8.4 KiB
| id | title | status | source_sections | related_topics | key_equations | key_terms | images | examples | open_questions |
|---|---|---|---|---|---|---|---|---|---|
| simulation | Simulation Environments | established | reference/sources/github-unitree-mujoco.md, reference/sources/github-unitree-rl-gym.md, reference/sources/github-unitree-rl-lab.md, reference/sources/github-unitree-sim-isaaclab.md, reference/sources/github-mujoco-menagerie-g1.md | [ros2-integration learning-and-ai locomotion-control] | [] | [sim_to_real domain_id] | [] | [] | [Optimal domain randomization parameters for G1 sim-to-real MJX vs standard MuJoCo performance for G1 training PyBullet G1 model quality and community support] |
Simulation Environments
Simulation tools, robot models, and sim-to-real transfer for the G1.
1. Available Simulators
| Simulator | Repository / Source | Status | Model Format | G1 Configs | Tier |
|---|---|---|---|---|---|
| MuJoCo (Unitree) | unitreerobotics/unitree_mujoco | Official | MJCF | G1 (all variants) | T0 |
| MuJoCo Menagerie | google-deepmind/mujoco_menagerie/unitree_g1 | Official | MJCF | G1 29-DOF, G1 with hands | T0 |
| Isaac Lab | unitreerobotics/unitree_sim_isaaclab | Official | USD/URDF | G1-29dof-gripper, G1-29dof-dex3, G1-23dof | T0 |
| Isaac Gym (legged) | unitreerobotics/unitree_rl_gym | Official | URDF | G1 | T0 |
| Isaac Lab (RL) | unitreerobotics/unitree_rl_lab | Official | USD/URDF | G1-29dof | T0 |
| Gazebo | unitreerobotics/unitree_ros | Limited | URDF | G1 (no high-level walking) | T1 |
| PyBullet | Community | Community | URDF | G1 (community models) | T2 |
| Unity ML-Agents | RizziGama/unitree-g1-rl-unity | Community | URDF | G1 (PPO/SAC training) | T2 |
2. Robot Models
MuJoCo Menagerie (Recommended for MuJoCo)
- Repository: https://github.com/google-deepmind/mujoco_menagerie/tree/main/unitree_g1
- Key files:
g1.xml— Main 29-DOF modelg1_with_hands.xml— Variant with hand modelsscene.xml— Standard environmentscene_mjx.xml— MJX-optimized environmentassets/— Mesh and texture files
- Requirements: MuJoCo 2.3.4+
- MJX variant: Manually designed collision geometries, tuned solver parameters, realistic PD gains validated on real hardware (MuJoCo Playground, arXiv:2502.08844)
- License: BSD-3-Clause [T0]
Unitree ROS URDF
- Repository: https://github.com/unitreerobotics/unitree_ros
- Location:
robots/g1_description/ - Contents: URDF with mass, inertia, moment, and joint limits
- Note: Designed for MuJoCo, NOT Gazebo-compatible for walking [T0]
USD Models (Isaac Sim)
- Repository: https://github.com/unitreerobotics/unitree_model (DEPRECATED)
- Current source: HuggingFace (newer models)
- Format: USD, converted from URDF via Isaac Sim [T0]
3. unitree_mujoco — Primary Simulator
Official MuJoCo simulator with seamless sim-to-real transition: [T0]
| Feature | Details |
|---|---|
| Languages | C++ (recommended) and Python |
| C++ location | simulate/ directory |
| Python location | simulate_python/ directory |
| Terrain generation | Stairs, rough ground, heightmaps |
| Humanoid init | Virtual elastic band for stable initialization |
| Joystick support | pygame-based joystick control (Python) |
C++ Dependencies
unitree_sdk2, MuJoCo, libyaml-cpp-dev, libspdlog-dev, libboost-all-dev, libglfw3-dev
Python Dependencies
unitree_sdk2_python, mujoco (pip), pygame (for joystick)
Supported Communication
- LowCmd/LowState (motor control)
- SportModeState (robot position/velocity)
- IMUState (for G1 robots)
4. unitree_sim_isaaclab — Isaac Lab Integration
High-fidelity simulation for data collection and model validation: [T0]
| Feature | Details |
|---|---|
| Isaac Sim versions | 4.5.0 or 5.0.0 |
| G1 configurations | G1-29dof-gripper, G1-29dof-dex3, G1-23dof |
| Tasks | Pick-and-place, stacking, mobile manipulation |
| DDS communication | Same protocol as physical robot |
| Visual data | Camera capture in simulation |
| Performance | 1s sim = 27 min real-world (RTX 4090, rough terrain) |
Example Command
python sim_main.py --task Isaac-PickPlace-Cylinder-G129-Dex1-Joint \
--enable_dex1_dds --robot_type g129
5. Sim-to-Real Transfer
The G1 ecosystem is designed for straightforward sim-to-real transfer: [T0]
MuJoCo → Real
Switch from simulation to real robot by changing only the network configuration:
- Simulation: Use domain ID for DDS routing
- Real hardware: Specify network interface (e.g.,
enp2s0)
No code changes required — the same DDS API works in both environments. [T0]
Training → Deployment Pipeline
1. Train (Isaac Gym / MuJoCo) → policy checkpoint
2. Play (MuJoCo sim) → validate behavior
3. Sim2Sim (MuJoCo ↔ Isaac Lab) → cross-sim validation
4. Sim2Real (unitree_sdk2) → deploy to physical robot
Domain Randomization
Standard RL training uses domain randomization for robustness:
- Physics parameters (friction, mass, restitution)
- Sensor noise (IMU bias, encoder noise)
- Terrain variation (procedural heightmaps)
- Latency simulation
- External force perturbations — random pushes applied to torso during training for push recovery robustness (see push-recovery-balance)
Known Sim-to-Real Gaps [T1 — Verified on real G1, 2026-02-15]
| Gap | Impact | Fix |
|---|---|---|
| IMU mounting offset | Persistent backward lean (~6° pitch offset between sim and real IMU) | Quaternion pitch rotation before gravity computation. See sensors-perception §4. |
| PD gain calibration | Policy trained with specific gains; changing gains degrades balance even if tracking improves | Use sim-trained gains OR recalibrate after gain change. Policy corrections are calibrated for training gains. |
| Action clipping | Not present in sim (RSL-RL default); adding clip in deployment causes saturation | Do NOT clip ONNX outputs — policy needs full range for push recovery |
| Surface compliance | Carpet adds ~1° effective ankle sag vs rigid sim floors | Minor — within policy tolerance |
Key insight: When a sim-trained policy produces poor real-world behavior, check sensor calibration BEFORE tuning gains or modifying the policy. An incorrect IMU reference frame cannot be fixed by any amount of gain tuning — the policy's balance loop actively fights the correction.
Perturbation Testing in Simulation
Both MuJoCo and Isaac Gym/Lab support applying external forces to the robot body during simulation. This is essential for:
- Training push-robust locomotion policies (push-recovery-balance)
- Validating balance during mocap playback (motion-retargeting)
- Testing whole-body controller robustness (whole-body-control)
In MuJoCo: use mj_applyFT() to apply forces/torques to bodies.
In Isaac Gym: use gym.apply_body_force_at_pos() for the same.
Motion Retargeting Validation
The AMASS motion dataset (retargeted for G1, available on HuggingFace) provides reference trajectories that can be played back in simulation before real-robot execution. This enables safe validation of the full mocap → retarget → WBC → execute pipeline. See motion-retargeting.
Key Relationships
- Models from: ros2-integration (URDF files)
- Trains policies for: learning-and-ai (RL training environments)
- Validates: locomotion-control (test gaits in sim before real hardware)
- Same API as: sdk-programming (DDS interface identical in sim and real)