Unitree go2 - IsaacLab - Motor sequence

전찬욱·2025년 12월 1일

Code

python << 'EOF'
from isaaclab.app import AppLauncher
app = AppLauncher(headless=True).app

import isaaclab.sim as sim_utils
from isaaclab.scene import InteractiveScene, InteractiveSceneCfg
from isaaclab.utils import configclass
from isaaclab_assets.robots.unitree import UNITREE_GO2_CFG

@configclass
class SceneCfg(InteractiveSceneCfg):
    terrain = None
    robot = UNITREE_GO2_CFG.replace(prim_path="{ENV_REGEX_NS}/Robot")

sim = sim_utils.SimulationContext(sim_utils.SimulationCfg(dt=0.005))
scene = InteractiveScene(SceneCfg(num_envs=1, env_spacing=1.0))

sim.reset()
scene.reset()
sim.step()

robot = scene.articulations["robot"]
print("\n=== Go2 Joint Order (policy action indexing) ===")
for i, name in enumerate(robot.data.joint_names):
    print(f"{i:2d} : {name}")

app.close()

EOF

Results

[INFO][AppLauncher]: Using device: cuda:0
[INFO][AppLauncher]: Loading experience file: /home/jeonchanwook/Documents/Github/IsaacLab/apps/isaaclab.python.headless.kit
[Warning] [simulation_app.simulation_app] Modules: ['omni.kit_app'] were loaded before SimulationApp was started and might not be loaded correctly.
[Warning] [simulation_app.simulation_app] Please check to make sure no extra omniverse or pxr modules are imported before the call to SimulationApp(...)
Loading user config located at: '/home/jeonchanwook/miniconda3/envs/env_isaaclab/lib/python3.11/site-packages/omni/data/Kit/Isaac-Sim/5.0/user.config.json'
[Info] [carb] Logging to file: /home/jeonchanwook/miniconda3/envs/env_isaaclab/lib/python3.11/site-packages/omni/logs/Kit/Isaac-Sim/5.0/kit_20251201_163903.log
2025-12-01T07:39:03Z [132ms] [Warning] [omni.usd_config.extension] Enable omni.materialx.libs extension to use MaterialX
2025-12-01T07:39:03Z [613ms] [Warning] [omni.isaac.dynamic_control] omni.isaac.dynamic_control is deprecated as of Isaac Sim 4.5. No action is needed from end-users.
Warp CUDA error: Failed to get driver entry point 'cuDeviceGetUuid' (CUDA error 1)
Warp CUDA error: Function cuDeviceGetUuid_f: a suitable driver entry point was not found
Warp CUDA error 36: API call is not supported in the installed CUDA driver (in function cuda_init, /builds/omniverse/warp/warp/native/warp.cu:277)
Warp CUDA error: Function cuDeviceGetUuid_f: a suitable driver entry point was not found
Warp CUDA error 36: API call is not supported in the installed CUDA driver (in function cuda_init, /builds/omniverse/warp/warp/native/warp.cu:277)

|---------------------------------------------------------------------------------------------|
| Driver Version: 580.95.05     | Graphics API: Vulkan
|=============================================================================================|
| GPU | Name                             | Active | LDA | GPU Memory | Vendor-ID | LUID       |
|     |                                  |        |     |            | Device-ID | UUID       |
|     |                                  |        |     |            | Bus-ID    |            |
|---------------------------------------------------------------------------------------------|
| 0   | NVIDIA RTX PRO 6000 Blackwell .. | Yes: 0 |     | 97887   MB | 10de      | 0          |
|     |                                  |        |     |            | 2bb4      | f6f6b3ef.. |
|     |                                  |        |     |            | 41        |            |
|---------------------------------------------------------------------------------------------|
| 1   | NVIDIA RTX PRO 6000 Blackwell .. | Yes: 1 |     | 97887   MB | 10de      | 0          |
|     |                                  |        |     |            | 2bb4      | f0731afa.. |
|     |                                  |        |     |            | 81        |            |
|=============================================================================================|
| OS: 22.04.5 LTS (Jammy Jellyfish) ubuntu, Version: 22.04.5, Kernel: 6.8.0-87-generic
| XServer Vendor: The X.Org Foundation, XServer Version: 12101004 (1.21.1.4)
| Processor: AMD Ryzen Threadripper 7970X 32-Cores
| Cores: 32 | Logical Cores: 64
|---------------------------------------------------------------------------------------------|
| Total Memory (MB): 257222 | Free Memory: 231261
| Total Page/Swap (MB): 0 | Free Page/Swap: 0
|---------------------------------------------------------------------------------------------|
2025-12-01T07:39:08Z [5,123ms] [Warning] [gpu.foundation.plugin] CPU performance profile is set to powersave. This profile sets the CPU to the lowest frequency reducing performance.

=== Go2 Joint Order (policy action indexing) ===
 0 : FL_hip_joint
 1 : FR_hip_joint
 2 : RL_hip_joint
 3 : RR_hip_joint
 4 : FL_thigh_joint
 5 : FR_thigh_joint
 6 : RL_thigh_joint
 7 : RR_thigh_joint
 8 : FL_calf_joint
 9 : FR_calf_joint
10 : RL_calf_joint
11 : RR_calf_joint

Isaac Version

Name: isaacsim
Version: 5.0.0.0
Summary: A metapackage to manage the Isaac Sim installation
Home-page: https://developer.nvidia.com/isaac-sim
Author: Isaac Sim team
Author-email: 
License: NVIDIA Proprietary Software
Location: /home/jeonchanwook/miniconda3/envs/env_isaaclab/lib/python3.11/site-packages
Requires: isaacsim-kernel
Required-by: 
---
Name: isaaclab
Version: 0.46.3
Summary: Extension providing main framework interfaces and abstractions for robot learning.
Home-page: https://github.com/isaac-sim/IsaacLab
Author: Isaac Lab Project Developers
Author-email: 
License: BSD-3-Clause
Location: /home/jeonchanwook/miniconda3/envs/env_isaaclab/lib/python3.11/site-packages
Editable project location: /home/jeonchanwook/Documents/Github/IsaacLab/source/isaaclab
Requires: dex-retargeting, einops, flaky, flatdict, gymnasium, hidapi, junitparser, numpy, onnx, pillow, pin-pink, prettytable, pyglet, pytest, pytest-mock, starlette, toml, torch, transformers, trimesh, warp-lang
Required-by: 

# Unitree[i] = IsaacLab[ISAACLAB_TO_UNITREE[i]]
ISAACLAB_TO_UNITREE = np.array([
    1, 5, 9,   # FR_hip, FR_thigh, FR_calf
    0, 4, 8,   # FL_hip, FL_thigh, FL_calf
    3, 7, 11,  # RR_hip, RR_thigh, RR_calf
    2, 6, 10   # RL_hip, RL_thigh, RL_calf
], dtype=np.int32)

0개의 댓글