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.

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

[Feature] Added RGB DP baseline and DrawTriangle/SVG task #876

Merged
merged 21 commits into from
Feb 25, 2025
Merged

Conversation

StoneT2000
Copy link
Member

@StoneT2000 StoneT2000 commented Feb 22, 2025

  • Adds in @arnavg115 work on a RGB Diffusion Policy Baseline and cleans the script up and improves documentation around IL in general
  • Make DrawTriangle a bit more strict but still solvable
  • New and improved FrameStack wrapper that works on both CPU and GPU sims and handles dictionary observations. Seems to be as fast as the gymnasium FrameStack wrapper that uses LazyFrames.
  • Removes the old generate.sh file for motionplanning demo generation and moves it with the other data generation scripts. motionplanning runner code for panda updated to run both panda stick and panda gripper solutions.
  • Fix bug with to_cpu_tensor not actually moving all tensors to the CPU if input was a dict
  • Update FlattenRGBDObservation wrapper to always put depth and rgb data separately by default. There isn't a good reason to put them together as these two modalities will always be have to handled differently regardless due to different normalizations.

arnavg115 and others added 12 commits February 22, 2025 10:26

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
…Triangle and Draw SVG task (#643)

* Added draw triangle with success condition

* parallelized progress

* fixed triangle rotation issues

* clean up and format

* rgbd diffusion policy progress

* diff policy rgbd cpu fixes

* minor diff policy fixes and finished draw triangle parallelization

* Added depth arg to diff pol rgbd + formatting

* Removed unused code

* Made requested fixes, made bugfix to frame stack wrapper

* Edited make_env and frame_stack

* Added state obs to draw triangle

* Update draw_triangle max steps

* Added DrawTriangle Docs

* Fixed naming

* draw svg progress

* fixed most issues and parallelized draw svg

* Update draw_svg.py

* added success condition and state based obs

* Added discontinuous paths for draw svg

* formatting, discontinuous state

* Updated run.py

* fixed state obs error for drawing envs

* Changed drawsvg imports

* Update draw_svg.py

* Update draw_svg.py

* Small bugfix

* Update draw_svg.py

* Update draw_svg.py

* Update draw_triangle.py

* Bugfixes, speed progress

* success condition speed up

* small fix

* Updated draw_triangle

* drawing env gpu bugfixes

* diff poll rgbd fixes

* minor changes

* fix for wandb logging

* autobuild docs for DrawTriangle and SVG

* Update utils.py to add PushCube

* adjustments for rgb

* added initial pose for drawing envs

* Update draw_triangle.py

* adjusted training arguments and shell scripts

* StackCube fix
for k in self.observation_space.keys()
}
else:
return torch.stack(list(self.frames)).transpose(0, 1)
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is torch.roll and ring buffer faster here?

@StoneT2000 StoneT2000 merged commit b75e188 into main Feb 25, 2025
@StoneT2000 StoneT2000 deleted the dp-cleanup branch February 25, 2025 20:41
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants