Intrinsic MoveIt planning service
SoftwareMoveIt planning services and client skills for Intrinsic Core, with a documented offline mock-hardware route. [1]
Installation & first result →Official websiteGetting started
- For
- ROS 2 developers integrating motion and grasp planning [1]
- Hardware
- Documented UR5e with Robotiq Hand-E and wrist-mounted Orbbec Gemini 335Le [1]
- Source rights
- Named licenses are documented by part. Review licenses
- Unknowns
- operating system, compute requirements not fully established. Review gaps
Source researched · Not tested by us
Sources checked · Research details
Licenses & related hardware
- License
- Apache-2.0 · Details by part
Overview
This integration adds MoveIt and MoveIt Task Constructor motion-planning services and grasp-planning actions, plus C++ client skills, to Intrinsic Core. It is a distinct integration layer rather than the upstream MoveIt framework itself. The documented hardware description is a UR5e with a Robotiq Hand-E gripper and an Orbbec Gemini 335Le camera. [1]
Is this for you?
- Workflows
- Offline mock-hardware planning
- Connected Core scene synchronization
- Grasp-planning action goals and motion-planning service calls
- Known limitations
- Connected mode requires an appropriately configured flowstate_ros_bridge and Zenoh link
- The repository remains in active development
- Hardware description generalization remains future work
What you need
- Dependencies
- ROS 2 Lyrical or Jazzy workspace and corresponding .repos dependencies
- rosdep and colcon
- MoveIt and MoveIt Task Constructor
Installation & first result
Open the upstream getting-started guide [1]
- Import the dependency file for the chosen ROS distribution.
- Build the planning service and both client skills.
- For offline testing, set use_mock_hardware:=true and expect_collision_objects:=false.
- Add the target_box collision object and send a PlanGrasps action goal; use the separate service for motion planning.
- Installation
Import the matching lyrical.repos or jazzy.repos dependencies, run rosdep, and build the planning service and motion/grasp client skills with colcon.
Hardware, models & data
- Supported hardware
- Documented UR5e with Robotiq Hand-E and wrist-mounted Orbbec Gemini 335Le
- Inputs and outputs
Scene objects and a PlanGrasps action goal produce ranked grasp candidates; motion planning remains a separate ROS service.
- File formats
- URDF/Xacro
- SRDF
- ROS services, messages and actions
Project notes
A cluster is optional for the first planning request
The README offers an offline route with mock hardware. Create a ROS workspace, import either lyrical.repos or jazzy.repos, resolve dependencies with rosdep and build the planning service and both skills with colcon. Launch with use_mock_hardware:=true and expect_collision_objects:=false; without the latter setting, the node can wait for a scene that no cluster is providing. [1]
The example then inserts a small collision box into the planning scene and sends a moveit_planning_interfaces/action/PlanGrasps goal to /grasp_planning/plan_grasps. The current interface is a ROS action, so older grasp-service calls need updating. That gives a concrete first check: inspect returned grasp candidates and pre-grasp poses before involving a physical arm. The README also provides a motion-planning service request; the responses shown are upstream examples, not results reproduced here. [1]
Connecting Core adds scene and transport requirements
Connected mode requires the workcell's flowstate_ros_bridge, including configuration for transforms and joint states, and a Zenoh connection on port 7447. Simply starting the offline node does not establish synchronization with an Intrinsic workcell. The README identifies Core as the primary deployment environment and a separate Flowstate route for licensed users. [1]
We reviewed v0.0.3, published October 13 as a prerelease at commit f0ee7c974873f2dc95fe16e20068865bd109a352; no stable release is listed. Its release note says the planning-service bundle exceeds GitHub’s 2 GB attachment limit, so do not assume every bundle is available as a release download. The repository calls out active development and future work on abstract hardware definitions. Its Apache-2.0 root license covers repository software; external dependencies and hardware geometry need their own scope checks. No installation, plan-quality benchmark or hardware execution was performed for this profile. [1] [2] [90]
What we checked
Source research only. No installation, upstream test execution, physical integration or performance measurement by this publication. No affiliation or endorsement claimed.
Not yet established
- Requirements: operating system, host computer
Updates
Source files and licenses
Useful open software component with documented development workflow; dependency rights, configuration matching and runtime results remain separate.
| Layer | Availability / license |
|---|---|
| software | available · Apache-2.0 Inspected root license for this repository. External dependencies, vendor SDKs, models and third-party geometry are not relicensed by it. [1] [2] |
| documentation | available · Apache-2.0 Inspected root license for this repository. External dependencies, vendor SDKs, models and third-party geometry are not relicensed by it. [1] [2] |
No particular model weights or dataset is offered or assessed by this component profile.
References
Each source links to the exact revision we read. “Used for” shows where this page relies on it.
Project sources
- S001 intrinsic-moveit: README.md
Revision, date & where cited
Intrinsic Innovation LLC / project contributors · github.com · revision
f0ee7c9· Accessed Oct 18, 2026
Used for: Overview, Is this for you?, What you need, Installation & first result and 4 more - S002 intrinsic-moveit: LICENSE
Revision, date & where cited
Intrinsic Innovation LLC / project contributors · github.com · revision
f0ee7c9· Accessed Oct 18, 2026
Used for: Connecting Core adds scene and transport requirements, Source files and licenses - S090 intrinsic-ai/intrinsic-moveit: commit f0ee7c9
Release metadata and exact reviewed commit.Revision, date & where cited
Intrinsic Innovation LLC / GitHub metadata · github.com · v0.0.3 prerelease / · Accessed Oct 18, 2026
Used for: Connecting Core adds scene and transport requirements, What we checked
Videos
- S091 Intrinsic (YouTube channel)
The project’s own YouTube channel, found by searching YouTube and checked against the channel page. Not reviewed by us for accuracy.Revision, date & where cited
YouTube channel Intrinsic · youtube.com · Accessed Oct 4, 2026
Correction guidance · Discussion is not enabled · Profile format 0.7.0-draft.5
Change history
2026-09-30 — Initial pinned-source component profile with setup route and integration boundaries.
2026-10-04 — Added 1 YouTube reference(s) (S091): official channel or videos linked from the pinned upstream sources. Existing claims, source-check dates and evidence are unchanged.