-
Notifications
You must be signed in to change notification settings - Fork 14
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
Robot doesn't respond to action in tor
(torque) mode
#230
Comments
Now that I'm seeing, we have the same issue with |
the magnitude of the applied torques is too small. Usually, for torques to be effective and overcome the friction, they must be in the order of 10000. Then however, you might have issues with the effort limits in the urdf's. |
How much?! 🤯🤯🤯 |
Yeah, I agree. I never really looked into that to be honest, because the friction model is unlikely to be very accurate with respect to the real robot. It would be very nice if you could investigate that, @behradkhadem . |
Sure, but a few questions. Thanks in advance! |
So, there are some parameters inside the URDF file. However, it feels like these are ignored by pybullet all together and in effect, there are some default values for all joints. You can change the friction parameters for individual joints similar to how I did it for the castor wheels: gym_envs_urdf/urdfenvs/urdf_common/differential_drive_robot.py Lines 110 to 118 in c7f7cb6
There is also a thread for a similar topic for a kuka arm: https://pybullet.org/Bullet/phpBB3/viewtopic.php?t=12644 I hope this hepls a bit. |
Hello @maxspahn, I think there's an issue with torque mode in robots. take this code for example:
Shouldn't robot respond to torque input? Is there something that I'm doing wrong? Everything seems fine in
vel
mode (and I even trained a simple RL agent with it) but I think there is something wrong withtor
.The text was updated successfully, but these errors were encountered: