Home

Awesome

ros_deep_grasp

This is the ROS implementation of our RA-L work 'Real-world Multi-object, Multi-grasp Detection'. The detector takes RGB-D image input and predicts multiple grasp candidates for a single object or multiple objects, in a single shot. The original arxiv paper can be found here. The final version will be updated after publication process.

If you find it helpful for your research, please consider citing:

@inproceedings{chu2018deep,
  title = {Real-World Multiobject, Multigrasp Detection},
  author = {F. Chu and R. Xu and P. A. Vela},
  journal = {IEEE Robotics and Automation Letters},
  year = {2018},
  volume = {3},
  number = {4},
  pages = {3355-3362},
  DOI = {10.1109/LRA.2018.2852777},
  ISSN = {2377-3766},
  month = {Oct}
}

If you encounter any questions, please contact me at fujenchu[at]gatech[dot]edu

Installation

Usage

open ROS master

roscore

run freenect for vision input

roslaunch freenect_launch freenect.launch

run grasp node

rosrun ros_deep_grasp grasp.py --net res50 --dataset grasp

Acknowledgement

Thanks to Anina Mu and all ORS18-19 team members (Joshua, Nicholas and Jianni) to develop this wrapper.