Add velocity_limit_sim and effort_limit_sim to actuator #1654
Conversation
jtigue-bdai
requested review from
jsmith-bdai,
kellyguo11 and
Mayankm96
as code owners
|
I like this! and enjoyed the insightful discussion in PR1509 I think previous commit that write the velocity limit in actuator cfg to simulation-level velocity limit broke some of my quadrupet training, and I only figured it out because of the commit before that one worked. |
| self.write_joint_armature_to_sim(actuator.armature, joint_ids=actuator.joint_indices) | ||
| self.write_joint_friction_to_sim(actuator.friction, joint_ids=actuator.joint_indices) | ||
| else: | ||
| # the gains and limits are processed by the actuator model | ||
| # we set gains to zero, and torque limit to a high value in simulation to avoid any interference | ||
| self.write_joint_stiffness_to_sim(0.0, joint_ids=actuator.joint_indices) | ||
| self.write_joint_damping_to_sim(0.0, joint_ids=actuator.joint_indices) | ||
| self.write_joint_effort_limit_to_sim(1.0e9, joint_ids=actuator.joint_indices) | ||
| self.write_joint_velocity_limit_to_sim(actuator.velocity_limit, joint_ids=actuator.joint_indices) | ||
| self.write_joint_effort_limit_to_sim(actuator.effort_limit_sim, joint_ids=actuator.joint_indices) |
There was a problem hiding this comment.
This could lead to some breaking changes, since the upper limit of the drives is not 1e9 anymore? Maybe change this to actuator.effort_limit_sim if actuator.effort_limit_sim is not None else 1.0e9 or change the default value from None to 1.0e9?
There was a problem hiding this comment.
yeah good call. I will change the default to 1.0e9
jtigue-bdai
force-pushed
the
jat/fix/velocity_limit_sim
branch
from
c7fef1e to
b08422e
Compare
| If None, the limit is set to the value specified in the USD joint prim. The simulation effort limits prevent | ||
| computed torques from exceeding. If effort limits are too tight issues with solver convergence may occur. |
There was a problem hiding this comment.
should we maybe give a hint here that it is recommended to set these values higher?
There was a problem hiding this comment.
Actually I just updated the default behavior based off @renezurbruegg's suggestion. I should update to reflect that.
Co-authored-by: Pascal Roth <57946385+pascal-roth@users.noreply.github.com> Signed-off-by: James Tigue <166445701+jtigue-bdai@users.noreply.github.com>
| If None, the limit is set to the value specified in the USD joint prim. Resulting solver solutions will constrain | ||
| velocities by these limits. If velocity limits are too tight issues with solver convergence may occur. |
There was a problem hiding this comment.
also here we could give the hint
Signed-off-by: James Tigue <166445701+jtigue-bdai@users.noreply.github.com>
Description
This PR follows up on Issue 1384 and PR 1509 by seperating actuator limits for calculating computed torques from physics solver limits.
Fixes # (#1384)
Type of change
Screenshots
Please attach before and after screenshots of the change if applicable.
Checklist
pre-commitchecks with./isaaclab.sh --formatconfig/extension.tomlfileCONTRIBUTORS.mdor my name already exists there