mkt1412/GraspGPT_public

code implementation of GraspGPT and FoundationGrasp

38
/ 100
Emerging

This project helps industrial automation engineers and roboticists program robotic arms to grasp objects for specific tasks. It takes in 3D sensor data (point clouds) of an object, along with a natural language description of the task (e.g., "scoop with spatula"), and outputs precise robotic grasp poses optimized for that action. This enables robots to interact with objects intelligently and perform complex manipulations in unstructured environments.

143 stars.

Use this if you need to train or deploy robotic systems that perform task-oriented grasping, allowing robots to understand and execute actions like pouring, scooping, or drinking with various objects.

Not ideal if you are looking for a pre-built, production-ready grasping solution that doesn't require familiarity with machine learning frameworks and robotic perception.

Robotics Industrial Automation Robot Grasping Manipulation Human-Robot Interaction
No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

143

Forks

16

Language

Python

License

Last pushed

Dec 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/mkt1412/GraspGPT_public"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.