OMPL (Open Motion Planning Library) is the flagship open-source library of sampling-based motion planning algorithms, developed since 2008 at the Kavraki Lab, Rice University in Houston. Creators: Ioan Şucan, Mark Moll, and Lydia Kavraki (one of the pioneers of probabilistic motion planners — co-author of the PRM algorithm from 1996). BSD-3-Clause license.
OMPL implements over a dozen planner families: RRT and its variants (RRT-Connect, RRT*, RRT#, Informed RRT*, BIT*, AIT*), PRM (Probabilistic Roadmap), EST (Expansive Space Trees), KPIECE, SBL (Single-query Bidirectional Lazy), SST, FMT*, and dynamic planners (KPIECE with controls). The library is agnostic about robot representation — it only requires the user to provide a collision-checker, state sampler, and forward propagation function.
OMPL sits under the hood of most motion planning frameworks: MoveIt (as the default planning engine), OpenRAVE, Drake (one of the available backends), and many academic projects. Bindings: Python (official), C# (community). Active quarterly releases, ~30 commits/month on the main branch.
An API Library is a software package that exposes programmatic interfaces for communicating with a device, service, or system. In robotics it typically forms a lightweight integration layer built on top of the manufacturer's official API or an open-source project, abstracting low-level protocol details and providing language-native bindings (Python, C++, Java, etc.).
A family of open-source libraries for motion planning (RRT, PRM, Lazy-PRM), inverse kinematics, rigid-body dynamics, and trajectory optimization: MoveIt, OMPL, Pinocchio, Drake, RBDL, TrajOpt, KDL, Bullet, iDynTree.
MoveIt (default planner), OpenRAVE, Drake, NASA JPL Mars Rovers (Curiosity, Perseverance — offline arm planning variant), Toyota Research Institute, DARPA Robotics Challenge, plus hundreds of academic papers each year. Built into 90%+ of ROS manipulation tutorials.
github.com/ompl/ompl ~830★, ompl.kavrakilab.org with Doxygen documentation + tutorials, ompl-users mailing list (>2k subscribers), > 2000 publications citing OMPL (Şucan et al., IEEE RAM 2012).
Boston Dynamics bipedal humanoid robot. The fully electric generation unveiled in 2024 succeeds the hydraulic Atlas that was retired after more than a decade of research.
Bipedal humanoid robot by Unitree Robotics, designed as a compact research, development, and developer platform.
Unitree H1 is a full-size general-purpose humanoid robot (~180 cm, ~47 kg). Bipedal, 5 DOF per leg + 4 DOF per arm, 3.3 m/s walking speed, 360° perception via 3D LiDAR + depth camera, Unitree M107 PMSM joint motors with ~360 N·m peak knee torque. Standard compute: Intel Core i5/i7; optional NVIDIA Jetson Orin NX.
Purely algorithmic library; integration with a robot requires a collision checker (e.g. FCL).
License family: Permissive
C++20 support, improved Python bindings (pybind11).
New SST planner (Stable Sparse Tree), C++17 fixes.
State API refactor, Python 3 bindings.
Support for Informed RRT*, BIT*, AIT*.
Stable API, full integration with MoveIt.
First public open-source release.
