gpd

Grasp Pose Detector

Software package for detecting grasp poses in 3D point clouds.

Detect 6-DOF grasp poses in point clouds

GitHub

646 stars
19 watching
236 forks
Language: C++
last commit: almost 3 years ago
Linked from 2 awesome lists

graspingroboticsros

Backlinks from these awesome lists:

Related projects:

Repository Description Stars
atenpas/agile_grasp Detects grasp poses in 3D point clouds using computer vision and robotics algorithms. 74
atenpas/gpg Generates 6-DOF grasp poses for robotic grasping tasks from point clouds 104
atenpas/grasp_selection A package that selects the most suitable grasp poses from multiple candidates based on reachability and movement efficiency. 16
lerrel/grasp-detector A Python-based system for detecting planar grasps using machine learning models. 45
mirsking/deep_learning_for_detectin_robotic_grasps Research code for detecting robotic grasps using deep learning algorithms 42
dougsm/ggcnn A deep learning-based system for generating precise grasp poses for robots in real-time 525
charlesq34/frustum-pointnets A deep learning framework for 3D object detection from RGB-D data 1,598
carlosmccosta/object_recognition A ROS package that estimates the 3D pose of objects on a plane or conveyor using various techniques such as feature matching and ICP registration. 17
oniietzschan/bump-3dpd A Lua library for fast and simple axis-aligned 3D collision detection 77
vmarsocci/3dcd Automatically inferring 2D and 3D change detection maps from bitemporal optical images without relying on DSMs. 29
robot-perception-group/airpose A deep learning framework for multi-view fusion network-based 3D human motion capture system 52
moveit/moveit_grasps A C++ library for generating grasp approaches and directions for objects in 3D space. 97
aweptimum/strike An open-source 2D collision detection library using the Separating-Axis Theorem for Lua 28
nvlabs/deep_object_pose Estimates object poses and positions in 3D space from RGB images 1,031
cpaxton/contact_graspnet This project provides a system to predict 6-DoF grasp distributions from raw point clouds in cluttered scenes. 2