...
Forward methods, particularly shooting methods and reinforcement learning, can be slow. Direct collocation aims to generate a forward simulation with the speed of inverse methods. It does so by concurrently optimizing the whole motion trajectory and muscle excitations (or other control values). This can speed up the process quite a bit , but intermediate solutions do not satisfy with physical constraints . Physical constraints are satisfied by only at the end of the optimization. While While direct collocation problems have traditionally been challenging to set up and solve, the OpenSim Moco project provides an open-source toolkit to facilitate the use of direct collocation methods in human and animal movement studies.
JEN: I don't think the red text is particularly relevant to users. ... I would instead pull in some text from Chris's paper or cover letter about how direct collocation problems have traditionally been challenging to set-up and solve, but Moco makes this easier. Could also link to their webinar.
JOY: I think the red text is actually critical in the decision-making process of whether to use direct collocation. It's also included in the comparison table above, but I think it is important to reiterate here. I did add in the language you provided. Moco is already linked to the Moco website, which embeds the webinar.
| Anchor | ||||
|---|---|---|---|---|
|
...