All Projects → atenpas → gpg

atenpas / gpg

Licence: BSD-2-Clause license
Generate grasp pose candidates in point clouds

Programming Languages

C++
36643 projects - #6 most used programming language
CMake
9771 projects

Projects that are alternatives of or similar to gpg

mvp grasp
Multi-Viewpoint Picking (ICRA 2019)
Stars: ✭ 158 (+95.06%)
Mutual labels:  grasping
handle detector
ROS package to localize handles in 3D point clouds
Stars: ✭ 24 (-70.37%)
Mutual labels:  grasping
good robot
"Good Robot! Now Watch This!": Repurposing Reinforcement Learning for Task-to-Task Transfer; and “Good Robot!”: Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer
Stars: ✭ 84 (+3.7%)
Mutual labels:  grasping
icra20-hand-object-pose
[ICRA 2020] Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands
Stars: ✭ 42 (-48.15%)
Mutual labels:  grasping
graspnetAPI
Toolbox for our GraspNet-1Billion dataset.
Stars: ✭ 105 (+29.63%)
Mutual labels:  grasping
robotic-grasping
Antipodal Robotic Grasping using GR-ConvNet. IROS 2020.
Stars: ✭ 131 (+61.73%)
Mutual labels:  grasping
grasp multiObject
Robotic grasp dataset for multi-object multi-grasp evaluation with RGB-D data. This dataset is annotated using the same protocal as Cornell Dataset, and can be used as multi-object extension of Cornell Dataset.
Stars: ✭ 59 (-27.16%)
Mutual labels:  grasping
graspnet-baseline
Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)
Stars: ✭ 146 (+80.25%)
Mutual labels:  grasping
obman render
[cvpr19] Code to generate images from the ObMan dataset, synthetic renderings of hands holding objects (or hands in isolation)
Stars: ✭ 61 (-24.69%)
Mutual labels:  grasping
multi-contact-grasping
This project implements a simulated grasp-and-lift process in V-REP using the Barrett Hand, with an interface through a python remote API.
Stars: ✭ 52 (-35.8%)
Mutual labels:  grasping
PROBOT Anno
ROS Packages for PROBOT Anno.
Stars: ✭ 75 (-7.41%)
Mutual labels:  grasping
GrabNet
GrabNet: A Generative model to generate realistic 3D hands grasping unseen objects (ECCV2020)
Stars: ✭ 146 (+80.25%)
Mutual labels:  grasping
drl grasping
Deep Reinforcement Learning for Robotic Grasping from Octrees
Stars: ✭ 160 (+97.53%)
Mutual labels:  grasping
kuka rl
Reinforcement Learning Experiments using PyBullet
Stars: ✭ 65 (-19.75%)
Mutual labels:  grasping
graspit
The GraspIt! simulator
Stars: ✭ 142 (+75.31%)
Mutual labels:  grasping
graspnetAPI
API for large scale benchmark of robotic grasping: GraspNet-1Billion: https://graspnet.net
Stars: ✭ 33 (-59.26%)
Mutual labels:  grasping
graspit interface
A GraspIt! plugin exposing a ROS interface via graspit-ros
Stars: ✭ 29 (-64.2%)
Mutual labels:  grasping

Grasp Pose Generator (GPG)

1) Overview

This package creates grasp candidates for 3D point clouds and can check if they are antipodal using geometric conditions. To use the package, you only need PCL and Eigen (see below).

This package is part of GPD. Please notice that no machine learning is included in this part. The package just generates 6-DOF grasp poses for a 2-finger grasp.

2) Requirements

  1. PCL 1.7 or later
  2. Eigen 3.0 or later

3) Compilation

  1. Open a terminal and clone the grasp_candidates_generator repository into some folder:

    $ cd <location_of_your_workspace>
    $ git clone https://github.com/atenpas/gpg.git
    
  2. Build the project:

    $ cd grasp_candidates_generator
    $ mkdir build && cd build
    $ cmake ..
    $ make
    
  3. (optional) Install the project:

    $ sudo make install
    

4) Generate Grasp Candidates for a Point Cloud File

Run the following from within the build folder:

$ ./generate_candidates ../cfg/params.cfg ~/data/some_cloud.pcd

5) Parameters

Brief explanations of parameters are given in cfg/params.cfg.

6) Citation

If you like this package and use it in your own work, please cite our arXiv paper:

@misc{1603.01564,
Author = {Marcus Gualtieri and Andreas ten Pas and Kate Saenko and Robert Platt},
Title = {High precision grasp pose detection in dense clutter},
Year = {2016},
Eprint = {arXiv:1603.01564},
} 
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].