Skip to content

xArm-Developer/ufactory_vision

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

56 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ufactory_vision

中文版说明 (Chinese Version)

Project Overview

ufactory_vision is a vision-based grasping demo project based on UFACTORY robot arms. Users can quickly implement vision-based object detection and grasping with this project.

Watch the video

Hardware Requirements

Hardware Configuration for Example Scripts

Robot Arm Model Camera Model End Effector
xArm 5/6/7 or 850 Intel Realsense D435 / Luxonis OAK-D-Pro-PoE UFACTORY Gripper
Lite 6 Intel Realsense D435 / Luxonis OAK-D-Pro-PoE Lite 6 Vacuum Gripper

Configuration with Intel Realsense D435 Camera

Configuration with Luxonis OAK-D-Pro-PoE Camera

Software

Supported Python Versions

Supported Python versions: 3.8-3.11 (Recommended: 3.11).

Installation

1. Clone the Repository

git clone https://github.com/xArm-Developer/ufactory_vision.git
cd ufactory_vision

2. Create a Python Virtual Environment

It is recommended to use a virtual environment for running this project.

Windows (Using Anaconda)

conda create --name ufactory_vision python=3.11
conda activate ufactory_vision

Linux (Using venv)

python3.11 -m venv ufactory_vision
source ufactory_vision/bin/activate

3. Install Dependencies and Run Examples

Please follow the corresponding installation and execution steps based on the camera model you are using. First, ensure you are in the ggcnn_grasping_demo directory:

cd ggcnn_grasping_demo

Using Intel Realsense D435 Camera

  1. Install Dependencies

    pip install -r requirements_rs.txt
  2. Run Example

    Replace 192.168.1.xxx with the actual IP address of your robot arm controller.

    • UFACTORY 850 or xArm 5/6/7 Series Robot Arm
      python run_rs_grasp.py 192.168.1.xxx
    • UFACTORY Lite 6 Robot Arm
      python run_rs_grasp_lite6.py 192.168.1.xxx

Using Luxonis OAK-D-Pro-PoE Camera

  1. Install Dependencies

    pip install -r requirements_depthai.txt
  2. Run Example

    Replace 192.168.1.xxx with the actual IP address of your robot arm controller.

    • UFACTORY 850 or xArm 5/6/7 Series Robot Arm
      python run_depthai_grasp.py 192.168.1.xxx
    • UFACTORY Lite 6 Robot Arm
      python run_depthai_grasp_lite6.py 192.168.1.xxx

Important Notes

  • TCP/Coordinate Offset: Do not set TCP offset or coordinate offset, otherwise you may need to fine-tune the code.
  • TCP Payload: Set TCP payload to avoid false collision detection.
  • Collision Detection: Before running the example, ensure that collision detection is enabled. It is recommended to set the collision sensitivity to 3 or higher.

License

This project is licensed under the BSD 3-Clause License. For details, please check the LICENSE file.

Acknowledgements

Our demo project is built based on the following open-source projects:

About

Vision demos for UFactory robots xArm 5/6/7, Lite6 and 850

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages