ABR Control supports Mujoco!

https://github.com/abr/abr_control

And it has for a while, actually. ‘Oh great’, you may be thinking, ‘but I can never afford the Mujoco license, I’m not a tenured professor!’

Well fear not, friends! Mujoco recently became free for all to use! You can now download their public license and be on your merry way. The associated downside is there’s also no more official support from Dr. Emo Todorov for paid subscribers on the forum. This, I’m sure, is unrelated to my barrage of questions over the years (really I’ve only posted 6 times so it actually probably is unrelated…probably).

And ABR Control has all your favorite examples written up for Mujoco! We’ve got the all the classics:

• operational space position control,
• operational space orientation control,
• operational space position AND orientation control,
• nonlinear adaptive control,
• control of a ball joint arm,
• path planning with force control,
• path planning with inverse kinematics,
• and many more!

You can find the full set of examples in the docs/examples folder of the repository.

If you’re not familiar with Mujoco, I highly recommend checking it out. What’s extra nice about Mujoco is that all of the simulation information used to compute the forward dynamics is available (we access it using the mujoco-py package through our mujoco interface file), which means our control is exact. For simulators like CoppelliaSim we don’t have access to this information, so we’re calculating the values ourselves, and there’s often a slight discrepancy. With Mujoco, however, if you set up a floating controller you can bet your bottom dollar that arm will float.

The other benefit of Mujoco, of course, is that it’s super fast, and handles contact dynamics well. Great for robotics applications. Also the visualizations are really slick:

The operational space position and orientation controller running with the path planner running with the Jaco2 arm from Kinova model. The red rectangle is the final target, and the blue rectangle is the path planner target.

I’m very excited that the Mujoco license is free, and I encourage everyone to download it and start playing around. It’s by far the best robotics simulator I’ve used, and it runs fast enough that you can use it to calculate everything you need for controlling a physical robot arm as well (which we’ve also done with the above Jaco2 arm)! The Jaco2, UR5, and a simple geometric arm are included in the ABR Control package, and if you want to have your own arm in there you can follow this previous post about how to build your own model.

Advertisement