GraspMolmo
- AI model
- Robot arms and industry
GraspMolmo is a model for task-oriented robotic grasping, choosing which predicted grasp suits a given task from an RGB-D view. It comes with code for generating synthetic data.
- Stale
Made by Ai2, United States (checked on github.com/allenai (opens in a new tab)).
Source on GitHub: github.com/abhaybd/GraspMolmo (opens in a new tab). Facts read at commit 73990b5 (opens in a new tab).
Licenses
- Code
- MIT (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit 73990b5 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
Labels
- StaleNo commit in 12 months: the newest is from 9 Oct 2025.
What it does
- Picks the grasp from a set of candidate grasps that fits a natural-language task, using an RGB image and point cloud.
- Candidate grasps come from an external grasp predictor such as M2T2, expressed in the camera frame.
- Provides a Python inference interface through a GraspMolmo class with a pred_grasp method.
- Includes a pipeline for generating large-scale synthetic grasping data, described in DATA.md.
- Can also generate TaskGrasp-Image, a dataset released alongside the project.
- Installable with pip extras for data generation, TaskGrasp-Image generation, or inference only.
Written by Robotheca from the project's README (opens in a new tab) at commit 73990b5.
Getting started
- Difficulty
- Advanced
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Stale: no commit in 12 months
- Newest commit
- 9 Oct 2025 on main
- Latest release
- None published on GitHub
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists AI models as a reference: nothing is hosted or run here, and every fact links to where it was read.