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

Prepping for V0.6 release #108

Merged
merged 82 commits into from
Aug 31, 2023
Merged

Prepping for V0.6 release #108

merged 82 commits into from
Aug 31, 2023

Conversation

vikashplus
Copy link
Owner

No description provided.

vikashplus and others added 30 commits April 19, 2023 11:35
get_visuals() checks obs_keys instead visual_keys for depth logging.
- Wall clock and sim_time was being compared which sped up the initial few steps.
- Default script to demo the robot was state. Reviving
* Allow examine_envs to load hard coded policies, E.g.
python robohive/utils/examine_env.py -e FrankaReachRandom-v0 -p robohive.utils.examine_env.rand_policy

* Remove unnecessary import
* examine_env loading scripted polcies: update DESC in examine_env and add unit test
Co-authored-by: Patrick Lancaster <plancaster@pop-os.localdomain>
…nittests to catch the logger bugs. It will need a lot more tests to compherensively test the logger - logger format wasn't properly dlowing through introducing a few bugs along the way
…ary checks for mujoco_py compilation if its not in use
Vittorio-Caggiano and others added 26 commits July 5, 2023 09:56
…LITE can now disable checks on envs that require encoder downloads
…e with FIXED and RANDOM convensions. Removing the franka_kitchen_v1.py
* add rendering test

* add ffmpeg
* DKITTY: Updates to the rwd weights and target angles

* initial files

* TCDM: FEATURE - refernce motions compatibility with fixed and random conditions
> - BUGFIX: find_timeslot_in_reference was buggy for FIXEd setting as horizon was 1
> - BUGFIX: ReferenceType.RANDOM wasn't seeded properly with the env's random number generator
> - FEATURE: init and ref[t=0] were getting confused. Its better handled now
> - Termination conditions for the env was firing all the time. Exposing it to the setup do that envs can be customized during registration

* MYO_SIM: Upgrading myo_hand models. The new version has kinematic chain cleanly isolated in a way that help incorporation of hand inside other kinematic chains

* BUGFIX: Target site updates correctly now, earlier all sites were updating. Better handeling of robot and object DoFs

* MYODEX+FEATURE: Adding the myodex envs. Envs and the replays are in working conditions. The motion files are the old files used in the repo. These files needs to be reparsed into the new env convensions. Adding new envs into the test as well

* MIMIC: Uses names tuple to build reference motion. This provides a consistent struture for reference to build upon. We can also now use pickle files in addition to the npg files. Missing motion entries are marked as None

* BugFix: Time was marked as int instead of float. Playback had a hardcoded env step delay

* MIMIC+FEATURE: Preparing for motion mimic. Two suites are added -- myodex and myomic. These suites are similar to the tcdm suites. They are currently disjoint but have very similar structure and should be brought closer together as things mature

* BUGFIX: Handling missing motion entries marked as None

* FEATURE: Adding the mocap bodies and constratins for IK-tracking

* add utils files for ik from mocap

* add mocap file

* add instructions

* MyoDex: Upgrading to the latest myo_sim. All tests passing

* fix arm coordinates

* readded traj ... just in case

* update trajectories

* new xml file

* CLEANING up MyoDex_tabletop model

---------
Bringing in MyoDex developments. 
- Hand+Object models look good 
- Trajectories playback well.
--------

Co-authored-by: Vittorio Caggiano <caggiano@fb.com>
- adding sar files
- merging mex branch bring myodm env suite: MyoSuite2.0 synced here with RoboHive
- reference class moved to logger
- all base envs moved to new myobase folder
- adding all the MC23 envs
@vikashplus vikashplus merged commit 50ebb2a into main Aug 31, 2023
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

5 participants