-
Notifications
You must be signed in to change notification settings - Fork 86
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
Push Environments #88
base: dev
Are you sure you want to change the base?
Conversation
palanc
commented
May 1, 2023
- Update existing push env to use cartesian action space
- Add new pushing envs
- All pushing envs use robotiq gripper. See additional PR here for gripper updates: Additional joint constraints robotiq_sim#1
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This seems like a larger refactor. See comments inline
@@ -1,7 +1,7 @@ | |||
{ | |||
# device1: sensors, actuators | |||
'franka':{ | |||
'interface': {'type': 'franka', 'ip_address':'169.254.163.91'}, | |||
'interface': {'type': 'franka', 'ip_address':'172.16.0.1', 'gain_scale': 1.5}, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Scale can only be a max of 1.0
<include file="../../../../simhive/scene_sim/topfloor_scene.xml"/> | ||
<include file="../../../../simhive/franka_sim/assets/assets.xml"/> | ||
<include file="../../../../simhive/franka_sim/assets/gripper_assets.xml"/> | ||
<include file="../../../../simhive/robotiq_sim/assets/assets.xml"/> |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Note that this is franka robot. Adding RobotiQ will cause confusion. We should create a new file for this and name it appropriately.
@@ -25,6 +30,27 @@ class PushBaseV0(env_base.MujocoEnv): | |||
|
|||
def __init__(self, model_path, obsd_model_path=None, seed=None, **kwargs): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Currently it looks like, the original env is being replaced by this new IK based env. Right? I think the right way to implement this is to
- define a new act mode called IK
- Once the robot receives
ctrl_desired
in the step, it relies on the process-actuator call to do the translation from ee space to jnt space. - I also think the action space definitions needs to be updated if its IK space
In summary, landing this in a generic way seems to require a rather larger refactor (possibly involving a refactor of the robot class). Let me know if should discuss this before going down this route.