A post about basic inverse kinematics in mujoco.

[alefram]

I was learning about inverse kinematics and using Mujoco to practice it, so I created a write-up about my experience. Maybe some people can benefit from it. If there are any errors or areas for improvement, please let me know so I can update it. Thanks!

[alefram]

https://alefram.github.io/posts/Basic-inverse-kinematics-in-Mujoco

[yuvaltassa]

This is very nice. One thing I think this is missing is the interactive/smooth setting. It's actually kind or rare that you just want to jump to your desired pose. Usually you want a smooth trajectory that takes you from the current pose to the desired one.

@kevinzakka, you were working a nice interactive inverse kinematics thing, you probably have something to say?

[kevinzakka]

Here's some code: https://github.com/kevinzakka/mjctrl

[alefram]

Thanks @kevinzakka I will check it.

[alefram]

I have updated the post. Thank you for your help. @kevinzakka @yuvaltassa

[alefram]

@yuvaltassa Yeah, I was thinking about including it in this post or another. I am currently checking out the robotics manipulation techniques of Russ Tedrake course to implement it, maybe some control. Do you have any advice?

[yuvaltassa]

My advice is look at @kevinzakka's code 🙂

[songwookim]

@yuvaltassa Yeah, I was thinking about including it in this post or another. I am currently checking out the robotics manipulation techniques of Russ Tedrake course to implement it, maybe some control. Do you have any advice?

Thanks for your post. it was really helpful for me.

[alefram]

@songwookim Thanks I like to share when I learning mujoco, if there is any advice would appreciated.