Skip to content

[WIP] Add shared configurations for robot manipulation tasks#2

Closed
Copilot wants to merge 1 commit intomainfrom
copilot/add-robot-manipulation-configs
Closed

[WIP] Add shared configurations for robot manipulation tasks#2
Copilot wants to merge 1 commit intomainfrom
copilot/add-robot-manipulation-configs

Conversation

Copy link
Copy Markdown

Copilot AI commented Jan 9, 2026

Thanks for asking me to work on this. I will get started on it and keep this PR's description up to date as I form a plan and make progress.

Original prompt

robot-manipulation-rl/
├── README.md
├── pyproject.toml # Root project config
├── requirements.txt # Shared dependencies
├── Makefile # Common tasks

├── configs/ # Shared configuration files
│ ├── tasks/
│ │ ├── pick_place.yaml
│ │ ├── in_hand_manipulation.yaml
│ │ └── peg_insertion.yaml
│ ├── rl/
│ │ ├── ppo.yaml
│ │ └── sac.yaml
│ └── shared/
│ └── robot_specs.yaml

├── mujoco/ # MuJoCo environment & training
│ ├── README.md
│ ├── requirements.txt # MuJoCo-specific deps
│ ├── environment.yml # Conda env (optional)
│ │
│ ├── envs/
│ │ ├── init.py
│ │ ├── base_env.py # BaseEnv inherits from gym.Env
│ │ ├── manipulation_env.py # Pick & place, in-hand tasks
│ │ ├── contact_sensor.py # Tactile sensing utilities
│ │ └── tasks/
│ │ ├── init.py
│ │ ├── pick_place.py
│ │ ├── in_hand_manip.py
│ │ └── peg_insertion.py
│ │
│ ├── models/
│ │ ├── robot/
│ │ │ ├── ur5e.xml
│ │ │ ├── shadow_hand.xml
│ │ │ └── gripper.xml
│ │ ├── objects/
│ │ │ ├── cube.xml
│ │ │ ├── sphere.xml
│ │ │ └── peg.xml
│ │ └── scenes/
│ │ ├── tabletop.xml
│ │ └── dexterous.xml
│ │
│ ├── train.py # MuJoCo training script
│ ├── eval.py
│ ├── test_env.py # Quick env sanity checks
│ └── utils/
│ ├── init.py
│ ├── tactile_utils.py # Force/torque extraction
│ ├── reward_shaping.py
│ └── wrappers.py # Gym wrappers

├── isaaclab/ # IsaacLab environment & training
│ ├── README.md
│ ├── requirements.txt # IsaacLab-specific deps
│ │
│ ├── envs/
│ │ ├── init.py
│ │ ├── base_env.py # BaseEnv inherits from RL-Games base
│ │ ├── manipulation_env.py
│ │ └── tasks/
│ │ ├── init.py
│ │ ├── pick_place.py
│ │ ├── in_hand_manip.py
│ │ └── peg_insertion.py
│ │
│ ├── assets/
│ │ ├── robots/
│ │ │ ├── ur5e/
│ │ │ │ └── ur5e.usd
│ │ │ └── shadow_hand/
│ │ │ └── shadow_hand.usd
│ │ ├── objects/
│ │ │ ├── cube.usd
│ │ │ ├── sphere.usd
│ │ │ └── peg.usd
│ │ └── scenes/
│ │ └── default_scene.usd
│ │
│ ├── train.py # IsaacLab training script
│ ├── eval.py
│ └── utils/
│ ├── init.py
│ ├── contact_sensor.py # Native Isaac contact API
│ ├── reward_shaping.py
│ └── wrappers.py

├── shared/ # Shared code across simulators
│ ├── init.py
│ ├── rl/
│ │ ├── init.py
│ │ ├── algorithms.py # PPO, SAC implementations
│ │ ├── replay_buffer.py
│ │ ├── networks.py # Actor/Critic networks
│ │ └── training_loop.py # Generic training logic
│ ├── sensors/
│ │ ├── init.py
│ │ ├── tactile_sensor.py # Unified tactile interface
│ │ └── camera_sensor.py
│ ├── utils/
│ │ ├── init.py
│ │ ├── data_utils.py
│ │ ├── visualization.py
│ │ ├── logging.py
│ │ └── metrics.py
│ └── envs/
│ ├── init.py
│ └── base_interface.py # Abstract base (both inherit from this)

├── scripts/
│ ├── train_mujoco.sh # Bash wrappers
│ ├── train_isaaclab.sh
│ ├── compare_results.py # Compare policies across sims
│ ├── convert_policy.py # Transfer learned policies
│ └── benchmark.py # Speed/accuracy benchmarks

├── tests/
│ ├── init.py
│ ├── test_mujoco_env.py
│ ├── test_isaaclab_env.py
│ ├── test_shared_rl.py
│ └── test_tactile_sensors.py

├── notebooks/
│ ├── mujoco_demo.ipynb
│ ├── isaaclab_demo.ipynb
│ └── comparison.ipynb

├── docs/
│ ├── setup.md # Installation instructions
│ ├── mujoco_guide.md
│ ├── isaaclab_guide.md
│ ├── tactile_integration.md
│ └── sim_transfer.md

└── .github/
└── workflows/
├── test.yml # Run tests on both
├── lint.yml
└── benchmark.yml


✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

Copilot AI requested a review from pietrodardano January 9, 2026 10:38
Copilot stopped work on behalf of pietrodardano due to an error January 9, 2026 10:38
@pietrodardano pietrodardano marked this pull request as ready for review January 9, 2026 14:52
@pietrodardano pietrodardano marked this pull request as draft January 9, 2026 14:53
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants