":178,"answer_zh":179,"source_url":180},2473,"机器人车轮位置不正确或碰撞体偏移如何处理？","检查车轮碰撞体（wheel colliders）的位置。1) 将 wheels_col 游戏对象的本地位置归零；2) 然后将车轮碰撞体定位到车轮的实际位置。确保 pivot points 在 Unity 中的变换位置正确。","https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fissues\u002F198",{"id":182,"question_zh":183,"answer_zh":184,"source_url":185},2474,"模拟运行时出现卡顿或延迟严重的原因及解决方法？","可能是网络延迟导致广播信息慢（特别是跨地域运行）。建议将模拟器运行在台式机，Apollo 运行在笔记本上，或者反之。优化硬件配置（如 CPU、GPU）也能改善感知激活时的卡顿问题。","https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Fissues\u002F1311",[187,192,197,202,207,212,217,222,227,232,237,242,247,252,257,262,267,272,277,282],{"id":188,"version":189,"summary_zh":190,"released_at":191},102009,"2021.1.1","**Note:** If you are cloning our repository to work with the source code for this release, please make sure to clone the release-2021.1 branch and NOT master.\r\n\r\n### Added\r\n - [3D Visualizer](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Flibrary#interacting-with-the-visual-editor) to help create sensor configuration on a vehicle\r\n - [HD map visualizer](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Flibrary#previewing-the-hd-map) on map profile pages\r\n - Ability to share test reports with other users\r\n - \"Supported Simulator versions\" value on asset profile page\r\n - Improved [sharing](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fsharing) feature for private assets and simulations\r\n - Save and Exit button on sensor configuration page\r\n - Tutorials to help new users on how to interact with the web user interface pages\r\n - Email confirmation upon sensor plugin sharing\r\n\r\n### Changed\r\n - Improved quick filters on Store and Library pages\r\n - Redirect to existing asset profile page when uploading an already uploaded asset\r\n - Request access button on private plugin pages\r\n - Require adding a vehicle sensor configuration when creating a simulation\r\n - Fixed issues with multi-vehicle simulation using same vehicle and sensor configuration\r\n - Improvements to cluster page user experience\r\n - Show proper names for missing sensors on invalid simulations\r\n - Proper error messages for wrong information on registration page\r\n - Proper error messages when maximum allowed cluster limit is reached\r\n","2021-05-21T17:26:55",{"id":193,"version":194,"summary_zh":195,"released_at":196},102010,"2021.1","### Added\r\n - New cloud-based [web user interface](https:\u002F\u002Fwise.svlsimulator.com\u002F) including:\r\n\t- [Asset Store](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Fstore) for downloading assets, uploading and sharing assets publicly\r\n\t- user account password management\r\n\t- user assets management [library](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Flibrary)\r\n\t- support for private assets\r\n\t- private assets\u002Fsimulations sharing with registered users\r\n\t- cluster\u002FSimulation status handling\r\n\t- SVL Simulator content from this release will be available in the [Asset Store](https:\u002F\u002Fwise.svlsimulator.com\u002Fmaps\u002Fpublic)\r\n - New and updated [runtime templates](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Frunning-simulations\u002Fruntime-templates) for simulations with automatic bringup and execution:\r\n\t- Random Traffic\r\n\t- Visual Scenario Editor\r\n\t- Python API\r\n\t- API Only\r\n - [Visual Scenario Editor](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fcreating-scenarios\u002Fvisual-scenario-editor) for creating scenarios including support for:\r\n\t- traffic vehicle and pedestrian waypoints\r\n\t- previews\r\n\t- copy\u002Fpaste\u002Fundo feature\r\n\t- ability to specify ego vehicle target destination\r\n\t- support for controllables with ability to edit default policy\r\n\t- color selection for actors\r\n\t- waypoint positions snapped to HD map lanes\r\n\t- support for distance, time, and time-to-collision triggers\r\n\t- traffic lights control\r\n - Automatically generated [test case reports](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Ftest-results) of simulations including:\r\n\t- success\u002Ffailure scenario evaluation\r\n\t- simulation statistics\r\n\t- analytics data per sensor\r\n\t- video recording of simulation\r\n\t- multiple violation event detection: collision, stopline, stopsign, ego-stuck, sudden jerk\u002Fbrake\u002Fturn, speed-limit, etc.\r\n - PythonAPI: many improvements including:\r\n\t- added cloudiness and road damage to weather parameters\r\n\t- ability to specify date in environment configuration\r\n\t- added [Dreamview API](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fpython-api\u002Fdreamview-api) as sub-module\r\n\t- added callback agents_traversed_waypoints\r\n\t- added ability to set speed at WalkWaypoints\r\n\t- added waypoint trigger system\r\n\t- ability to set simulator camera free-state position and rotation\r\n\t- sample Python API [scripts](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Frunning-simulations\u002Fapi-how-to-run-scenario) based on NHTSA-defined scenarios for end-to-end testing\r\n\t- additional Python API test samples: random-traffic mode, cut-in, sudden-braking, etc.\r\n - Environment configuration improvements:\r\n\t- moon position in nighttime environment configurations\r\n\t- Improved environment road wetness layer\r\n\t- UI for FPS and SIM time\r\n\t- Improved rain particles\r\n\t- Increased types of traffic lights, model improvements\r\n - Improvements in [Developer Mode](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Frunning-simulations\u002Fdeveloper-mode):\r\n\t- developer settings to use ego vehicle within Developer Mode\r\n\t- ability to select and add actors to simulation in Developer Settings\r\n\t- added sensor debug mode\r\n\t- added tool to rotate Editor scene view to -X north\r\n - Features for traffic agents in simulation:\r\n\t- support for bicyclist traffic agents\r\n\t- support for custom [traffic vehicle behavior plugins](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fplugins\u002Fnpc-plugins)\r\n\t- pedestrian crosswalk support with yield for traffic vehicles (SanFrancisco map)\r\n\t- added direction for pedestrian crosswalk annotation tool\r\n\t- spawning NPCs now raycasts target bounds from egos' positions\r\n - New map\u002Fenvironment creation improvements:\r\n\t- default ego [destination points](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fadd-destinations) for LG-provided maps\r\n\t- HD map road network [environment generation tool](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fhd-map-mesh-generation)\r\n\t- [test maps](https:\u002F\u002Fwise.svlsimulator.com\u002Fmaps\u002Fpublic?search=API) for NHTSA-like test cases: Straight1LanePedestrianCrosswalk, Straight1LaneSame, etc.\r\n - General simulation improvements:\r\n\t- ability to create and run a [Distributed Simulation](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fdistributed-simulation\u002Fdistributed-simulation-introduction) from web user interface\r\n\t- [offline mode](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Frunning-simulations\u002Foffline-mode) for running saved simulation configurations\r\n\t- improved cache control for downloaded assets\r\n - Sensors improvements:\r\n\t- [new sensors](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fsensors-list): StopLine, HUDKeyboardControl, AutowareAIControl, LGSVLControl, etc.\r\n\t- improved  LiDAR simulation performance\r\n\t- sun-flare, raindrops, greyscale, and video artifacts [effects](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fsensors-list#color-camera) for sensors\r\n\t- support for sensor post-distortion effects\r\n\t- Default values for simple and complex sensor parameter types\r\n\t- Enabled sensors to load texture assets\r\n - Improvements around support for AD stacks:\r\n\t- Optimized [ROS2 interface and bridge](https:\u002F\u002Fwww.svlsi","2021-03-23T23:54:37",{"id":198,"version":199,"summary_zh":200,"released_at":201},102011,"2020.06","If you are cloning our repository to work with the source code for this release, please make sure to clone the `release-2020.06` branch and NOT `master`.\r\n\r\n### Added\r\n - Support [modular testing](https:\u002F\u002Fwww.lgsvlsimulator.com\u002Fdocs\u002Fmodular-testing) of planning with Apollo 5.0\r\n - Bridge plugin system with example ([LoggingBridge](https:\u002F\u002Fgithub.com\u002Flgsvl\u002FLoggingBridge))\r\n - Added default [ultrasonic distance sensor](https:\u002F\u002Fwww.lgsvlsimulator.com\u002Fdocs\u002Fsensor-json-options#ultrasonic)\r\n - Sensor TF visualizer in [sensor visualizations](https:\u002F\u002Fwww.lgsvlsimulator.com\u002Fdocs\u002Fsensor-visualizers)\r\n - Added button in [map annotation tool](https:\u002F\u002Fwww.lgsvlsimulator.com\u002Fdocs\u002Fmap-annotation) to add synthetic lane boundary lines automatically\r\n - Python API: added callback agents_traversed_waypoints\r\n - Python API: added ability to set speed at WalkWaypoints\r\n - Python API: Added waypoint trigger system\r\n\r\n### Changed\r\n - Fixed 90 degree orientation offset in GPS odometry sensor\r\n - Replaced default ROS2 bridge to improved [custom ROS2 bridge](https:\u002F\u002Fwww.lgsvlsimulator.com\u002Fdocs\u002Fros2-bridge) instead of ros2-web-bridge\r\n - Unity update to 2019.3.15f1\r\n - Fixed timestamps in GPS, IMU\r\n - Added timestamp to default LiDAR sensor PointCloud message\r\n - Fixed bugs in OpenDrive map importer to correctly compute reference lines and lane widths for edge cases\r\n - Improved OpenDrive map exporter to export parametric cubic curves instead of simple lines for each reference line segment\r\n","2020-08-31T23:39:55",{"id":203,"version":204,"summary_zh":205,"released_at":206},102012,"2020.05","If you are cloning our repository to work with the source code for this release, please make sure to clone the `release-2020.05` branch and NOT `master`.\r\n\r\n### Added\r\n - Support for custom [traffic vehicle behavior plugins](https:\u002F\u002Fwww.lgsvlsimulator.com\u002Fdocs\u002Fnpc-plugins\u002F)\r\n - Support for [Apollo 5.5](https:\u002F\u002Fwww.lgsvlsimulator.com\u002Fdocs\u002Fapollo-master-instructions\u002F) ([latest master](https:\u002F\u002Fgithub.com\u002FApolloAuto\u002Fapollo\u002Ftree\u002Fmaster))\r\n - Support for distributed simulation\r\n - Velodyne VLS-128 support\r\n - Python API function to spawn random non-ego vehicles and pedestrians\r\n - Unlit shadows support for point cloud environment rendering\r\n - AD system-agnostic message definitions to \"lgsvl_msgs\" for vehicle control, CAN bus and status data, etc.\r\n\r\n### Changed\r\n - Refactored traffic agent Waypoint Mode with fixes for idle and trigger waypoints\r\n - Changed gnss_odom message coordinate system to right-handed coordinate system\r\n - Fixed \"ignore map origin\" option for gnss_odom message\r\n - Fixed acceleration values in IMU sensor\r\n - Fix sky flickering issue during point cloud rendering\r\n - Fixed LiDAR readback error\r\n - Removed and replaced documentation source files from main repository to separate Documentation [repository](https:\u002F\u002Fgithub.com\u002Flgsvl\u002FDocumentation)","2020-06-04T01:10:04",{"id":208,"version":209,"summary_zh":210,"released_at":211},102013,"2020.03","If you are cloning our repository to work with the source code for this release, please make sure to clone the `release-2020.03` branch and NOT `master`.\r\n\r\n### Added\r\n- Velodyne VLP-16 and VLP-32C support through custom LiDAR sensor plugin\r\n- Support for LiDAR sensor plugin with direct UDP socket interface\r\n- Support for point cloud environment rendering\r\n- Extensible vehicle dynamics\r\n- Functional Mockup Interface 2.0 (FMI 2.0) interface for vehicle dynamics\r\n- Support for fisheye camera lens distortion\r\n- Support for sensor_msgs\u002FNavSatFix message type for GPS messages in ROS2\r\n- Vehicle Odometry sensor for reporting steering angles and velocity in ROS2\r\n\r\n### Changed\r\n- Upgraded to Unity 2019.3.3f1\r\n- Fixed black artifacts in Linux bug\r\n- Fixed display issues in Unity Editor bug\r\n- Fixed camera sensor invalid data bug\r\n- 3D Ground Truth sensor now generates different ID for vehicle after each respawn\r\n- Fixed orientation misalignment and missing fields in IMU messages","2020-04-18T00:45:59",{"id":213,"version":214,"summary_zh":215,"released_at":216},102014,"2020.03-rc1","Check official release notes here: https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Ftag\u002F2020.03","2020-04-08T03:06:21",{"id":218,"version":219,"summary_zh":220,"released_at":221},102015,"2020.01","**New Plugin** - [TrafficCone](https:\u002F\u002Fgithub.com\u002Flgsvl\u002FTrafficCone) Controllable Object\r\n\r\n### Added\r\n - Controllable Object plugin support, dynamically add and control Controllables with the Python API\r\n - Ability to create [LIDAR sensor](https:\u002F\u002Fwww.lgsvlsimulator.com\u002Fdocs\u002Fsensor-json-options\u002F#lidar) with non-uniform beam distribution\r\n - Ability to add distortion effects to [Camera sensors](https:\u002F\u002Fwww.lgsvlsimulator.com\u002Fdocs\u002Fsensor-json-options\u002F#color-camera)\r\n - Support for Autoware.Auto messages (ROS2)\r\n - Ability to create custom message types for sensor plugins\r\n - TransformSensor which can act as a parent for other sensors\r\n - VehicleStateSensor which is needed by Autoware.Auto\r\n\r\n### Changed\r\n - Added SanFrancisco map as a default map option\r\n - Allow null texture bundles without an error\r\n - Pedestrian mass reduced to 70kg. Merged #583 \r\n - Fixed lagging of 2D Ground Truth boxes (in visualization and data)\r\n - ComfortSensor included with Simulator binary\r\n - TrafficCone included with Simulator binary\r\n - Fixed exported HD map lane relations\r\n - Fixed ROS2 GPS","2020-02-12T02:21:31",{"id":223,"version":224,"summary_zh":225,"released_at":226},102016,"2020.01-rc1","Check official release notes here: https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Ftag\u002F2020.01","2020-02-04T01:22:40",{"id":228,"version":229,"summary_zh":230,"released_at":231},102017,"2019.12","**New environment** - added [San Francisco, CA](https:\u002F\u002Fcontent.lgsvlsimulator.com\u002Fmaps\u002Fsanfrancisco\u002F).\r\n\r\n### Added\r\n - Custom callback for Python API, useful in sensor plugins.\r\n - Ability to specify count and types of NPCs to spawn on the map.\r\n\r\n### Changed\r\n - Optimized texture usage in maps - significantly reduces size on disk and GPU memory used.\r\n - Allow boundary type to be optional for Apollo HD map import.\r\n - Fix Python API to be able load maps & vehicles that are shared between multiple users.\r\n - Separated bundle file format version for map and vehicle bundles.\r\n - Improved headlights for EGO vehicles.\r\n - Improved HD map annotation icons.\r\n - Fixed Sedan NPC mesh.\r\n","2020-01-18T02:05:53",{"id":233,"version":234,"summary_zh":235,"released_at":236},102018,"2019.12-rc1","Check official release notes here: https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Ftag\u002F2019.12","2019-12-27T02:10:41",{"id":238,"version":239,"summary_zh":240,"released_at":241},102019,"2019.11","### Added\r\n - **Important** - map and vehicle bundle format changed. You'll need to rebuild or redownload existing bundles.\r\n - New environment - [GoMentum Station](https:\u002F\u002Fcontent.lgsvlsimulator.com\u002Fmaps\u002Fgomentum\u002F) at Concord, CA.\r\n - OpenDrive 1.4 HD map import.\r\n - Rain drops on ground when it is raining.\r\n - Separated Apollo HD map export between version 3.0 and 5.0 to support 5.0 specific features.\r\n - Cache vehicle prefabs when loading same vehicle multiple times into simulation.\r\n - Ability to login to account via command-line.\r\n - Ability for vehicle to have multiple interior lights. Fixes #474.\r\n - Allow Color, Depth and Semantic cameras to have higher capture & publish rate.\r\n - Building & loading custom sensors as plugins.\r\n\r\n\r\n### Changed\r\n - Fixed traffic lights signal colors on Shalun map.\r\n - Fixed exceptions when NPCs are despawned while still in intersection.\r\n - Fixed errors when adding pedestrian to map without NavMesh.\r\n - Fixed Lanelet2 boundary import and export.\r\n - Multiple fixes for OpenDrive import and export.\r\n - Fixed wrong raycast layers in 2D Ground Truth sensor to detect if NPC is visible.\r\n - Fixed missing timestamp when publishing ROS\u002FCyber messages from 2D Ground Truth sensor.\r\n - Limit number of spawned NPCs and vehicles for large maps.\r\n\r\n对于中国的用户，您可以从[百度网盘](https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1M33ysJYZfi4vya41gmB0rw)（提取码: 6k91）下载使用我们的仿真器。\r\n","2019-12-03T22:54:59",{"id":243,"version":244,"summary_zh":245,"released_at":246},102020,"2019.11-rc1","Check official release notes here: https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Ftag\u002F2019.11","2019-11-21T21:41:26",{"id":248,"version":249,"summary_zh":250,"released_at":251},102021,"2019.10","# Added\r\n - Apollo HD map import\r\n - Accurate sun position in sky based of map location. Including time of sunrise and sunset.\r\n - [Control calibration sensor](https:\u002F\u002Fwww.lgsvlsimulator.com\u002Fdocs\u002Fsensor-json-options\u002F#control-calibration) to help calibrating AD stack control.\r\n - Ported Shalun map from previous non-HDRP simulator version.\r\n - Ground Truth sensor for traffic light.\r\n - Python API method to get controllable object by position.\r\n - Python API method to convert multiple map coordinates in single call.\r\n - Python API method to perform multiple ray-casts in single call.\r\n - Sensor for controlling vehicle with [steering wheel](https:\u002F\u002Fwww.lgsvlsimulator.com\u002Fdocs\u002Fsensor-json-options\u002F#wheel-control) (Logitech G920).\r\n - Platform independent asset bundles (Windows and Linux).\r\n - Allow to set custom data path for database and downloaded bundles.\r\n - Visualize data values for non-image senors (GPS, IMU, etc).\r\n - Populate scene with required objects when new scene is created in Unity Editor.\r\n\r\n\r\n# Changed\r\n - Fixed exceptions in ROS Bridge where if it receives message on topic that it has not subscribed.\r\n - Fixed 3D Ground Truth sensor to report correct NPC orientation angles.\r\n - Fixed Radar sensor to visualize pedestrians.\r\n - Fixed Color camera to render mountains in BorregaAve.\r\n - Fixed EGO vehicle collision callback to Python API.\r\n - Fixed WebUI redirect loop that happens if you are logged out.\r\n - Fixed reported NPC vehicle speed. Fixes #347 and #317.\r\n - Fixed gear shifting for EGO vehicle control. Fixes #389.\r\n - Fixed NPC waypoint following where NPCs stopped if assigned speed is too low.\r\n - Fixed semantic segmentation for vehicles and pedestrians added with Python API.\r\n - Fixed ROS2 message publishing (seq field was missing in Header). Fixes #413.\r\n - Fixed issue with database on some non-English locales. Fixes #381.\r\n - Fixed point cloud generation in Unity Editor.\r\n - Fixed browser loosing cookie when session ends in WebUI.\r\n - Fixed slowness in Python API when running without access to Internet.\r\n - Fixed issue when multiple users could not use same map url.\r\n - Improved error messages when simulation fails to start.\r\n\r\n\r\n对于中国的用户，您可以从[百度网盘](https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1M33ysJYZfi4vya41gmB0rw)（提取码: 6k91）下载使用我们的仿真器。\r\n","2019-11-01T22:25:01",{"id":253,"version":254,"summary_zh":255,"released_at":256},102022,"2019.10-rc1","Check official release notes here: https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Ftag\u002F2019.10","2019-10-29T01:35:37",{"id":258,"version":259,"summary_zh":260,"released_at":261},102023,"2019.09","# Added\r\n - Sensor visualization UI\r\n - HD map export to [OpenDrive](http:\u002F\u002Fwww.opendrive.org) 1.4 format\r\n - ROS service support for ROS bridge\r\n - Python API to support more robust waypoints for NPC vehicles\r\n - Python API with ability to control traffic lights on map\r\n - [Hyundai Nexo](https:\u002F\u002Fcontent.lgsvlsimulator.com\u002Fvehicles\u002Fhyundai2018nexo\u002F) vehicle\r\n\r\n# Changed\r\n - Improved NPC movement and right turns on red traffic light\r\n - Fixed NPC vehicle despawning logic so they don't get stuck in intersections\r\n - Change NPC vehicles colliders from box to mesh to improves collision precision\r\n - Updated generated protobuf message classes for latest Apollo 5.0\r\n - Fixed 3D Ground Truth message type for ROS\r\n - Fixed 3D and 2D Ground Truth bounding box locations\r\n\r\n对于中国的用户，您可以从[百度网盘](https:\u002F\u002Fpan.baidu.com\u002Fs\u002F1M33ysJYZfi4vya41gmB0rw)（提取码: 6k91）下载使用我们的仿真器。\r\n","2019-09-12T21:59:57",{"id":263,"version":264,"summary_zh":265,"released_at":266},102024,"2019.09-rc1","Check official release notes here: https:\u002F\u002Fgithub.com\u002Flgsvl\u002Fsimulator\u002Freleases\u002Ftag\u002F2019.09","2019-09-06T21:58:19",{"id":268,"version":269,"summary_zh":270,"released_at":271},102005,"2021.3","### Added\r\n- Content creation:\r\n    - [Annotation size](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fmap-annotation) support\r\n    - Map preview option can be set by user \r\n    - [SDF importer](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fsdf-import) and STL fixes and improvements\r\n    - [Lighting for indoor](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Flighting-for-interiors) environments\r\n    - [Rain colliders](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fadd-new-map#adding-rain-colliders) for indoor environments\r\n    - New indoor environments with [costmaps](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Ftutorials\u002Frobotics-mapping): [Warehouse](https:\u002F\u002Fwise.svlsimulator.com\u002Fmaps\u002Fprofile\u002F903118ab-7246-48a9-81a4-1be3eca5121f), [WarehouseDT](https:\u002F\u002Fwise.svlsimulator.com\u002Fmaps\u002Fprofile\u002Fb0881caf-2727-4cb6-abe7-0f47a27899ea)\r\n    - Add map support for NavOrigin\r\n- Sensors:\r\n    - Sensors support multiple data feeds, e.g. [RealSenseSensor]( https:\u002F\u002Fwise.svlsimulator.com\u002Fplugins\u002Fprofile\u002Faf45d8d4-f5e3-11eb-a493-93b6d1b3c480)\r\n    - [Async GPU readback](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Fsystem-under-test\u002Fsensor-message-publishing) support for Lidar, DirectionalLidar, VelodyneLidar for performance boost\r\n    - LaserScan support for [Lidar2D](https:\u002F\u002Fwise.svlsimulator.com\u002Fplugins\u002Fprofile\u002F2392cabf-47b4-4410-bd81-37545b78feca)\r\n    - 2D\u002F3D Ground Truth sensor accuracy improvements\r\n    - New sensors: [Lidar2DSensor](https:\u002F\u002Fwise.svlsimulator.com\u002Fplugins\u002Fprofile\u002F2392cabf-47b4-4410-bd81-37545b78feca), [DestinationSensor](https:\u002F\u002Fwise.svlsimulator.com\u002Fplugins\u002Fprofile\u002F3f1db91f-4eed-43b2-99ed-c78c129d6aa1), [IntelRealSense](https:\u002F\u002Fwise.svlsimulator.com\u002Fplugins\u002Fprofile\u002Faf45d8d4-f5e3-11eb-a493-93b6d1b3c480)\r\n- Agents:\r\n    - NPCManager extension for creating complex NPC behaviors like [Parking]( https:\u002F\u002Fgithub.com\u002Flgsvl\u002FBehavioursNPC\u002Ftree\u002Fmaster\u002FNPCParkingBehaviour)\r\n    - NPC support customized rigidbody and wheel collider settings: F1Tenth\r\n    - New pedestrian models: See [VRU\u002FWalkers: Jun, Yun](https:\u002F\u002Fgithub.com\u002Flgsvl\u002FWalkers)\r\n- General:\r\n    - Loaded Assets main menu option for assets in memory\r\n    - [Docker support](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Finstallation-guide\u002Finstalling-simulator#docker) for enabling scenario runners on windows\r\n    - Console for Docker logs\r\n    - Graphics setting menu\r\n    - Main Menu simulator\u002Funity\u002FwebUrl display for debugging\r\n    - Added TargetGear for Autoware Auto reverse driving\r\n- Visual scenario editor:\r\n    - Ego Lane Following feature for VSE playback\r\n    - Support for the BezierSpline paths in the waypoints\r\n    - Support for the NavOrigin\r\n    - Added acceleration support for agents' waypoints\r\n- Python API:\r\n    - Add Python API commands for Destination sensor\r\n    - API function to set\u002Fget NavOrigin in\u002Ffrom scene\r\n    - API versioning support\r\n- Web user interface:\r\n    - [Local Automation](https:\u002F\u002Fsvlsimulator.com\u002Fdocs\u002Frunning-simulations\u002Flocal-automation) support\r\n    - Local automation API token access token creation, listing, and deletion in User Profile page\r\n    - Added preservation of the order of sensors in a sensor configuration\r\n    - Added 'Add to Library' modal preview\r\n    - Added preview images for private asset links in Skype, Facebook, LinkedIn, etc.\r\n    - Added preview images for Simulation links in Skype, Facebook, LinkedIn, etc.\r\n    - Implemented accurate trending algorithm\r\n    - 'Draft' feature for Simulation creation page\r\n    - Improved Simulations gallery loading performance\r\n\r\n### Changed\r\n- Moved simulator input actions to sensor bundles\r\n- Visual scenario editor:\r\n    - Smoother agent rotation while in playback mode\r\n    - Fix for editing controllables policy and resetting map signals policies\r\n- Miscellaneous Github issue fixes:\r\n    - API connection fixes\r\n    - Bridge connection fixes\r\n    - Custom Bridge fixes\r\n    - Point Cloud renderer fixes \r\n    - Add checks for pedestrian and traffic annotation for api random agents\r\n    - Development Settings fixes and improvements. Supports cloud assets\r\n    - Import HDMap tool fixes\r\n    - BaseLink fixes\r\n    - Radar velocity fix\r\n    - Build asset fixes\r\n    - NPC segmentation id issues in API\r\n    - Fixed OpenDrive MapOrigin export logic\r\n    - Fix export point cloud feature in simulator editor. Requires latest Lidar Sensor\r\n    - OpenDrive, Apollo Lane, Sign and Signal IDs import & export\r\n    - Refresh cached sims on deleted asset\r\n    - NPC\u002FPedestrian pool no longer removes existing agents\r\n    - Fixed NPC controller stopping all coroutines on the initialization\r\n    - Fix for Input package error on lost focus\r\n    - Correct name of Cyber bridge asmdef file\r\n    - Fixed initializing spawns manager if there are no active agents\r\n    - Bridge client watchdog coroutine\r\n    - Fix lighting on API agent spawn\r\n    - Removed NavSystem from pedestrian waypoint behavior\r\n    - Fixed invariant float and double parameters in NMEA\r\n    - Fixed SF, Shalun, Highway101 map origin rotation issues\r\n- Package updates:\r\n ","2021-10-04T19:40:16",{"id":273,"version":274,"summary_zh":275,"released_at":276},102006,"2021.2.2","### Added\r\n - Support for indoor robotics and Nav2 [navigation stack](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Ftutorials\u002Frobotics-ros2.md)\r\n - Sample indoor environment for robots: [LGSeocho](https:\u002F\u002Fwise.svlsimulator.com\u002Fmaps\u002Fprofile\u002F26546191-86e8-4b53-9432-1cecbbd95c87)\r\n - Sample two-wheel drive robot model: [LGCLOi](https:\u002F\u002Fwise.svlsimulator.com\u002Fvehicles\u002Fprofile\u002F20609b67-6dbd-40ad-9b46-e6bc455278ed)\r\n - [DifferentialDriveControl](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fdifferential-drive-control) sensor to control two-wheel drive robots in ROS\u002FROS 2\r\n - Support for Unity's ArticulationBody for ego vehicles (robot models)\r\n\r\n### Changed\r\n - Fixed error reporting for bridge connection\r\n - Fixed baselink offset in sensor visualizer for sensor configurations\r\n - Added Development as version for custom builds or when running in Developer Mode\r\n - Fixed NPC vehicle and pedestrian spawn position issue","2021-08-19T18:33:27",{"id":278,"version":279,"summary_zh":280,"released_at":281},102007,"2021.2.1","### Changed\r\n - Reduce duplicate bridge messages by only loading one bridge in Developer Mode\r\n - Add log about which assembly a sensor was loaded from to help debug bridges\r\n - Create folder when [user defined data directory path](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fconfig-and-cmd-line-params#command-line-parameters) points to absent folder (not recursively)\r\n - Update default data folder name to **“SVLSimulator-\\\u003Cversion\\>”**\r\n - Fix empty version issue by providing fallback simulator version\r\n - Fix to allow different versions of simulator to connect to [cloud](https:\u002F\u002Fwise.svlsimulator.com)\r\n - Support bridge type attribute in manifest \r\n - Remove error when disconnecting from [cloud](https:\u002F\u002Fwise.svlsimulator.com) (WebException: task was cancelled)","2021-07-26T12:22:39",{"id":283,"version":284,"summary_zh":285,"released_at":286},102008,"2021.2","Note: If you are cloning our repository to work with the source code for this release, please make sure to clone the release-2021.2 branch and NOT master.\r\n\r\n### Added\r\n\r\n- External [Pedestrians](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fplugins\u002Fpedestrian-plugins) and [NPC](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fplugins\u002Fnpc-plugins) (other traffic vehicles) Support\r\n- New [NPCs](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fplugins\u002Fnpc-plugins) and [Pedestrians](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fplugins\u002Fpedestrian-plugins) like Scooters, Bicyclists and Animals\r\n- External [Bridge](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fplugins\u002Fbridge-plugins) Support\r\n- Multiple simulator asset bundle versions support\r\n- Rain Collision effect\r\n- Support for simulations without EGO (Spectator Ego)\r\n- New “Driver view” camera state\r\n- New API to set simulator camera state\r\n- [Annotation tool](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fmap-annotation) to set accurate values (position, rotation and scale) for MapOrigin\r\n- New “clear cache” option\r\n- Ability to use proxy server for cloud_url in config.yml\r\n- New enhanced web user interface:\r\n    - Improved [visual sensor editor](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Flibrary#interacting-with-the-visual-editor)\r\n    - Ability to clone Sensors in [sensor configuration](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Flibrary#managing-sensor-configurations)\r\n    - User warning messages for privilege based restriction\r\n    - Markdown support for Asset description\r\n\r\n### Changed\r\n\r\n- Unity Upgrade to 2020.3.3f1\r\n    - Revert FBX package to 3.2.1-preview.2\r\n    - Remove overdraw with HDRP flare\r\n- Improved [NPC](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fplugins\u002Fnpc-plugins) handling:\r\n    - Fixed rotating NPC wheels when using NPCWaypointBehaviour\r\n    - Pedestrian ground truth from bounds\r\n- Improvements and bug fixes around [Distributed Simulation](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fdistributed-simulation\u002Fdistributed-simulation-introduction) with multi-ego support:\r\n    - Fixed API mode for distributed simulation on a single machine\r\n    - Fixed pedestrian animations on client machine\r\n    - Improved distributing VehicleActions\r\n    - Support for the ArticulationBody in distributed simulations\r\n    - Improved load balancing of the sensors\r\n- Updated [Sensor](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fsensors-list) support:\r\n    - Fix TF visual and sensor hierarchy\r\n    - update input for g920 wheel for windows\r\n    - Publish camera intrinsic parameters to ROS and ROS2\r\n    - Rework lidar to use cubemap\r\n- Improved lighting and rain:\r\n    - Fix brown lighting\r\n    - Rotate sun and moon to match map rotation\r\n    - Rain collision improvements and fixes\r\n    - Fix overlapping rain chunks\r\n- Enhanced [Visual Scenario Editor](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fcreating-scenarios\u002Fvisual-scenario-editor) support:\r\n    - Minor UX fixes\r\n    - Fixed changing agents' variants\r\n    - Fix issue with agent dropdown not refreshing on click\r\n    - Loading pedestrians from config\r\n- Improvements around [HD Map Mesh Generator](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fsimulation-content\u002Fhd-map-mesh-generation):\r\n    - Improve data handling in HD map mesh builder\r\n    - Erosion and re-leveling for point cloud mesh\r\n- Work in progress improvements on Developer mode:\r\n    - Rework developer settings\r\n    - Bundle version uptick and unity editor check on developer debug mode for bridges\r\n    - Sensor debug developer loading\r\n- More enhanced and user friendly [web user interface](https:\u002F\u002Fwise.svlsimulator.com\u002F):\r\n    - Password Sensitivity improvements\r\n    - [GLTF editor](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Flibrary#interacting-with-the-visual-editor) bug fixes and improvements\r\n    - [HD map preview](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Flibrary#previewing-the-hd-map) improvements\r\n    - Simulation invalid items management\r\n    - [WCAG accessibility](https:\u002F\u002Fwww.w3.org\u002FWAI\u002Fstandards-guidelines\u002Fwcag\u002F) UI compatibility\r\n    - Live [Test Results](https:\u002F\u002Fwww.svlsimulator.com\u002Fdocs\u002Fuser-interface\u002Fweb\u002Ftest-results) view in Simulation Profile\r\n    - Updated algorithm for [Trending](https:\u002F\u002Fwise.svlsimulator.com\u002Fmaps\u002Fpublic\u002Ftrending) assets view\r\n    - Simulation form auto-save\r\n- Misc Improvements:\r\n    - Support default light layers in point cloud renderer\r\n    - Loads assembly with the ego name from asset bundle\r\n    - Added public driver view transform to be set in the Inspector\r\n    - Asmdef added, loader fixed to deal with bundle\u002FWISE name mismatch\r\n    - Loader: improve the error message about BundleFormat\r\n    - Make sure Simulator.Editor.Build.Run exits on any exception\r\n    - Trimming last slash in the cloud url if needed.\r\n    - get full path from data path provided","2021-07-07T21:33:00"]