Python package for single and dual robot arm motion planning.
Key motivation:
Features: this packages provides two main things:
SingleArmPlanner
DualArmPlanner
Design goals:
โ Robustness and stability: provide an off-the-shelf motion planner that supports research by reliably covering most (not all) use cases at our labs, prioritizing dependability over niche, cutting-edge features.
๐งฉ Modularity and flexibility in the core components:
๐ Debuggability and transparency: many things can go wrong in motion planning, so we log generously and store debugging information (IK solutions, alternative paths) to troubleshoot issues.
๐งช Enable experimentation: Facilitate the benchmarking and exploration of experimental planning algorithms.
๐๏ธ Planned features:
Complete the Installation ๐ง and then see ๐ง Coming soon: 01_getting_started.ipynb
, where we set up:
airo-planner
is available on PyPI and installable with pip:
pip install airo-planner
๐ง Important post-installation step
We depend on ompl
with its Python bindings, which are not available on PyPI yet. The easiest way to install this for now is to use a pre-release wheel fom their Github:
pip install https://github.com/ompl/ompl/releases/download/prerelease/ompl-1.6.0-cp310-cp310-manylinux_2_28_x86_64.whl
For Python 3.11:
pip install https://github.com/ompl/ompl/releases/download/prerelease/ompl-1.6.0-cp311-cp311-manylinux_2_28_x86_64.whl
See the airo-mono
developer guide.
A very similar process and tools are used for this package.
See airo-models
, releasing airo-planner
works the same way.