Drake（中古英语中的“龙”）是一个 C++ 工具箱，由 麻省理工学院计算机科学与人工智能实验室 (CSAIL)的机器人运动小组创建。开发团队现已显着壮大，核心开发由丰田 研究所牵头。它是一组工具，用于分析我们的机器人的动态并为它们构建控制系统，重点强调基于优化的设计/分析。

尽管可用于机器人技术的仿真工具越来越多，但它们中的大多数都像黑匣子一样工作：命令输入，传感器输出。Drake 旨在模拟甚至非常复杂的机器人动力学（例如，包括摩擦、接触、空气动力学……），但始终强调揭示控制方程中的结构（稀疏性、解析梯度、多项式结构、不确定性量化……）和使这些信息可用于高级规划、控制和分析算法。Drake 为 Python 提供了一个接口，以实现新算法的快速原型设计，并且还旨在为许多最先进的算法提供可靠的开源实现。

Drake: Model-Based Design and Verification for RoboticsDrake ("dragon" in Middle English) is a C++ toolbox started by the RobotLocomotion Group at the MIT Computer Science and Artificial IntelligenceLab (CSAIL). The development team has now grown significantly, with coredevelopment led by the Toyota Research Institute. It is a collection oftools for analyzing the dynamics of our robots and building controlsystems for them, with a heavy emphasis on optimization-based design/analysis.https://drake.mit.edu/

 通过 Pip 安装

将 drake 安装到 虚拟环境 目录中。在下面的示例中，我们将命名该目录env，但您可以选择任何名称。

创建一个虚拟环境并安装 Drake：

python3 -m venv env
env/bin/pip install --upgrade pip
env/bin/pip install drake

Drake 需要来自主机 linux 发行版的某些基本运行时库。

对于 Ubuntu 20.04，安装这些附加库：

sudo apt-get install --no-install-recommends \
  libpython3.8 libx11-6 libsm6 libxt6 libglib2.0-0

激活虚拟环境：

source env/bin/activate

C++ API文档

Drake: Main Pagehttps://drake.mit.edu/doxygen_cxx/index.htmlpython API文档

pydrake — pydrake documentationhttps://drake.mit.edu/pydrake/index.htmlGitHub教程

drake/tutorials at master · RobotLocomotion/drake · GitHubModel-based design and verification for robotics. Contribute to RobotLocomotion/drake development by creating an account on GitHub.https://github.com/RobotLocomotion/drake/tree/master/tutorials在 Python 中使用 Drake

Drake: Using Drake from PythonDrake ("dragon" in Middle English) is a C++ toolbox started by the RobotLocomotion Group at the MIT Computer Science and Artificial IntelligenceLab (CSAIL). The development team has now grown significantly, with coredevelopment led by the Toyota Research Institute. It is a collection oftools for analyzing the dynamics of our robots and building controlsystems for them, with a heavy emphasis on optimization-based design/analysis.https://drake.mit.edu/python_bindings.html

Github

RobotLocomotion · GitHubRobotLocomotion has 64 repositories available. Follow their code on GitHub.https://github.com/RobotLocomotion/

MIT Russ Tedrake主页

Robot Locomotion Grouphttp://groups.csail.mit.edu/locomotion/russt.html