Fix Unitree Go2 calf actuator limits - #7562
Conversation
There was a problem hiding this comment.
Isaac Lab Review Bot
The Go2 calf joints are correctly split into a dedicated DC-motor group with reduction-adjusted effort and velocity limits, while existing gains and friction are preserved. The changelog should also document the changed actuator-group layout and migration impact for downstream overrides.
- Design and architecture: Using a separate
DCMotorCfggroup is appropriate because the calf joints require different effort and velocity limits from the hip and thigh joints. The group split preserves the previous stiffness, damping, and friction values. - API:
UNITREE_GO2_CFG.actuatorsnow narrowsbase_legsto hip and thigh joints and introduces thecalveskey. Because downstream configurations overridingactuators["base_legs"]will no longer affect calves, the changelog must identify the new group and provide migration guidance for that changed behavior. - Implementation: The calf joint expression and reduction-adjusted limits are applied consistently, and the regression test directly checks the new group boundaries and limit values. The remaining fix is limited to documenting the actuator-group restructuring in the changelog fragment.
Minor fixes needed. Posted 1 actionable finding inline.
Automated review; human maintainers own approval decisions.
| Fixed | ||
| ^^^^^ | ||
|
|
||
| * Fixed the Unitree Go2 calf actuator limits to reflect the knee reduction instead of sharing the hip/thigh limits. |
There was a problem hiding this comment.
🟡 Warning · Api — Changelog omits actuator group restructure guidance
The fragment only mentions limit values, but the public config layout also changed: UNITREE_GO2_CFG.actuators["base_legs"] no longer matches .*_calf_joint, and a new "calves" group was added. Downstream configs that override actuators["base_legs"] (stiffness, damping, limits, joint expressions) now silently skip calf joints. Repository rules require migration guidance for changed behavior; state the narrowed base_legs scope and the new group name.
Greptile SummaryThe PR separates Unitree Go2 calf joints into their own DC-motor actuator group so their effort and velocity limits account for the knee reduction, and adds a configuration regression test and changelog entry.
Confidence Score: 4/5The PR should not merge until the new calf actuator group receives the existing Go2 backend-specific armature preset. The limit conversion is internally consistent, but splitting the actuator group causes current rough and flat Go2 environments to leave calf armature at the USD value while applying their configured preset only to hip and thigh joints. Files Needing Attention: source/isaaclab_assets/isaaclab_assets/robots/unitree.py and source/isaaclab_tasks/isaaclab_tasks/core/velocity/config/go2/rough_env_cfg.py Important Files Changed
Reviews (1): Last reviewed commit: "docs: add Go2 actuator changelog fragmen..." | Re-trigger Greptile |
| damping=0.5, | ||
| friction=0.0, | ||
| ), | ||
| "calves": DCMotorCfg( |
There was a problem hiding this comment.
When Go2 rough or flat velocity environments initialize, their backend-specific armature preset updates only base_legs; moving the calf joints into calves leaves them at the USD-authored armature instead of the configured 0.0 or 0.02 value, unintentionally changing calf dynamics.
|
Thanks for the PR @sylvesterkaczmarek I think we want to go a slightly different route by avoiding the creation of two actuator groups, it can be a bit slower. Also looks like Go1 is affected by similar issues. Some other unitree assets are also affected (like G1 or H1) but for this we likely need new assets. #7564 to replace |
…ion (#7564) # Description Fixes #7479. `UNITREE_GO1_CFG` and `UNITREE_GO2_CFG` apply one set of DC-motor limits to all twelve leg joints, but on both robots the calf sits behind an extra knee reduction. The calf was capped at roughly half its rated torque, while the torque-speed curve kept producing motoring torque up to a no-load speed the hardware cannot reach. The values are not a guess — they are already authored in the USD assets we ship, and the Python configs were discarding them. Dumping the joint drives from the configured asset root: | joint | `go2.usd` `maxForce` | `go2.usd` `maxJointVelocity` | old config | | --- | --- | --- | --- | | hip / thigh | 23.7 N·m | 1724.6 °/s = 30.1 rad/s | 23.5 / 30.0 | | calf | **45.43 N·m** | 899.54 °/s = **15.70 rad/s** | 23.5 / 30.0 | | joint | `go1.usd` `maxForce` | `go1.usd` `maxJointVelocity` | old config | | --- | --- | --- | --- | | hip / thigh | 23.7 N·m | 1724.6 °/s = 30.1 rad/s | 23.7 / 30.0 | | calf | **35.55 N·m** | 1149.35 °/s = **20.06 rad/s** | 23.7 / 30.0 | Both match the official Unitree URDFs exactly ([go2](https://github.com/unitreerobotics/unitree_ros/blob/master/robots/go2_description/urdf/go2_description.urdf), [go1](https://github.com/unitreerobotics/unitree_ros/blob/master/robots/go1_description/urdf/go1.urdf)), giving reductions of 1.9169 and 1.5000. Go1 is affected for the same reason even though it uses an actuator net: `ActuatorNetMLP` subclasses `DCMotor`, so the network output goes through the same envelope. `UNITREE_A1_CFG` was checked and needs no change — `a1.urdf` and `a1.usd` are both flat at 33.5 N·m / 21.0 rad/s, matching the config. ## Why `saturation_effort` had to change The calf needs its own *stall* torque, not just its own effort and velocity limits. `saturation_effort` was the one actuator limit typed as a bare `float`, so expressing this previously required splitting the legs into two actuator groups — which changes the `actuators` dict keys that `go1/rough_env_cfg.py`, `go2/rough_env_cfg.py` and `test_hydra.py` index by name, and adds a second group to iterate every step. The first commit resolves it through `resolve_joint_parameter` like every other limit, so it accepts a joint-name-pattern dict. This is not a new concept in the codebase: `sim/schemas/schemas_actuators.py` already expands dict-shaped `saturation_effort` when authoring `NewtonActuator` prims, so the config type was simply narrower than the machinery behind it. Scalar configurations are unaffected. ## Note on #7562 @sylvesterkaczmarek filed #7479 and opened #7562 for the Go2 half of this. That PR takes the second-actuator-group route and derives the calf values from the reduction ratio (45.05 / 15.65) rather than reading them off the asset. This PR covers Go1 as well, keeps a single actuator group, and uses the values already in the USD. Happy to defer if maintainers prefer the other shape. ## Type of change - Bug fix (non-breaking change which fixes an issue) - New feature (non-breaking change which adds functionality) Simulated Go1 and Go2 behavior changes: the calf now produces up to 1.92x more torque and stops motoring at roughly half the previous speed. Policies trained against the old configuration should be retrained rather than reused. This is called out in the `isaaclab_assets` changelog fragment. ## Tests - `source/isaaclab/test/actuators/test_dc_motor.py` gains `test_dc_motor_clip_with_per_joint_saturation_effort`, which checks that a dict-configured two-joint group reproduces, column by column, what a scalar-configured actuator produces for the same joint. Verified failing before the fix (`TypeError: unsupported operand type(s) for /: 'Tensor' and 'dict'`) and passing after. - `source/isaaclab/test/actuators/test_dc_motor.py` — 170 passed. - `source/isaaclab/test/actuators/test_actuator_collection.py` — 30 passed. - `source/isaaclab_assets/test/test_valid_configs.py -k cpu` — 1 passed (spawns every registered asset, including both Go configs). - Confirmed the patterns resolve against the real joint names: all four calf joints get 45.43 / 15.70 (Go2) and 35.55 / 20.06 (Go1); hips and thighs get 23.7 / 30.1. No config-literal assertion test was added for `unitree.py` — it would restate the constants without checking behavior. The behavioral contract is covered by the DC-motor test above. ## Release backport - [x] <!-- backport-active-release --> Backport this pull request to the active release branch after it merges into `develop` ## Checklist - [x] I have read and understood the [contribution guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html) - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] I have added a changelog fragment under `source/<pkg>/changelog.d/` for every touched package - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there
…ion (#7564) # Description Fixes #7479. `UNITREE_GO1_CFG` and `UNITREE_GO2_CFG` apply one set of DC-motor limits to all twelve leg joints, but on both robots the calf sits behind an extra knee reduction. The calf was capped at roughly half its rated torque, while the torque-speed curve kept producing motoring torque up to a no-load speed the hardware cannot reach. The values are not a guess — they are already authored in the USD assets we ship, and the Python configs were discarding them. Dumping the joint drives from the configured asset root: | joint | `go2.usd` `maxForce` | `go2.usd` `maxJointVelocity` | old config | | --- | --- | --- | --- | | hip / thigh | 23.7 N·m | 1724.6 °/s = 30.1 rad/s | 23.5 / 30.0 | | calf | **45.43 N·m** | 899.54 °/s = **15.70 rad/s** | 23.5 / 30.0 | | joint | `go1.usd` `maxForce` | `go1.usd` `maxJointVelocity` | old config | | --- | --- | --- | --- | | hip / thigh | 23.7 N·m | 1724.6 °/s = 30.1 rad/s | 23.7 / 30.0 | | calf | **35.55 N·m** | 1149.35 °/s = **20.06 rad/s** | 23.7 / 30.0 | Both match the official Unitree URDFs exactly ([go2](https://github.com/unitreerobotics/unitree_ros/blob/master/robots/go2_description/urdf/go2_description.urdf), [go1](https://github.com/unitreerobotics/unitree_ros/blob/master/robots/go1_description/urdf/go1.urdf)), giving reductions of 1.9169 and 1.5000. Go1 is affected for the same reason even though it uses an actuator net: `ActuatorNetMLP` subclasses `DCMotor`, so the network output goes through the same envelope. `UNITREE_A1_CFG` was checked and needs no change — `a1.urdf` and `a1.usd` are both flat at 33.5 N·m / 21.0 rad/s, matching the config. ## Why `saturation_effort` had to change The calf needs its own *stall* torque, not just its own effort and velocity limits. `saturation_effort` was the one actuator limit typed as a bare `float`, so expressing this previously required splitting the legs into two actuator groups — which changes the `actuators` dict keys that `go1/rough_env_cfg.py`, `go2/rough_env_cfg.py` and `test_hydra.py` index by name, and adds a second group to iterate every step. The first commit resolves it through `resolve_joint_parameter` like every other limit, so it accepts a joint-name-pattern dict. This is not a new concept in the codebase: `sim/schemas/schemas_actuators.py` already expands dict-shaped `saturation_effort` when authoring `NewtonActuator` prims, so the config type was simply narrower than the machinery behind it. Scalar configurations are unaffected. ## Note on #7562 @sylvesterkaczmarek filed #7479 and opened #7562 for the Go2 half of this. That PR takes the second-actuator-group route and derives the calf values from the reduction ratio (45.05 / 15.65) rather than reading them off the asset. This PR covers Go1 as well, keeps a single actuator group, and uses the values already in the USD. Happy to defer if maintainers prefer the other shape. ## Type of change - Bug fix (non-breaking change which fixes an issue) - New feature (non-breaking change which adds functionality) Simulated Go1 and Go2 behavior changes: the calf now produces up to 1.92x more torque and stops motoring at roughly half the previous speed. Policies trained against the old configuration should be retrained rather than reused. This is called out in the `isaaclab_assets` changelog fragment. ## Tests - `source/isaaclab/test/actuators/test_dc_motor.py` gains `test_dc_motor_clip_with_per_joint_saturation_effort`, which checks that a dict-configured two-joint group reproduces, column by column, what a scalar-configured actuator produces for the same joint. Verified failing before the fix (`TypeError: unsupported operand type(s) for /: 'Tensor' and 'dict'`) and passing after. - `source/isaaclab/test/actuators/test_dc_motor.py` — 170 passed. - `source/isaaclab/test/actuators/test_actuator_collection.py` — 30 passed. - `source/isaaclab_assets/test/test_valid_configs.py -k cpu` — 1 passed (spawns every registered asset, including both Go configs). - Confirmed the patterns resolve against the real joint names: all four calf joints get 45.43 / 15.70 (Go2) and 35.55 / 20.06 (Go1); hips and thighs get 23.7 / 30.1. No config-literal assertion test was added for `unitree.py` — it would restate the constants without checking behavior. The behavioral contract is covered by the DC-motor test above. ## Release backport - [x] <!-- backport-active-release --> Backport this pull request to the active release branch after it merges into `develop` ## Checklist - [x] I have read and understood the [contribution guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html) - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] I have added a changelog fragment under `source/<pkg>/changelog.d/` for every touched package - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there (cherry picked from commit 5c78379)
Description
Fixes #7479.
UNITREE_GO2_CFGcurrently applies the same DC-motor effort and velocity limits to the hip, thigh, and calf joints. The Go2 calf sits behind an additional knee reduction, so using the hip/thigh limits underestimates calf torque and allows an unrealistically high motor-curve velocity.This change keeps the existing hip/thigh actuator settings and gives the calf joints their own actuator group with reduction-adjusted limits:
The stiffness, damping, and friction settings are unchanged.
Tests
Adds a configuration regression test verifying the calf group and its reduced joint-side limits.
Changelog
Adds the required
isaaclab_assetschangelog fragment.