iris2333 Goto Github PK

agile_grasp

A ROS package to detect grasp poses in point clouds.

apriltag_ros

A ROS wrapper of the AprilTags 2 visual fiducial detector

arc-robot-vision

MIT-Princeton Vision Toolbox for Robotic Pick-and-Place at the Amazon Robotics Challenge 2017 - Grasp Detection and Image Matching for Novel Objects with Deep Learning

deep_learning_for_detectin_robotic_grasps

Code from Robot Learning Lab, Cornell in paper Deep Learning for Detecting Robotic Grasps

detection-of-robotic-grasp

easy_handeye

Simple, straighforward ROS library for hand-eye calibration

fastmaskrcnn

Mask RCNN in TensorFlow

fcis

Fully Convolutional Instance-aware Semantic Segmentation

ggcnn

Generative Grasping CNN from "Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach" (RSS 2018)

gpd

Detect grasp poses in point clouds

grasp-and-lift-eeg-challenge

Code and documentation for the winning sollution to the Grasp-and-Lift EEG Detection challenge

grasp-detector

Code to detect planar grasps

iai_kinect2

Tools for using the Kinect One (Kinect v2) in ROS

mask_rcnn

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

mastering_ros

This repository contains exercise files of the book "Mastering ROS for Robotics Programming"

models

Models and examples built with TensorFlow

moveit_simple_grasps

Generate basic grasp poses for simple objects such as blocks or cylinders

mvision

机器人视觉 移动机器人 VS-SLAM ORB-SLAM2 深度学习目标检测 yolov3 行为检测 opencv PCL 机器学习 无人驾驶

robot-grasp-detection

Detecting robot grasping positions with deep neural networks. The model is trained on Cornell Grasping Dataset. This is an implementation mainly based on the paper 'Real-Time Grasp Detection Using Convolutional Neural Networks' from Redmon and Angelova.

robotic-grasping-detection-program

shining-spot

tensorflow-yolo-v3

Implementation of YOLO v3 object detector in Tensorflow (TF-Slim)

ur3_ros-hardware

Universal Robot (UR3) Pick and Place Hardware Implementation with ROS using a USB Cam and an Electromagnetic Gripper

ur5_manipulation

The goal of the project is to implement robotic agents that could rapidly build structures from random objects in a disaster/crisis situation to facilitate operation of other robotic agents, or fast and affordable accommodation of the injured groups, e.g. to facilitate operation of rescue agents in a post-earthquake situation. We are proposing a system that employs robotics manipulators (UR5 industrial arm equipped with a gripper in our experiments) to stack objects with arbitrary shapes to construct a rigid wall. Some of the challenges in this problem are: 1) Planning the optimal stacking order and relative placing of the objects 2) Reliable grasping and transporting of arbitrarily shaped objects 3) Accurate detection and localization of the arm and the objects The system is being implemented over ROS to connect to and control the UR5 arm, and MoveIt package is employed to perform collision aware trajectory planning for the manipulator/grasper set. A variety of objects with different shapes and features, e.g. deformability, are considered for the experiments.

visual-pushing-grasping

Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.

yolov3_tensorflow