Cookies help us deliver our services. By using our services, you agree to our use of cookies. Learn more

crowdAI is shutting down - please read our blog post for more information

Learning How to Walk

Reinforcement learning environments with musculoskeletal models



Posted by Zxc_596 about 3 years ago


I noticed that the geometry (at least for visualization) seems to be incorrect. I am not sure if this affects the calculation or not. What I noticed is that the geometry for left and right femur are the same:

https://github.com/stanfordnmbl/osim-rl/blob/master/osim/models/Geometry/femur.vtp https://github.com/stanfordnmbl/osim-rl/blob/master/osim/models/Geometry/l_femur.vtp

This can be seen in the attached picture


I assume that this could be fixed by applying a transformation around here or the corresponding part for the other femur…


Another issue I recognized is that somehow, the pelvis position in the observation vector is not in X, Y, Z order but it seems Z, X, Y. Still, the supposed Z position/speed values are quite odd and I am wondering what they really are…

These plus other issues I already described make me doubt the validity model… Could you provide a little more information about this? I would be happy to help and provide fixes but I am yet not sure if I am missing something.


Posted by Lukasz_  about 3 years ago |  Quote

Hi, thanks for pointing that out! It’s indeed an error and we actually have the right geometries, I will try to fix it in the update (since it doesn’t change the competition).

Regarding [Z, X, Y] it is actually [rotation, X, Y] for pelvis. Note that different joints have different degrees of freedom. In particular, only pelvis has X and Y position all the others are rotational.

Thanks for your input and sorry for the late answer,

Best, Łukasz