467
edits
Changes
no edit summary
== Setup - Linux ==
[https://github.com/kscalelabs/gym-kmanip https://github.com/kscalelabs/gym-kmanip]
'''Clone and install dependencies'''
<pre>
pip install pytest
pytest tests/test_env.py
</pre>
== Setup - Jetson Orin AGX ==
'''No conda on ARM64, install on bare metal'''
<pre>
sudo apt-get install libhdf5-dev
git clone https://github.com/kscalelabs/gym-kmanip.git && cd gym-kmanip
pip install -e .
</pre>
== Usage - Basic ==
'''Visualize the MuJoCo scene'''
<pre>
python gym_kmanip/examples/1_view_env.py
</pre>
'''Record a video of the MuJoCo scene'''
<pre>
python gym_kmanip/examples/2_record_video.py
</pre>
== Usage - Recording Data ==
'''K-Scale HuggingFace Datasets'''
'''Data is recorded via teleop, this requires additional dependencies'''
<pre>
pip install opencv-python==4.9.0.80
pip install vuer==0.0.30
pip install rerun-sdk==0.16.0
</pre>
'''Start the server on the robot computer'''
<pre>
python gym_kmanip/examples/4_record_data_teleop.py
</pre>
'''Start ngrok on the robot computer'''
<pre>
ngrok http 8012
</pre>
'''Open the browser app on the VR headset and go to the ngrok URL'''
== Usage - Visualizing Data ==
'''Data is visualized using rerun'''
<pre>
rerun gym_kmanip/data/test.rrd
</pre>
== Usage - MuJoCo Sim Visualizer ==
'''MuJoCo provides a nice visualizer where you can directly control the robot'''
'''Download standalone MuJoCo'''
<pre>
tar -xzf ~/Downloads/mujoco-3.1.5-linux-x86_64.tar.gz -C /path/to/mujoco-3.1.5
</pre>
'''Run the simulator'''
<pre>
/path/to/mujoco-3.1.5/bin/simulate gym_kmanip/assets/_env_solo_arm.xml
</pre>
== Citation ==
<pre>
@misc{teleop-2024,
title={gym-kmanip},
author={Hugo Ponte},
year={2024},
url={https://github.com/kscalelabs/gym-kmanip}
}
</pre>