# Initial Implementation of UR10e Reach Environment for IsaacLab

<!--
Thank you for your interest in sending a pull request. Please make sure
to check the contribution guidelines.

Link:
https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html
-->

This PR introduces a UR10e robot reach environment for IsaacLab,
enabling reinforcement learning-based end-effector pose control using
keypoint-based rewards and domain randomization.

## Summary

Adds a new UR10e reach environment that trains RL agents to control the
robot's end-effector to reach target poses. Uses manager-based RL
framework with 6D keypoint alignment rewards.

### Key Features:
- **UR10e Robot Configuration**: Asset definition for UE10e
- **Keypoint-based Rewards**: 6D pose alignment using multiple keypoints
for precise control
- **Domain Randomization**: Joint position, stiffness, damping, and
friction randomization

## Type of change

- [x] New feature (non-breaking change which adds functionality)
- [x] This change requires a documentation update

## Implementation Details
### Environment Configuration:
- **Observations**: Joint positions, velocities, target pose commands
(19-dim)
- **Actions**: Relative joint position control with 0.0625 scale factor
(6-dim)
- **Rewards**: Keypoint tracking with exponential reward functions
- **Domain Randomization**: Joint offsets (±0.125 rad), stiffness
(0.9-1.1x), damping (0.75-1.5x), friction (0.0-0.1 N⋅m)

### Target Workspace:
- **Position**: Center (0.8875, -0.225, 0.2) ± (0.25, 0.125, 0.1) meters
- **Orientation**: (π, 0, -π/2) ± (π/6, π/6, 2π/3) radians

## Checklist

- [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 updated the changelog and the corresponding version in the
extension's `config/extension.toml` file
- [x] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there

## Usage Example

```python
./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/train.py --task Isaac-Reach-UR10e-v0 --num_envs 1024 --headless
./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/play.py --task Isaac-Reach-UR10e-v0 --num_envs 1 --checkpoint <path_to_checkpoint>
```
Co-authored-by: Kelly Guo <kellyg@nvidia.com>