1. Authors
2. Required packages - Kinetic Version
3. Easy install
4. Run GGCNN in Gazebo and RVIZ

Back to the top

• M.Sc. Caio Viturino* - [Lattes] [Linkedin] - engcaiobarros@gmail.com
• M.Sc. Kleber de Lima Santana Filho** - [Lattes] [Linkedin] - engkleberf@gmail.com
• M.Sc. Daniel M. de Oliveira* - [Linkedin] - danielmoura@ufba.br
• Prof. Dr. André Gustavo Scolari Conceição* - [Lattes] - andre.gustavo@ufba.br

*LaR - Laboratório de Robótica, Departamento de Engenharia Elétrica e de Computação, Universidade Federal da Bahia, Salvador, Brasil

**PPGM - Programa de Pós-Graduação em Mecatrônica, Universidade Federal da Bahia, Salvador, Brasil.

Back to the top

This code was developed with Python 2.7 on Ubuntu 16.04 with ROS Kinetic.

It is recommended to follow the EASY INSTALL step below

• Realsense Gazebo Plugin
• Realsense-ros Release version 2.2.11
• Librealsense Release version 2.31.0 - Install from source
• Moveit Kinetic
• Moveit Python
• Robotiq Gripper
• Universal Robot
• ur_modern_driver
• Gluoncv
• Opencv
• Mxnet Install Mxnet for your CUDA version.

NOTE: This package should be placed into your src folder. Please open an issue if you find any problem related to this package.

In order to run the experiment you will need a trained .params (Contact the authors to download the .params) Create a folder called params inside the selective_grasping folder and put the .params there. Remember to rename the .params files and related variables in detect.py

Back to the top

In order to install all the required packages easily, create a new catkin workspace

mkdir -p ~/catkin_ws_new/src

Clone this repository into the src folder

cd ~/catkin_ws_new/src
git clone https://github.com/caiobarrosv/selective_grasping

Run the install.sh file

cd ~/catkin_ws_new/src/selective_grasping/install
./install.sh

Back to the top

THE GAZEBO SIMULATION IS NOT WORKING PROPERLY. THE GRASPS ARE UNSTABLE AND NEED TO BE FIXED. THE SIMULATION IS USED ONLY TO RUN EXPERIMENTS PRIOR TO THE REAL WORLD APPLICATION TO AVOID ACCIDENTS

Please follow each following steps:

roslaunch selective_grasping gazebo_ur5.launch

Press enter after the following message appears and jump to the step 4.3: "==== Press enter to move the robot to the 'depth cam shot' position!"

rosrun selective_grasping ur5_open_loop.py --gazebo

rosrun selective_grasping detect.py --gazebo

Press enter after the following message appears and jump to the step 4.5: "Press enter to start the GGCNN"

rosrun selective_grasping run_ggcnn.py --gazebo

rosrun selective_grasping spawn_objects.py

After running the GG-CNN node you are able to move the robot and perform the grasp using the terminal provided by step 4.2

It will speed up your Gazebo simulation a little bit :)

rosrun selective_grasping change_gazebo_properties.py

You might want to see the grasp or any other image. In order to do that, you can use the rqt_image_view.

rosrun rqt_image_view

If you want to visualize the data being published by the Intel Realsense D435 please run the following node:

rosrun selective_grasping rviz_ur5.launch