Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add support for SE2 poses in Collision2D #278

Merged
merged 6 commits into from
Aug 30, 2022
Merged

Add support for SE2 poses in Collision2D #278

Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
f968fde
Refactored MotionPlanner so that objective can be passed separately.
luisenp Aug 24, 2022
faeb3ae
Changed SE2.xy() to return a Point2 instead of a tensor.
luisenp Aug 25, 2022
f9b79b0
Added support for SE2 in Collision2D.
luisenp Aug 25, 2022
2719173
Minor cleanup in collision jacobians test.
luisenp Aug 26, 2022
8c84a94
Revert notebook changes.
luisenp Aug 26, 2022
d0cba30
SE2.translation is now an alias for SE2.xy().
luisenp Aug 26, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Minor cleanup in collision jacobians test.
  • Loading branch information
@luisenp
luisenp committed Aug 30, 2022
commit 2719173cf915ca9b594061c747ae36a12f8b3f30
8 changes: 2 additions & 6 deletions theseus/embodied/collision/tests/test_collision_factor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,18 +76,14 @@ def test_collision2d_copy():
assert cost_function2.name == "new_name"


@pytest.mark.parametrize("pose_cls", [th.Vector, th.SE2])
@pytest.mark.parametrize("pose_cls", [th.Point2, th.SE2])
def test_collision2d_jacobians(pose_cls):
rng = torch.Generator()
rng.manual_seed(0)
for _ in range(10):
for batch_size in [1, 10, 100]:
cost_weight = th.ScaleCostWeight(torch.ones(1).squeeze().double())
if pose_cls == th.Vector:
pose = th.Point2.randn(batch_size, generator=rng, dtype=torch.float64)
else:
pose = th.SE2.randn(batch_size, generator=rng, dtype=torch.float64)

pose = pose_cls.randn(batch_size, generator=rng, dtype=torch.float64)
origin = th.Point2(torch.ones(batch_size, 2).double())
sdf_data = th.Variable(
torch.randn(batch_size, 10, 10, generator=rng).double()
Expand Down