Autolife-Planning

A planning library for the Autolife robot. It provides inverse kinematics (TRAC-IK and Pink), motion planning (VAMP), and collision-aware planning through a unified Python interface.

Features

• Inverse Kinematics — TRAC-IK (unconstrained) and Pink (QP-based constrained) solvers with CoM stability, camera stabilization, and self-collision avoidance
• Motion Planning — VAMP-based planner with collision checking, path validation, and subgroup planning
• Time Parameterization — TOPP-RA converts planned paths into executable trajectories with velocity/acceleration limits
• Collision Geometry — Spherized URDF representations for efficient collision detection, pointcloud obstacle support

Quick Start

Platform: Linux, Python 3.12+.

For inference — running the planners and IK solvers — just pip install:

git clone --recursive https://github.com/AdaCompNUS/Autolife-Planning.git
cd Autolife-Planning
pip install -e .

For development — rebuilding URDFs, regenerating FK headers, running the C++ toolchain end-to-end — use the setup script, which also installs pixi and the conda-forge deps (pinocchio, orocos-kdl, eigen, boost, ...):

bash scripts/setup.sh

See the Getting Started guide for detailed installation options.

Usage

# Inverse kinematics
pixi run python examples/ik/basic.py
pixi run -e dev python examples/ik/basic_vis.py           # PyBullet visualization
pixi run -e dev python examples/ik/constrained_vis.py     # Pink QP with CoM stability

# Motion planning
pixi run -e dev python examples/planning/motion.py
pixi run python examples/planning/subgroup.py
pixi run -e dev python examples/planning/constrained/plane.py
pixi run -e dev python examples/planning/cost/orientation_lock.py

# Time parameterization
pixi run python examples/planning/time_parameterization.py

# End-to-end pick-and-place demo (the video above)
pixi run -e dev python examples/demos/rls_pick_place.py

# Tests
pixi run -e dev test

Project Structure

autolife_planning/     # Core Python package
  kinematics/          # TRAC-IK + Pink IK, FK, collision checking
  planning/            # VAMP motion planning, cost + constrained planners
  trajectory/          # TOPP-RA time parameterization
  envs/                # Simulation environments (PyBullet)
  types/               # Shared dataclasses (SE3Pose, PlannerConfig, PlanningResult, ...)
  resources/           # Packaged URDFs, meshes and point clouds
ext/
  ompl_vamp/           # OMPL + VAMP planner extension, generated FK header
  time_parameterization/ # Vendored TOPP-RA C++ core (nanobind)
  trac_ik/             # Vendored TRAC-IK C++ (pybind11)
third_party/
  cricket/             # FK code generator
  foam/                # Collision geometry processing (editable PyPI dep, robot env)
  ompl/                # OMPL, built from source into _ompl_vamp
  vamp/                # VAMP collision checking (header-only, compiled into _ompl_vamp)
examples/
  ik/                  # TRAC-IK + Pink examples
  planning/            # Motion, subgroup, cost, constrained planning demos
  demos/               # End-to-end scenarios (rls_pick_place, ...)
tests/                 # Pytest suite (CI)
scripts/
  render_videos/       # Docs/demo video pipeline
  ...                  # Setup, build, spherize, FK codegen
resources/             # Robot URDF and mesh files
assets/                # Scene pointclouds and env meshes
docs/                  # MkDocs site sources (GitHub Pages)

Acknowledgements

This project builds on several outstanding open-source libraries:

• VAMP — SIMD-accelerated motion planning and collision checking (Kavrakilab, Rice University).
• OMPL — The Open Motion Planning Library (Kavrakilab, Rice University).
• TOPP-RA — Reachability-analysis-based time-optimal path parameterization (MIT, © Hung Pham). Its C++ core is vendored unmodified under ext/time_parameterization/toppra/.
• TRAC-IK — Inverse kinematics solver (TRACLabs).