Skip to content

Latest commit

 

History

History
116 lines (77 loc) · 3.06 KB

README.md

File metadata and controls

116 lines (77 loc) · 3.06 KB
Raw

StrideSim

Table of Contents

IsaacSim Isaac Lab Python License

Overview

StrideSim is a project based on Isaac Lab. This repository is designed to allow development in an independent environment outside the core repository of Isaac Lab.

Docker Installation (Recommended)

You can build and run the container using the Dockerfile.

Docker Installation Guide

Local Installation

  1. Install Isaac Sim 4.0.0: Refer to the Installation Guide.

  2. Install Isaac Lab v1.0.0: Refer to the Installation Guide.

  3. Install StrideSim:

    git clone https://github.com/AuTURBO/StrideSim.git
    sudo apt-get install -y git-lfs
git lfs install

cd StrideSim
git lfs pull

Tips

  1. Set environment variables:

    # Isaac Sim root directory
export ISAACSIM_PATH="${HOME}/.local/share/ov/pkg/isaac-sim-4.0.0"
# Isaac Sim python executable
alias ISAACSIM_PYTHON="${ISAACSIM_PATH}/python.sh"
# Isaac Sim app
alias ISAACSIM="${ISAACSIM_PATH}/isaac-sim.sh"

Usage

  1. Install the reinforcement learning library:

    cd rl
python -m pip install -e .

  2. Run reinforcement learning independently:

    python rl/train.py --task Template-Isaac-Velocity-Rough-Anymal-D-v0

  3. Run StrideSim:

    3-1. Execute the program:

    # After setting environment variables
ISAACSIM

    3-2. Configure the extension program:

    • Navigate to window -> extension.
    • Click the trident button to insert the extension program path (include up to the exts of this project).
    • Click the simulation button on the left (enabling AUTOLOAD is convenient).

    3-3. Run the extension program: Description of image You can now see the StrideSim_AnymalD tab in the Isaac Examples tab.

    Description of image By clicking the button, you can view scenes like the one above, and perform tasks such as calling anymalD, training, and parallel execution.

Code Formatting

pre-commit hook is used to automate code formatting.

Install pre-commit:

pip install pre-commit

Run pre-commit:

pre-commit run --all-files

License

This project is distributed under the MIT license.