google-deepmind / google-deepmind/mujoco_playground
Pretrained g1 policy doesn't seem to respect command well
Open
enhancement
- Dominant language
- Python
- Stars
- 2.2k
- Forks
- 359
- Avg merge
- 7d 3h
- Merged PRs (30d)
- 1
Description
I tried the play_g1_joystick.py example with the default g1 onnx policy, without connecting it to a gamepad so the command is always [0, 0, 0]. Seems like the robot still moves forward and doesn't track orientation well. Is this expected?
https://github.com/user-attachments/assets/7b535b02-8d63-4d88-9f44-1eb1bd12f4ad
Contributor guide
Assessment
This issue has not been assessed yet.