Open hjsuh94 opened 2 years ago
As we discussed with @pangtao22 and @lujieyang today, a lot of samples currently seem to be wasted on configurations which do not make contact, and therefore have quite degenerate ellipses.
Biasing our samples towards contacting configurations may not necessarily help because the finger really needs to make and break contact through multiple trees in order to successfully rotate the tree.
To address this problem, it now seems inevitable to use some kind of more long-horizon information on the contact configurations. We can either do this with:
which is consistent with our options above.
The third strategy doesn't seem to work too well without investing a lot into engineering issues.
It would seem that we would need a separate motion planner to handle teleporting....
Related / done simultaneously with #27
[ ] Teleport Grasp, Choose Goal, then Trajopt.
[ ] Teleport Grasp, Choose Goal, then Rollout.
[x] Choose Goal, Choose Grasp, then Trajopt.