Drake: Robotics Planning, Control And Analysis Toolbox

From MIT:

Drake ("dragon" in Middle English) is a toolbox maintained by the Robot Locomotion Group at the MIT Computer Science and Artificial Intelligence Lab (CSAIL). It is a collection of tools for analyzing the dynamics of our robots and building control systems for them in MATLAB and C++, with a heavy emphasis on optimization-based design/analysis. Here is a quick summary of capabilities:

Simulation

  • Rigid-body dynamics including contact/collisions (hybrid+LCP) and kinematic loops
  • Basic aerodynamics/fluid dynamics
  • Sensor models (lidar, depth camera, imu, contact force/torque; cameras coming soon)
  • Hand-derived models for many canonical control dynamical systems
  • Easily add your own models/components
  • Some support for stochastic models
  • For all of the above we aim to expose sparsity and provide analytical gradients / symbolic analysis
  • Primary limitations: code is optimized for analysis / planning / control design (as opposed to speed, generality)...

​... Most of these models/tools are described in the companion textbook from an MIT course/MOOC. We've also recently started populating the Drake Gallery (contributions welcome!)... (git repo)

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

 Discover the power of Omron mobile robotics.

Discover the power of Omron mobile robotics.

Our fully autonomous intelligent vehicles will help you to transform the way you move materials and route your workflows. Increase throughput, eliminate material flow errors, improve traceability, maximize flexibility and allow your employees to focus on higher level tasks. Unlike traditional AGV's, our mobile robotics navigate using the natural features of your facility and do not require expensive facility modifications or guidance. Our AIV's can adapt to changes in their environment and work freely and safely with your staff. Our mobile robots are intelligent enough to quickly learn their environment and then automatically find the optimal path to where they need to go. They also automatically make adjust for dynamic environments and can work together in fleets of up to 100 robots.