Alexander Winkler

The joint angles are not in the walking bag data (mostly because joint angles are not part of the optimization, only endeffector positions). The visualization is performed by doing inverse...

Hi! Thanks for pointing this out. I have not experienced this issue, but let me know if you figure anything out!

Hi Roberto! I think this is very interesting direction to explore 👍 I'm suspecting there are some conflicting constraints at work here, which make it hard for the solver to...

Okey, thanks for clarifying the NLP layout and I see you already tried the above. So you have some redundant variables you're optimizing over (joint torques vs foot forces &...

You could increase the height of the range of motion constraint (blue boxes around the legs), which might cause the legs to be lifted higher (but not enforced). That's probably...

Hi Henrique! Currently the total time `t_total `is _not_ a decision variable nor a constraint. It's set at the start (hard parameterization). With that fixed, we have to make sure...

Thanks for following up on this, yeah, i think that's a good idea. I'll see if I find time to look at this during the weekend. My first thought is,...

Thanks for that input Remo!🙂

I added most of the elements above (see https://github.com/leggedrobotics/xpp/tree/anymal_integration) and also adapted the towr repo as you suggested (https://github.com/ethz-adrl/towr/tree/anymal_integration). Will merge once the IK is fixed. I didn't have time...

No, no plans for that unfortunately. To get this real-time, you would have to call the towr function from C++ in Unreal (so somehow link these external libraries in the...