Adds example for gear assembly sim-to-real with UR10e (#4044)

https://github.com/user-attachments/assets/a04cfa6c-3c06-4cb6-8e81-500857c98cb2

# Description

This PR introduces a new **Gear Assembly manipulation task** for
sim-to-real training with the UR10e robot arm. This environment enables
training policies for precise gear insertion tasks using reinforcement
learning, with comprehensive sim-to-real transfer capabilities.

## Summary of Changes

### New Features
- **Gear Assembly Environment**: Complete environment implementation for
gear insertion tasks
  - Environment configuration (`gear_assembly_env_cfg.py`)
- UR10e-specific joint position control configuration
(`joint_pos_env_cfg.py`)
  - RSL-RL PPO training configuration (`rsl_rl_ppo_cfg.py`)
  
- **MDP Components**: Task-specific observation, reward, termination,
and event functions
  - `mdp/events.py`: Randomization and reset events for robust training
  - `mdp/observations.py`: State observation functions
  - `mdp/rewards.py`: Reward shaping for gear insertion
  - `mdp/terminations.py`: Episode termination conditions

- **Noise Models**: Enhanced noise simulation for domain randomization
  - Added configurable noise models (`noise_model.py`, `noise_cfg.py`)
- Integration with observation and action spaces for realistic
sim-to-real transfer

### Documentation
- **Sim-to-Real Training Walkthrough**: Complete guide for training and
deploying the gear assembly task
  - Step-by-step training instructions
  - Real robot deployment guidelines
  - Visual assets (GIFs and screenshots)

### Core Enhancements
- **Training Script**: Enhanced `train.py` with additional logging and
configuration options
- **UR10e Robot Configuration**: Updated `universal_robots.py` with gear
assembly specific parameters
- **Reward System**: Extended core reward functions in
`isaaclab/envs/mdp/rewards.py`
- **RL Configuration**: Updated RSL-RL integration (`rl_cfg.py`,
`setup.py`)

## Type of change

- [x] New feature (non-breaking change which adds functionality)
- [x] Documentation update

## 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
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have updated the changelog and the corresponding version in the
extension's `config/extension.toml` file
- [ ] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there

## Usage Example

```bash
# Train the gear assembly task
python scripts/reinforcement_learning/rsl_rl/train.py \
  --task Isaac-Deploy-GearAssembly-UR10e-2F140-ROS-Inference-v0 \
  --num_envs 256 \
  --headless

# Run inference with trained policy
python scripts/reinforcement_learning/rsl_rl/play.py \
  --task Isaac-Deploy-GearAssembly-UR10e-2F140-ROS-Inference-v0 \
  --num_envs 1 \
 --checkpoint <checkpoint_path>
```

---------

Signed-off-by: Ashwin Varghese Kuruttukulam <123109010+ashwinvkNV@users.noreply.github.com>
Co-authored-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>

Author: ashwinvkNV

docs/source/_static/policy_deployment/02_gear_assembly/gear_assembly_sim_real.webm

@@ -10,3 +10,4 @@ Below, you’ll find detailed examples of various policies for training and depl
 
     00_hover/hover_policy
     01_io_descriptors/io_descriptors_101
+    02_gear_assembly/gear_assembly_policy

docs/source/_static/policy_deployment/02_gear_assembly/sim_real_gear_assembly_train.jpg

@@ -10,6 +10,7 @@
 
 * :obj:`UR10_CFG`: The UR10 arm without a gripper.
 * :obj:`UR10E_ROBOTIQ_GRIPPER_CFG`: The UR10E arm with Robotiq_2f_140 gripper.
+* :obj:`UR10e_ROBOTIQ_2F_85_CFG`: The UR10E arm with Robotiq 2F-85 gripper.
 
 Reference: https://github.com/ros-industrial/universal_robot
 """
@@ -167,4 +168,44 @@
     armature=0.0,
 )
 
+
+UR10e_ROBOTIQ_2F_85_CFG = UR10e_CFG.copy()
 """Configuration of UR-10E arm with Robotiq_2f_140 gripper."""
+UR10e_ROBOTIQ_2F_85_CFG.spawn.variants = {"Gripper": "Robotiq_2f_85"}
+UR10e_ROBOTIQ_2F_85_CFG.spawn.rigid_props.disable_gravity = True
+UR10e_ROBOTIQ_2F_85_CFG.init_state.joint_pos["finger_joint"] = 0.0
+UR10e_ROBOTIQ_2F_85_CFG.init_state.joint_pos[".*_inner_finger_joint"] = 0.0
+UR10e_ROBOTIQ_2F_85_CFG.init_state.joint_pos[".*_inner_finger_knuckle_joint"] = 0.0
+UR10e_ROBOTIQ_2F_85_CFG.init_state.joint_pos[".*_outer_.*_joint"] = 0.0
+# the major actuator joint for gripper
+UR10e_ROBOTIQ_2F_85_CFG.actuators["gripper_drive"] = ImplicitActuatorCfg(
+    joint_names_expr=["finger_joint"],  # "right_outer_knuckle_joint" is its mimic joint
+    effort_limit_sim=10.0,
+    velocity_limit_sim=1.0,
+    stiffness=11.25,
+    damping=0.1,
+    friction=0.0,
+    armature=0.0,
+)
+# enable the gripper to grasp in a parallel manner
+UR10e_ROBOTIQ_2F_85_CFG.actuators["gripper_finger"] = ImplicitActuatorCfg(
+    joint_names_expr=[".*_inner_finger_joint"],
+    effort_limit_sim=1.0,
+    velocity_limit_sim=1.0,
+    stiffness=0.2,
+    damping=0.001,
+    friction=0.0,
+    armature=0.0,
+)
+# set PD to zero for passive joints in close-loop gripper
+UR10e_ROBOTIQ_2F_85_CFG.actuators["gripper_passive"] = ImplicitActuatorCfg(
+    joint_names_expr=[".*_inner_finger_knuckle_joint", "right_outer_knuckle_joint"],
+    effort_limit_sim=1.0,
+    velocity_limit_sim=1.0,
+    stiffness=0.0,
+    damping=0.0,
+    friction=0.0,
+    armature=0.0,
+)
+
+"""Configuration of UR-10E arm with Robotiq 2F-85 gripper."""

docs/source/policy_deployment/02_gear_assembly/gear_assembly_policy.rst

@@ -1,7 +1,7 @@
 [package]
 
 # Note: Semantic Versioning is used: https://semver.org/
-version = "0.11.10"
+version = "0.11.12"
 
 # Description
 title = "Isaac Lab Environments"

docs/source/policy_deployment/index.rst

@@ -1,6 +1,15 @@
 Changelog
 ---------
 
+0.11.12 (2025-12-16)
+~~~~~~~~~~~~~~~~~~~~
+
+Added
+^^^^^
+
+* Added ``Isaac-Deploy-GearAssembly`` environments.
+
+
 0.11.11 (2025-12-16)
 ~~~~~~~~~~~~~~~~~~~~
 

source/isaaclab_assets/isaaclab_assets/robots/universal_robots.py

@@ -0,0 +1,6 @@
+# Copyright (c) 2025-2026, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md).
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Assemble 3 gears into a base."""

source/isaaclab_tasks/config/extension.toml

@@ -0,0 +1,9 @@
+# Copyright (c) 2025-2026, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md).
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+"""Configurations for arm-based gear assembly environments."""
+
+# We leave this file empty since we don't want to expose any configs in this package directly.
+# We still need this file to import the "config" module in the parent package.

source/isaaclab_tasks/docs/CHANGELOG.rst

@@ -0,0 +1,75 @@
+# Copyright (c) 2025-2026, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md).
+# All rights reserved.
+#
+# SPDX-License-Identifier: BSD-3-Clause
+
+import gymnasium as gym
+
+from . import agents
+
+##
+# Register Gym environments.
+##
+
+
+# UR10e with 2F-140 gripper
+gym.register(
+    id="Isaac-Deploy-GearAssembly-UR10e-2F140-v0",
+    entry_point="isaaclab.envs:ManagerBasedRLEnv",
+    disable_env_checker=True,
+    kwargs={
+        "env_cfg_entry_point": f"{__name__}.joint_pos_env_cfg:UR10e2F140GearAssemblyEnvCfg",
+        "rsl_rl_cfg_entry_point": f"{agents.__name__}.rsl_rl_ppo_cfg:UR10GearAssemblyRNNPPORunnerCfg",
+    },
+)
+
+gym.register(
+    id="Isaac-Deploy-GearAssembly-UR10e-2F140-Play-v0",
+    entry_point="isaaclab.envs:ManagerBasedRLEnv",
+    disable_env_checker=True,
+    kwargs={
+        "env_cfg_entry_point": f"{__name__}.joint_pos_env_cfg:UR10e2F140GearAssemblyEnvCfg_PLAY",
+    },
+)
+
+# UR10e with 2F-85 gripper
+gym.register(
+    id="Isaac-Deploy-GearAssembly-UR10e-2F85-v0",
+    entry_point="isaaclab.envs:ManagerBasedRLEnv",
+    disable_env_checker=True,
+    kwargs={
+        "env_cfg_entry_point": f"{__name__}.joint_pos_env_cfg:UR10e2F85GearAssemblyEnvCfg",
+        "rsl_rl_cfg_entry_point": f"{agents.__name__}.rsl_rl_ppo_cfg:UR10GearAssemblyRNNPPORunnerCfg",
+    },
+)
+
+gym.register(
+    id="Isaac-Deploy-GearAssembly-UR10e-2F85-Play-v0",
+    entry_point="isaaclab.envs:ManagerBasedRLEnv",
+    disable_env_checker=True,
+    kwargs={
+        "env_cfg_entry_point": f"{__name__}.joint_pos_env_cfg:UR10e2F85GearAssemblyEnvCfg_PLAY",
+    },
+)
+
+# UR10e with 2F-140 gripper - ROS Inference
+gym.register(
+    id="Isaac-Deploy-GearAssembly-UR10e-2F140-ROS-Inference-v0",
+    entry_point="isaaclab.envs:ManagerBasedRLEnv",
+    disable_env_checker=True,
+    kwargs={
+        "env_cfg_entry_point": f"{__name__}.ros_inference_env_cfg:UR10e2F140GearAssemblyROSInferenceEnvCfg",
+        "rsl_rl_cfg_entry_point": f"{agents.__name__}.rsl_rl_ppo_cfg:UR10GearAssemblyRNNPPORunnerCfg",
+    },
+)
+
+# UR10e with 2F-85 gripper - ROS Inference
+gym.register(
+    id="Isaac-Deploy-GearAssembly-UR10e-2F85-ROS-Inference-v0",
+    entry_point="isaaclab.envs:ManagerBasedRLEnv",
+    disable_env_checker=True,
+    kwargs={
+        "env_cfg_entry_point": f"{__name__}.ros_inference_env_cfg:UR10e2F85GearAssemblyROSInferenceEnvCfg",
+        "rsl_rl_cfg_entry_point": f"{agents.__name__}.rsl_rl_ppo_cfg:UR10GearAssemblyRNNPPORunnerCfg",
+    },
+)