- Simulation to Simulation framework is available on sim2sim_onnx branch
- You can simply inference trained policy (basically export as .onnx from isaac lab)
https://docs.omniverse.nvidia.com/isaacsim/latest/installation/index.html
https://isaac-sim.github.io/IsaacLab/source/setup/installation/index.html
- Set the ISAACSIM_PATH environment variable to point to your isaaclab installation directory(register on your environment [.bashrc])
export ISAACSIM_PATH="${HOME}/.local/share/ov/pkg/isaac-sim-4.0.0" export ISAACSIM_PYTHON_EXE="${ISAACSIM_PATH}/python.sh" export ISAACLAB_PATH="${HOME}/IsaacLab"
- clone repository
git clone -b flamingo_isaac_lab_envs
- replace 'source' folder into your isaaclab 'source' folder
cp ${HOME}/lab.flamingo/modified_source/source ${HOME}/IsaacLab/source
- install lab.flamingo pip package by running below command
${ISAACLAB_PATH}/isaaclab.sh -p -m pip install --upgrade pip ${ISAACLAB_PATH}/isaaclab.sh -p -m pip install -e .
on lab.flamingo root path, type
${ISAACLAB_PATH}/isaaclab.sh -p scripts/rsl_rl/train.py --task Isaac-Velocity-Flat-Flamingo-v1 --num_envs 4096 --headless
${ISAACLAB_PATH}/isaaclab.sh -p scripts/rsl_rl/play.py --task Isaac-Velocity-Flat-Flamingo-Play-v1 --num_envs 32