Units and wrapping of joint_pos_rel, joint_vel_rel, base_ang_vel, and root_euler_angle in Isaac Lab?

Omniverse Isaac Sim
,
1

Note: For any Isaac Lab topics, please submit your topic to its GitHub repo (GitHub - isaac-sim/IsaacLab: Unified framework for robot learning built on NVIDIA Isaac Sim) following the instructions provided on Isaac Lab’s Contributing Guidelines (Contribution Guidelines — Isaac Lab Documentation).

Please provide all relevant details below before submitting your post. This will help the community provide more accurate and timely assistance. After submitting, you can check the appropriate boxes. Remember, you can always edit your post later to include additional information if needed.

Isaac Sim Version

[v] 4.5.0
4.2.0
4.1.0
4.0.0
4.5.0
2023.1.1
2023.1.0-hotfix.1
Other (please specify):

Operating System

[v] Ubuntu 22.04
Ubuntu 20.04
Windows 11
Windows 10
Other (please specify):

GPU Information

  • Model:
  • Driver Version:

Topic Description

Detailed Description

I’m currently working on a Sim2Real project using an ONNX policy trained in Isaac Lab. To apply the policy on my real robot, I need to align the observations from my code with the real hardware: specifically, Dynamixel MX-64 motors and an IMU sensor.

In Isaac Lab, the observation configuration is as follows:
joint_pos = ObsTerm(
func=mdp.joint_pos_rel,
noise=Unoise(n_min=-0.04, n_max=0.04),
params={
“asset_cfg”: SceneEntityCfg(“robot”, joint_names=[“.*”])
},
)
joint_vel = ObsTerm(func=mdp.joint_vel_rel, noise=Unoise(n_min=-1.5, n_max=1.5))
base_ang_vel = ObsTerm(func=mdp.base_ang_vel, noise=Unoise(n_min=-0.15, n_max=0.15))
base_euler = ObsTerm(func=mdp.root_euler_angle, noise=Unoise(n_min=-0.125, n_max=0.125))

To ensure compatibility between the simulation and the real robot, I’d like to confirm:

  1. What are the units used for joint_pos_rel, joint_vel_rel, base_ang_vel, and root_euler_angle in the ONNX file? Are all angular quantities in radians?
  2. How is angle wrapping handled for joint_pos_rel and root_euler_angle? For example, do angles wrap within [-π, π], [-2π, 2π], or are they unbounded?
  3. When mapping real sensor data (from the MX-64 motors and IMU) to match the Isaac Lab observations, do I need to wrap or normalize the values in any specific way?

Any clarification would be greatly appreciated!

Steps to Reproduce

(Add more steps as needed)

Error Messages

(If applicable, copy and paste any error messages you received)

Screenshots or Videos

(If applicable, add screenshots or links to videos that demonstrate the issue)

Additional Information

What I’ve Tried

(Describe any troubleshooting steps you’ve already taken)

Related Issues

(If you’re aware of any related issues or forum posts, please link them here)

Additional Context

(Add any other context about the problem here)

3

Thank you for your interest in Isaac Lab. We are following up about this question here.